Recommendation method and storage device for pesticides for special small crops pest control based on rule association
Through a rule-related method, the drug use plan for special small crops is recommended using the association rule base, which solves the problem of pests and diseases of special small crops, and achieves precise drug use and scientific recommendations, reducing the risk of drug resistance.
Patent Information
- Application Number
- CN202110696145.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-06-23
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2041-06-23
AI Technical Summary
When pests occur in characteristic small crop varieties, the existing technology is difficult to provide accurate drug use information, resulting in high risk of pesticide use and increased drug-resistant pests and diseases, making it difficult to effectively prevent and control it.
Using a rule-based association method, we pre-establish the association rule database, obtain information from the pest and disease database and pesticide database, use the association rule algorithm to calculate the appropriate frequent item set of drug formulas, build the association rule database, and recommend the target characteristic small crops. Medication plan.
It has achieved accurate recommendations for pests and diseases of characteristic small crops, reduced the risk of pesticide use, improved the scientificity and accuracy of medication, and met the scientific drug use needs of characteristic small crops.
Smart Images

Figure CN113849724B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of plant protection, and in particular to a method and storage device for recommending drugs for controlling pests and diseases of specialty small crops based on rule association. Background Art
[0002] Pesticides are the most widely used means of preventing and controlling crop diseases and pests in agricultural production. The scientific use of pesticides is not only related to the safety of agricultural product quantity, but also closely related to the quality of agricultural products. Pest and disease prevention and control is still one of the links in the current agricultural production process that employs the most labor, has the highest intensity, and has the highest technical requirements. On the one hand, a certain disease and pest can be prevented and controlled by a variety of pesticides, and on the other hand, many pesticides have the function of preventing and controlling multiple diseases and pests. Although this brings more choices to users, it greatly increases the difficulty for farmers and even plant protection workers to make accurate choices.
[0003] The long-term and large-scale use of chemical pesticides has led to an increase in the types of pesticide-resistant pests and diseases, and the resistance has become increasingly severe. It is difficult for farmers to fully grasp the applicable objects and safe use methods of various pesticides. Especially for specialty small crops, because there are fewer types of pesticides registered by the state, they cannot meet the actual needs of specialty small crops when they are sick. When specialty small crops are affected by diseases and pests, actual production is mainly based on literature reports and experience. The use of pesticides is risky. How to provide more accurate drug use information for specialty small crops has become an urgent problem to be solved. Summary of the invention
[0004] Therefore, it is necessary to provide a method for recommending pesticides for specialty small crops based on rule association to solve the problem that the use of pesticides for specialty small crops is mainly based on experience and cannot provide more accurate pesticide information for specialty small crops. The specific technical solution is as follows:
[0005] The method for recommending pesticides for pest control of specialty small crops based on rule association includes the following steps:
[0006] Input the target specialty minor crops into the pre-established association rule library;
[0007] The range of drug formulas under the same family classification of the target specialty minor crops is obtained in the pre-established association rule library, and drug recommendations are made for the target specialty minor crops.
[0008] Furthermore, the step of “inputting target specialty minor crops into a pre-established association rule library” specifically includes the following steps:
[0009] Obtain disease information and pest information from a pest database to construct a first set;
[0010] Obtain the pesticide information of the control object from the pesticide database to construct the second set;
[0011] Reading registered crop information from the pesticide database, and combining the crop family classification tree to construct a third set;
[0012] Calculate the first set and the second set by using an association rule algorithm, and construct a fourth set based on the calculation results;
[0013] An association rule base is constructed by the association rules of the third set and the association rules of the fourth set.
[0014] Furthermore, the “obtaining the range of drug formulas for the target specialty minor crops in the same family classification in the pre-established association rule library, and recommending drugs for the target specialty minor crops” specifically includes the following steps:
[0015] The range of drug formulas for the target specialty minor crops in the same family classification is obtained through the association rules of the third set;
[0016] The association rules of the fourth set are used to recommend drugs for target specialty small-scale crops with the same pathogens or pests.
[0017] Furthermore, the “calculating the first set and the second set by an association rule algorithm, and constructing a fourth set from the calculation results” specifically includes the following steps:
[0018] The frequent item sets and the support of the frequent item sets of the medication prescriptions of the prevention and treatment objects are calculated by the association rule algorithm. The suitable frequent item sets of the medication prescriptions are obtained by screening the support of the frequent item sets. The suitable association rules are determined by using the filtered frequent item sets of the medication prescriptions to form the fourth set.
[0019] Furthermore, the “obtaining disease information and pest information from the pest database to construct a first set” specifically includes the following steps:
[0020] Reading disease information from the pest database, obtaining the disease name and the category to which the pathogen belongs; reading pest information from the pest database, obtaining the pest name and the category to which the pest belongs, and constructing a first set;
[0021] The “obtaining pesticide information of control objects from the pesticide database to construct a second set” specifically includes the following steps:
[0022] The information of the control target is read from the pesticide database, and the name of the control target and the drug formula are obtained to form the second set.
[0023] In order to solve the above technical problems, a storage device is also provided, and the specific technical solution is as follows:
[0024] A storage device having an instruction set stored therein, wherein the instruction set is used to execute:
[0025] Input the target specialty minor crops into the pre-established association rule library;
[0026] The range of drug formulas under the same family classification of the target specialty minor crops is obtained in the pre-established association rule library, and drug recommendations are made for the target specialty minor crops.
[0027] Furthermore, the instruction set is also used to execute: the step of “inputting target specialty minor crops into a pre-established association rule library” specifically includes the following steps:
[0028] Obtain disease information and pest information from a pest database to construct a first set;
[0029] Obtain the pesticide information of the control object from the pesticide database to construct the second set;
[0030] Reading registered crop information from the pesticide database, and combining the crop family classification tree to construct a third set;
[0031] Calculate the first set and the second set by using an association rule algorithm, and construct a fourth set based on the calculation results;
[0032] An association rule base is constructed by the association rules of the third set and the association rules of the fourth set.
[0033] Furthermore, the instruction set is also used to execute: the "obtaining the range of drug prescriptions under the same family classification of the target specialty minor crops in the pre-established association rule library, and recommending drugs for the target specialty minor crops", specifically including the steps of:
[0034] The range of drug formulas for the target specialty minor crops in the same family classification is obtained through the association rules of the third set;
[0035] The association rules of the fourth set are used to recommend drugs for target specialty small-scale crops with the same pathogens or pests.
[0036] Furthermore, the instruction set is also used to execute: the "calculating the first set and the second set by an association rule algorithm, and constructing a fourth set from the calculation results", which specifically includes the steps of:
[0037] The frequent item sets and the support of the frequent item sets of the medication prescriptions of the prevention and treatment objects are calculated by the association rule algorithm. The suitable frequent item sets of the medication prescriptions are obtained by screening the support of the frequent item sets. The suitable association rules are determined by using the filtered frequent item sets of the medication prescriptions to form the fourth set.
[0038] Furthermore, the instruction set is also used to execute: the step of “obtaining disease information and pest information from a pest database to construct a first set” specifically includes the following steps:
[0039] Reading disease information from the pest database, obtaining the disease name and the category to which the pathogen belongs; reading pest information from the pest database, obtaining the pest name and the category to which the pest belongs, and constructing a first set;
[0040] The “obtaining pesticide information of control objects from the pesticide database to construct a second set” specifically includes the following steps:
[0041] The information of the control target is read from the pesticide database, and the name of the control target and the drug formula are obtained to form the second set.
[0042] The beneficial effect of the present invention is that the method for recommending drugs for pest control of specialty small crops based on rule association includes the steps of: inputting target specialty small crops into a pre-established association rule library; obtaining the drug formula range under the same family classification of the target specialty small crops in the pre-established association rule library, and recommending drugs for the target specialty small crops. By pre-establishing an association rule library and then obtaining drug recommendations in the association rule library, drug recommendations have a basis to follow, and more accurate and scientific drug recommendations can be made. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] Figure 1 This is a flow chart of a method for recommending pesticides for special small crops pest control based on rule association as described in a specific implementation method;
[0044] Figure 2 A flowchart of establishing an association rule base as described in a specific implementation method;
[0045] Figure 3 This is a schematic diagram of a method for recommending pesticides for controlling pests and diseases of specialty small crops based on rule association according to a specific implementation method;
[0046] Figure 4 A module schematic diagram of a storage device described in a specific implementation manner.
[0047] Description of reference numerals:
[0048] 400. Storage device. DETAILED DESCRIPTION
[0049] In order to explain the technical content, structural features, achieved objectives and effects of the technical solution in detail, the following is a detailed description in conjunction with specific embodiments and accompanying drawings.
[0050] See also Figures 1 to 3In this embodiment, the rule-based association-based drug recommendation method for specialty small crop pest control can be applied to a storage device, including but not limited to: a personal computer, a server, a general-purpose computer, a special-purpose computer, a network device, an embedded device, a programmable device, an intelligent mobile terminal, etc. The specific technical solution can be as follows:
[0051] Step S101: input target specialty minor crops into a pre-established association rule library.
[0052] Step S102: obtaining the range of drug prescriptions under the same family classification of the target specialty minor crops in the pre-established association rule library, and making drug recommendations for the target specialty minor crops.
[0053] A method for recommending drugs for pest control of specialty small crops based on rule association includes the steps of: inputting target specialty small crops into a pre-established association rule library; obtaining the drug formula range under the same family classification of the target specialty small crops in the pre-established association rule library, and recommending drugs for the target specialty small crops. By pre-establishing an association rule library and then obtaining drug recommendations in the association rule library, drug recommendations have a basis to follow, and more accurate and scientific drug recommendations can be made.
[0054] like Figure 2 As shown, the following will explain in detail how to pre-establish the association rule base:
[0055] Step S201: Obtain disease information and pest information from the pest database to construct a first set. Specifically, the steps include: reading disease information from the pest database to obtain the name of the disease and the classification of its pathogen, reading pest information from the pest database to obtain the name of the pest and the classification of its pest, and constructing the first set. The classification of the pathogen includes the species name and the genus name, and the classification of the pest includes the species name and the family name, which constitute the first set (disease-pathogen association rules, pest-insect association rules).
[0056] Example 1 (disease): Read cabbage downy mildew from the pest and disease database, obtain the disease name "cabbage downy mildew", pathogen genus name "Peronospora", and species name "parasitic downy mildew", and form the first set (association rule: cabbage downy mildew-Peronospora);
[0057] Example 2 (pests): Read the cabbage armyworm from the pest database, obtain the pest name "cabbage armyworm", the pest classification family name "Noctuidae", and the species name "Spodoptera litura", and form the first set (association rule: cabbage armyworm-Noctuidae).
[0058] Step S202: Obtain the drug information of the control object from the pesticide database to construct the second set. Read the control object information from the pesticide database, obtain the name of the control object (disease, pest) and the drug formula, and form the second set (disease-drug formula, pest-drug formula data set).
[0059] Example 3 (disease): Read the pesticide control information of cabbage downy mildew and cabbage downy mildew from the pesticide database, obtain the control objects "cabbage downy mildew", "cabbage downy mildew", and the drug formula "propineb (70% wettable powder)", and form the second set (cabbage downy mildew-propineb (70% wettable powder), cabbage downy mildew-propineb (70% wettable powder));
[0060] Example 4 (insect pests): Read the information on the control of cabbage armyworm using pesticides from the pesticide database, obtain the control targets "cabbage armyworm", "cabbage armyworm", and the drug formula "cyantraniliprole (10% dispersible oil suspension)", and form the second set (cabbage armyworm-cyantraniliprole (10% dispersible oil suspension); cabbage armyworm-cyantraniliprole (10% dispersible oil suspension)).
[0061] Step S203: Read the registered crop information from the pesticide database, and build a third set in combination with the crop family classification tree. The third set includes: a crop-drug formula association rule data set.
[0062] Example 5 (Pests and diseases): Read the registered crop "cabbage" from the pesticide control dataset, and combine it with the crop family classification tree (Cruciferae) to form the third set (Cruciferae - Propineb (70% wettable powder), Cruciferae - Cyantraniliprole (10% dispersible oil suspension)).
[0063] Step S204: Calculate the first set and the second set by using an association rule algorithm, and construct a fourth set with the calculation results. Specifically, the steps include:
[0064] The pathogen classification tree-drug formula and pest classification tree-drug formula of the control objects (disease name, pest name) are obtained from the first set and the second set, and the frequent item sets and frequent item set support of the control object drug formula are calculated through the association rule algorithm. The suitable frequent item set of drug formula is obtained by screening the support of the frequent item set, and the suitable association rules are determined using the filtered frequent item set of drug formula to form the fourth set.
[0065] Example 6 (disease): Obtain the pathogen classification tree of the control object "Cabbage Downy Mildew - Downy Mildew - Propineb (70% wettable powder)" from the first set and the second set; "Cabbage Downy Mildew - Downy Mildew - Propineb (70% wettable powder)"; Use the association rule algorithm to filter out the association rule "Downy Mildew - Propineb (70% wettable powder)" to form the fourth set;
[0066] Example 7 (Pests): Obtain the pest classification trees of the control targets "Cabbage armyworm - Noctuidae - Cyantraniliprole (10% dispersible oil suspension)" and "Cabbage armyworm - Noctuidae - Cyantraniliprole (10% dispersible oil suspension)" from the first and second sets; use the association rule algorithm to filter out the association rule "Noctuidae - Cyantraniliprole (10% dispersible oil suspension)" to form the fourth set.
[0067] The association rule algorithms include but are not limited to: Apriori algorithm and FP-tree frequency set algorithm.
[0068] Step S205: construct an association rule base based on the association rules of the third set and the association rules of the fourth set.
[0069] After the association rule base is constructed, step S102 specifically further includes the following steps:
[0070] The range of drug formulas for the target specialty minor crops in the same family classification is obtained through the association rules of the third set;
[0071] The association rules of the fourth set are used to recommend drugs for target specialty small-scale crops with the same pathogens or pests.
[0072] Example 8 (diseases): Using the association rules of the third set, obtain the range of drug formulas for the specialty small-scale crop "broccoli" in the same family "Cruciferae", "Cruciferae-Propineb (70% wettable powder), Cruciferae-Cyantraniliprole (10% dispersible oil suspension)"; then use the association rules from the fourth set to recommend "Propineb (70% wettable powder)" for the prevention and control of the current specialty small-scale crop "broccoli downy mildew";
[0073] Example nine (insect pests): using the association rules of the third set, obtain the range of drug formulas for the specialty small crop "broccoli" under the same family "Cruciferae" classification: "Cruciferae-Propineb (70% wettable powder), Cruciferae-Cyantraniliprole (10% dispersible oil suspension)"; then use the association rules from the fourth set to recommend "Cyantraniliprole (10% dispersible oil suspension)" for the prevention and control of the current specialty small crop "broccoli armyworm".
[0074] The above method uses association rule algorithms to obtain association rules between pathogens and drug formulas, and between pests and drug formulas from existing pest and disease databases and pesticide databases, and recommends drugs for the same pathogens or pests of current specialty small crops to meet the needs of scientific drug use for specialty small crops in my country. The overall process diagram is as follows: Figure 3 shown.
[0075] See also Figure 3 to Figure 4 In this embodiment, a specific implementation of a storage device 400 is as follows:
[0076] A storage device 400 stores an instruction set, wherein the instruction set is used to execute:
[0077] Input the target specialty minor crops into the pre-established association rule library;
[0078] The range of drug formulas under the same family classification of the target specialty minor crops is obtained in the pre-established association rule library, and drug recommendations are made for the target specialty minor crops.
[0079] By pre-establishing an association rule base and then obtaining medication recommendations from the association rule base, medication recommendations can be based on evidence and more accurate and scientific medication recommendations can be made.
[0080] Furthermore, the instruction set is also used to execute: the step of “inputting target specialty minor crops into a pre-established association rule library” specifically includes the following steps:
[0081] The disease information and pest information are obtained from the pest database to construct the first set. Specifically, the steps include: reading the disease information from the pest database to obtain the disease name and the classification of its pathogen, reading the pest information from the pest database to obtain the pest name and the classification of its pest, and constructing the first set. The classification of the pathogen includes the species name and the genus name, and the classification of the pest includes the species name and the family name, which constitute the first set (disease-pathogen association rules, pest-insect association rules).
[0082] Example 1 (disease): Read cabbage downy mildew from the pest and disease database, obtain the disease name "cabbage downy mildew", pathogen genus name "Peronospora", and species name "parasitic downy mildew", and form the first set (association rule: cabbage downy mildew-Peronospora);
[0083] Example 2 (pests): Read the cabbage armyworm from the pest database, obtain the pest name "cabbage armyworm", the pest classification family name "Noctuidae", and the species name "Spodoptera litura", and form the first set (association rule: cabbage armyworm-Noctuidae).
[0084] Obtain the drug use information of the control object from the pesticide database to construct the second set. Read the control object information from the pesticide database, obtain the name of the control object (disease, pest) and the drug formula, and form the second set (disease-drug formula, pest-drug formula data set).
[0085] Example 3 (disease): Read the pesticide control information of cabbage downy mildew and cabbage downy mildew from the pesticide database, obtain the control objects "cabbage downy mildew", "cabbage downy mildew", and the drug formula "propineb (70% wettable powder)", and form the second set (cabbage downy mildew-propineb (70% wettable powder), cabbage downy mildew-propineb (70% wettable powder));
[0086] Example 4 (insect pests): Read the information on the control of cabbage armyworm using pesticides from the pesticide database, obtain the control targets "cabbage armyworm", "cabbage armyworm", and the drug formula "cyantraniliprole (10% dispersible oil suspension)", and form the second set (cabbage armyworm-cyantraniliprole (10% dispersible oil suspension); cabbage armyworm-cyantraniliprole (10% dispersible oil suspension)).
[0087] The registered crop information is read from the pesticide database, and combined with the crop family classification tree to construct a third set. The third set includes: a crop-drug formula association rule data set.
[0088] Example 5 (Pests and diseases): Read the registered crop "cabbage" from the pesticide control dataset, and combine it with the crop family classification tree (Cruciferae) to form the third set (Cruciferae - Propineb (70% wettable powder), Cruciferae - Cyantraniliprole (10% dispersible oil suspension)).
[0089] The first set and the second set are calculated by an association rule algorithm, and the calculation results are used to construct a fourth set. Specifically, the steps include:
[0090] The pathogen classification tree-drug formula and pest classification tree-drug formula of the control objects (disease name, pest name) are obtained from the first set and the second set, and the frequent item sets and frequent item set support of the control object drug formula are calculated through the association rule algorithm. The suitable frequent item set of drug formula is obtained by screening the support of the frequent item set, and the suitable association rules are determined using the filtered frequent item set of drug formula to form the fourth set.
[0091] Example 6 (disease): Obtain the pathogen classification tree of the control object "Cabbage Downy Mildew - Downy Mildew - Propineb (70% wettable powder)" from the first set and the second set; "Cabbage Downy Mildew - Downy Mildew - Propineb (70% wettable powder)"; Use the association rule algorithm to filter out the association rule "Downy Mildew - Propineb (70% wettable powder)" to form the fourth set;
[0092] Example 7 (Pests): Obtain the pest classification trees of the control targets "Cabbage armyworm - Noctuidae - Cyantraniliprole (10% dispersible oil suspension)" and "Cabbage armyworm - Noctuidae - Cyantraniliprole (10% dispersible oil suspension)" from the first and second sets; use the association rule algorithm to filter out the association rule "Noctuidae - Cyantraniliprole (10% dispersible oil suspension)" to form the fourth set.
[0093] The association rule algorithms include but are not limited to: Apriori algorithm and FP-tree frequency set algorithm.
[0094] An association rule base is constructed by the association rules of the third set and the association rules of the fourth set. After the association rule base is constructed, further, the instruction set is also used to execute: the "obtaining the range of drug prescriptions under the same family classification of the target specialty minor crops in the pre-established association rule base, and recommending drugs for the target specialty minor crops", specifically also includes the steps of:
[0095] The range of drug formulas for the target specialty minor crops in the same family classification is obtained through the association rules of the third set;
[0096] The association rules of the fourth set are used to recommend drugs for target specialty small-scale crops with the same pathogens or pests.
[0097] Example 8 (diseases): Using the association rules of the third set, obtain the range of drug formulas for the specialty small-scale crop "broccoli" in the same family "Cruciferae", "Cruciferae-Propineb (70% wettable powder), Cruciferae-Cyantraniliprole (10% dispersible oil suspension)"; then use the association rules from the fourth set to recommend "Propineb (70% wettable powder)" for the prevention and control of the current specialty small-scale crop "broccoli downy mildew";
[0098] Example nine (insect pests): using the association rules of the third set, obtain the range of drug formulas for the specialty small crop "broccoli" under the same family "Cruciferae" classification: "Cruciferae-Propineb (70% wettable powder), Cruciferae-Cyantraniliprole (10% dispersible oil suspension)"; then use the association rules from the fourth set to recommend "Cyantraniliprole (10% dispersible oil suspension)" for the prevention and control of the current specialty small crop "broccoli armyworm".
[0099] The above instruction set executes the command process, and uses the association rule algorithm to obtain the association rules between pathogens and drug formulas, and pests and drug formulas from the existing pest and disease database and pesticide database, and recommends the prevention and control drugs for the same pathogens or pests of the current specialty small crops to meet the needs of scientific drug use for my country's specialty small crops. The overall process diagram is as follows: Figure 3 shown.
[0100] It should be noted that, although the above embodiments have been described in this article, the patent protection scope of the present invention is not limited thereby. Therefore, based on the innovative concept of the present invention, changes and modifications made to the embodiments described herein, or equivalent structures or equivalent process changes made using the contents of the present invention specification and drawings, directly or indirectly applying the above technical solutions to other related technical fields, are all included in the patent protection scope of the present invention.
Claims
1. A rule-based association-based method for recommending pesticides for the prevention and control of diseases and insect pests of specialty small crops, characterized in that: Includes steps: Step S101: inputting target specialty minor crops into a pre-established association rule library; Step S102: obtaining the range of drug prescriptions under the same family classification of the target specialty minor crops in the pre-established association rule library, and recommending drugs for the target specialty minor crops; Step S201: obtaining disease information and pest information from a pest database, and constructing a first set, specifically including the steps of: reading disease information from the pest database, obtaining the name of the disease and the classification of its pathogen, reading pest information from the pest database, obtaining the name of the pest and the classification of its pest, and constructing a first set, wherein the classification of the pathogen includes the species name and the genus name, and the classification of the pest includes the species name and the family name, forming the first set, and forming a disease-pathogen association rule and a pest-insect association rule; Step S202: Obtaining the drug information of the control object from the pesticide database, constructing a second set, reading the control object information from the pesticide database, obtaining the names of the control object diseases and pests and the drug formula, forming the second set, and forming the disease-drug formula association rules and the pest-drug formula association rules; Step S203: Reading registered crop information from the pesticide database, and combining it with the crop family classification tree to construct a third set to form crop-drug formula association rules; Step S204: Calculate the first set and the second set by using an association rule algorithm, and construct a fourth set based on the calculation results, which specifically includes the following steps: Obtain the pathogen classification tree-drug formula and the pest classification tree-drug formula of the disease name and the pest name of the control object from the first set and the second set, and calculate the frequent item set and the support of the frequent item set of the drug formula of the control object through the association rule algorithm, obtain the appropriate frequent item set of the drug formula through the frequent item set support, and determine the appropriate association rules using the drug formula frequent item set obtained through the screening to form the fourth set; Step S205: constructing an association rule base based on the association rules of the third set and the association rules of the fourth set; After the association rule base is constructed, step S102 specifically further includes the following steps: The range of drug formulas for the target specialty minor crops in the same family classification is obtained through the association rules of the third set; The fourth set of association rules is used to recommend drugs for target specialty small-scale crops with the same pathogens or pests; The association rule algorithm is used to obtain the association rules between pathogens and drug formulas, and between pests and drug formulas from the existing pest and disease database and pesticide database, and to recommend the control drugs for the same pathogens or pests of the current specialty small-scale crop pests.
2. A storage device having an instruction set stored therein, characterized in that: The instruction set is used to execute the method for recommending drugs for controlling pests and diseases of specialty small crops based on rule association as claimed in claim 1, and further comprises the following steps: Input the target specialty minor crops into the pre-established association rule library; The range of drug formulas under the same family classification of the target specialty minor crops is obtained in the pre-established association rule library, and drug recommendations are made for the target specialty minor crops.
3. A storage device according to claim 2, characterized in that: The instruction set is also used to execute: the step of "inputting target specialty minor crops into a pre-established association rule library", specifically including the steps of: Obtain disease information and pest information from a pest database to construct a first set; Obtain the pesticide information of the control object from the pesticide database to construct the second set; Reading registered crop information from the pesticide database, and combining the crop family classification tree to construct a third set; Calculate the first set and the second set by using an association rule algorithm, and construct a fourth set based on the calculation results; An association rule base is constructed by the association rules of the third set and the association rules of the fourth set.
4. A storage device according to claim 3, characterized in that: The instruction set is also used to execute: the "obtaining the range of drug prescriptions under the same family classification of the target specialty minor crops in the pre-established association rule library, and recommending drugs for the target specialty minor crops", specifically including the steps of: The range of drug formulas for the target specialty minor crops in the same family classification is obtained through the association rules of the third set; The association rules of the fourth set are used to recommend drugs for target specialty small-scale crops with the same pathogens or pests.
5. A storage device according to claim 3, characterized in that: The instruction set is also used to execute: "calculating the first set and the second set by an association rule algorithm, and constructing a fourth set from the calculation results", which specifically includes the steps of: The frequent item sets and the support of the frequent item sets of the medication prescriptions of the prevention and treatment objects are calculated by the association rule algorithm. The suitable frequent item sets of the medication prescriptions are obtained by screening the support of the frequent item sets. The suitable association rules are determined by using the filtered frequent item sets of the medication prescriptions to form the fourth set.
6. A storage device according to claim 3, characterized in that: The instruction set is also used to execute: the "obtaining disease information and pest information from the pest database to construct a first set", specifically including the steps of: Reading disease information from the pest database, obtaining the disease name and the category to which the pathogen belongs; reading pest information from the pest database, obtaining the pest name and the category to which the pest belongs, and constructing a first set; The "obtaining pesticide information of control objects from the pesticide database to construct a second set" specifically includes the following steps: The information of the control target is read from the pesticide database, and the name of the control target and the drug formula are obtained to form the second set.
