A method and system for intelligently regulating the dosage of pesticides for forest pest control

Abstract

The present invention discloses a method and system for intelligently regulating the dosage of pesticides for controlling forest pests and diseases, which relates to the field of intelligent control technology. The method includes: collecting a dataset of disease images of a target forest area; connecting a pesticide dosage regulator, including a data receiving module, a mode switching module, and a dosage adjustment module; receiving the dataset of disease images through the data receiving module to identify pest groups; when entering the night mode, the mode switching module switches the daytime pesticide spraying mode to the night pesticide spraying mode; predicting and converting the types of night pests through the dosage adjustment module, outputting the night pesticide dosage, and adjusting the night pesticide dosage of the pesticide spraying tank. The present invention solves the technical problem in the prior art that due to inaccurate pesticide dosage, the control of forest pests and diseases is incomplete or the growth of vegetation is affected, and achieves the technical effect of improving the accuracy and comprehensiveness of forest pest and disease control through intelligent regulation of pesticide dosage without affecting the growth of vegetation.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control, and particularly relates to a method and system for intelligently regulating the dosage of pesticides for forest pests and diseases. Background Art

[0002] Forest pests and diseases are the main threats to the healthy growth of forest trees. Traditional pest control methods mainly include pruning and removing trees with pest larvae attached and spraying pesticides using manual spraying techniques, which have certain limitations. The use of automatic spraying techniques can solve the limitations of manual spraying techniques to a certain extent, but there are still problems such as inappropriate selection of pesticide dosage, resulting in unsatisfactory pest control effects or affecting the growth of vegetation. Summary of the Invention

[0003] This application provides a method and system for intelligently regulating the dosage of pesticides for forest pests and diseases, which are used to solve the technical problem in the prior art that due to inaccurate pesticide dosage, the control of forest pests and diseases is not comprehensive or the growth of vegetation is affected.

[0004] In the first aspect of this application, a method for intelligently regulating the dosage of pesticides for forest pests and diseases is provided. The method includes: collecting diseased leaves in a target forest area to obtain a diseased image dataset; connecting a pesticide dosage regulator, which includes a data receiving module, a mode switching module, and a dosage adjustment module; when the data receiving module receives the diseased image dataset, identifying pest groups with the diseased image dataset, and outputting daytime pest samples and nighttime pest samples; collecting environmental information, and judging whether to enter the nighttime mode according to the indicators of the environmental information. When entering the nighttime mode, adjusting from the daytime pesticide spraying mode to the nighttime pesticide spraying mode according to the mode switching module; when the mode is in the nighttime pesticide spraying mode, predicting and converting the types of nighttime pests through the dosage adjustment module, and outputting the nighttime pesticide dosage, where the dosage adjustment module is obtained by establishing and training a siamese network with the daytime pest samples and the nighttime pest samples; adjusting the nighttime pesticide dosage of the pesticide liquid tank connected to the dosage adjustment module according to the nighttime pesticide dosage.

[0005] The second aspect of the present application provides a system for intelligently regulating the dosage of pesticides and disinfectants for forest pests and diseases. The system includes: a disease image dataset acquisition module for collecting disease images of leaves in a target forest area to obtain a disease image dataset; a pesticide and disinfectant dosage regulator connection module for connecting to a pesticide and disinfectant dosage regulator, which includes a data receiving module, a mode switching module, and a dosage adjustment module; a pest sample output module for, when the data receiving module receives the disease image dataset, identifying pest groups based on the disease image dataset and outputting daytime pest samples and nighttime pest samples; a disinfection mode switching module for collecting environmental information, judging whether to enter the nighttime mode according to the indicators of the environmental information, and when entering the nighttime mode, adjusting from the daytime disinfection mode to the nighttime disinfection mode according to the mode switching module; a nighttime dosage output module for, when the mode is in the nighttime disinfection mode, predicting and converting the types of nighttime pests through the dosage adjustment module and outputting the nighttime dosage, where the dosage adjustment module is obtained by training a siamese network with the daytime pest samples and the nighttime pest samples; a pesticide and disinfectant dosage adjustment module for adjusting the nighttime dosage of the pesticide and disinfectant liquid tank connected to the dosage adjustment module according to the nighttime dosage.

[0006] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0007] A method for intelligently regulating the dosage of pesticides and disinfectants for forest pests and diseases provided by the present application relates to the technical field of intelligent control. By collecting a disease image dataset of a target forest area, connecting to a pesticide and disinfectant dosage regulator, receiving the disease image dataset through a data receiving module, identifying pest groups, and switching between daytime / nighttime disinfection modes by a mode switching module, predicting and converting the types of daytime / nighttime pests through a dosage adjustment module, outputting daytime / nighttime dosages, and adjusting the daytime / nighttime dosages of the pesticide and disinfectant liquid tank, the technical problem in the prior art that due to inaccurate dosages of pesticides and disinfectants, the disinfection of forest pests and diseases is incomplete or the growth of vegetation is affected is solved, and the technical effect of accurately and comprehensively disinfecting forest pests and diseases through intelligent regulation of the dosage of pesticides and disinfectants without affecting the growth of vegetation is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0009] Figure 1 Schematic flow chart of a method for intelligently regulating the dosage of pesticides for forest pest control provided by an embodiment of the present application;

[0010] Figure 2 Schematic flow chart of predicting the dosage of pesticides for daytime / nighttime use in a method for intelligently regulating the dosage of pesticides for forest pest control provided by an embodiment of the present application;

[0011] Figure 3 Schematic flow chart of connecting a pesticide dosage regulator in a method for intelligently regulating the dosage of pesticides for forest pest control provided by an embodiment of the present application;

[0012] Figure 4 Schematic structural diagram of a system for intelligently regulating the dosage of pesticides for forest pest control provided by an embodiment of the present application.

[0013] Explanation of reference numerals: Disease image dataset acquisition module 11, pesticide dosage regulator connection module 12, pest sample output module 13, pesticide application mode switching module 14, nighttime pesticide dosage output module 15, pesticide dosage adjustment module 16. Detailed implementation manners

[0014] The present application provides a method for intelligently regulating the dosage of pesticides for forest pest control, which is used to solve the technical problem in the prior art that due to inaccurate pesticide dosage, the forest pest control is incomplete or the growth of vegetation is affected.

[0015] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0016] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0017] Example 1

[0018] As Figure 1 shown, this application provides a method for intelligently regulating the dosage of pesticides and insecticides for forest pests and diseases. The method includes:

[0019] P10: Collect diseased leaves in the target forest area to obtain a diseased image dataset;

[0020] Exemplarily, by installing multiple image acquisition devices in the target forest area, the multiple image devices are communicatively connected to the image data processing module. The multiple image devices are used to monitor the pests and diseases of the vegetation in the target forest area in real time, and collect real-time diseased images of the diseased leaves to form a diseased image dataset, which is transmitted to the image data processing module for pest group identification.

[0021] P20: Connect the pesticide dosage regulator, which includes a data receiving module, a mode switching module, and a dosage adjustment module;

[0022] Specifically, establish a communication connection between the pesticide dosage regulator and the total control system. The pesticide dosage regulator is a device used to adjust the dosage of pesticides for pest control, and is composed of a data receiving module, a mode switching module, and a dosage adjustment module. The data receiving module is used to receive the diseased image dataset and identify and process the diseased images in the diseased image dataset, and is communicatively connected to multiple image acquisition devices. The mode switching module is used to switch the pest control mode according to environmental information. The dosage adjustment module is used to predict the types of pests and diseases and adjust the dosage of pesticides.

[0023] Further, as Figure 2 shown, step P20 of the embodiment of this application further includes:

[0024] P21: Obtain the operable disinfection and killing range of the pesticide dosage regulator;

[0025] P22: Distribute the target forest area with the operable disinfection and killing range to obtain multiple distribution nodes. Among them, a corresponding pesticide dosage regulator is set on each distribution node;

[0026] P23: Establish an equipment communication interface according to the pesticide dosage regulator, and communicatively connect the interfaces of each pesticide dosage regulator to the total control center for unified management and control of the target forest area.

[0027] Optionally, according to the network signal situation, device computing power, etc., obtain the operable disinfection drug range of the currently used disinfection drug regulator, that is, the adjustable forest area range, and distribute the disinfection drug regulator to the target forest area according to the operable disinfection drug range. When ensuring that all local areas within the target forest area are covered by the disinfection range of the disinfection drug regulator, obtain distribution nodes of multiple disinfection drug regulators, and set corresponding disinfection drug regulators at each distribution node.

[0028] Further, establish a device communication interface based on the disinfection drug regulator, connect the interfaces of each disinfection drug regulator to the central control center for communication, and control each disinfection drug regulator through the central control center to achieve unified management and control of the pests and diseases in the target forest area.

[0029] Further, step P20 of the embodiment of the present application further includes:

[0030] P24: Synchronously monitor the real-time status of each disinfection drug regulator. If there is at least one disinfection drug regulator whose real-time status is different from that of other disinfection drug regulators, generate a first synchronization instruction, where the status of each disinfection drug regulator includes a daytime disinfection mode and a nighttime disinfection mode;

[0031] P25: Perform mode synchronization switching on the disinfection drug regulators that are not in the same state according to the first synchronization instruction.

[0032] It should be understood that through the central control system, the real-time status of each disinfection drug regulator is synchronously monitored. Among them, the status of each disinfection drug regulator includes a daytime disinfection mode and a nighttime disinfection mode, and the disinfection regulator judges whether it is daytime or nighttime through environmental data, and then selects to use the daytime disinfection mode or the nighttime disinfection mode. If there are a small number of disinfection drug regulators whose real-time status is different from that of other disinfection drug regulators, it means that the environmental data characteristics may not be obvious at present. For example, misjudgment may occur due to weak light intensity on cloudy days, or individual regulators may be blocked by leaves. Then generate a first synchronization instruction, and perform mode synchronization switching on the disinfection drug regulators that are not in the same state according to the first synchronization instruction to correct the error in the determination of the disinfection mode.

[0033] P30: When the data receiving module receives the disease image data set, identify the pest groups with the disease image data set, and output daytime pest samples and nighttime pest samples;

[0034] Exemplarily, the data receiving module includes various pest identification features, and its construction process can be as follows: Crawl various pest and disease identification feature data based on big data, use this as the construction data, combine it with a BP neural network to construct the data receiving module, and use the constructed data to perform supervised training on the data receiving module until the module output converges and meets the preset accuracy requirement, obtaining the data receiving module. The BP neural network is a multi-layer feedforward neural network trained according to the error backpropagation algorithm, without the need to determine in advance the mathematical equation of the mapping relationship between the input and output. It only learns a certain rule through its own training and obtains the result closest to the expected output value when a given input value is provided.

[0035] Further, when the data receiving module of the disinfection regulator receives the disease image dataset, the data receiving module identifies the pest group according to the picture features in the disease image dataset and classifies them according to the image acquisition time, obtaining daytime pest samples and nighttime pest samples, which can be used as the construction data for the drug dosage adjustment module.

[0036] P40: Collect environmental information, judge whether to enter the nighttime mode according to the indicators of the environmental information. When entering the nighttime mode, adjust the switching from the daytime disinfection mode to the nighttime disinfection mode according to the mode switching module;

[0037] In a possible embodiment of the present application, since there are differences in pest types between daytime and nighttime, different disinfection modes need to be adopted for pest disinfection during daytime and nighttime. By installing multiple environmental monitoring devices in the target forest area, such as light monitoring devices, temperature monitoring devices, humidity monitoring devices, etc., to obtain the environmental information of the target forest area, generating multiple environmental information indicators, including environmental light intensity, temperature, humidity, etc., and judging whether the current period is daytime or nighttime according to the indicators of the environmental information, and then judging whether the current pest disinfection mode needs to enter the nighttime mode. If the judgment result is the nighttime mode, the daytime disinfection mode is switched to the nighttime disinfection mode through the mode switching module to ensure the accuracy of the pest control drugs.

[0038] P50: When the mode is in the nighttime disinfection mode, predict and convert the nighttime pest type through the drug dosage adjustment module, and output the nighttime drug dosage, where the drug dosage adjustment module is obtained by establishing and training a siamese network with the daytime pest samples and the nighttime pest samples;

[0039] Specifically, using the daytime pest samples and the nighttime pest samples as training data, a siamese network is established for training. The siamese network consists of two sub-networks with similar structures that share weights. By using the daytime pest samples and the nighttime pest samples as training data and combining with a BP neural network for supervised training, two similar sub-networks can be obtained. Further, according to the trained siamese network, the dosage adjustment module is constructed. When the disinfection mode is in the nighttime disinfection mode, through the dosage adjustment module, combined with the recent daytime pest types, the nighttime pest types are predicted and converted to obtain visual and processable values such as the existing quantity of pests and diseases, the estimated spread trend, and the pest disaster area, etc., and based on this, the dosage of medicine is matched to output the nighttime dosage of medicine for nighttime disinfection dosage adjustment.

[0040] Further, as Figure 3 shown, step P50 of the embodiment of the present application further includes:

[0041] P51: Establish Markov prediction functions using the daytime pest samples and the nighttime pest samples as two sets of input data respectively;

[0042] P52: Among them, the Markov prediction function is used to predict the pest quantity based on the daytime pest samples, and when the preset expected probability is reached, the daytime pest prediction index is output, and to predict the pest quantity based on the nighttime pest samples, and when the preset expected probability is reached, the nighttime pest prediction index is output;

[0043] P53: According to the real-time mode of the dosage adjustment module, input the daytime pest prediction index or the nighttime pest prediction index into the dosage adjustment module for dosage conversion, and output the corresponding daytime dosage of medicine or nighttime electricity consumption.

[0044] Among them, using the daytime pest samples and the nighttime pest samples as input data respectively, a daytime Markov prediction function and a nighttime Markov prediction function are established. The Markov prediction function is a function that applies the basic principles and methods of Markov chains to study the change law of the time series of pest quantity and predict its future change trend. The Markov chain is a sequence of random variables with Markov properties. The Markov property means that when a random process is given the current state and all past states, the conditional probability distribution of its future state depends only on the current state and is independent of the past state.

[0045] Further, taking the daytime pest sample as a random variable with Markov property, predicting the pest quantity through the daytime Markov prediction function. When the predicted state probability of the pest quantity reaches the preset expected probability, that is, when the accuracy rate of the pest state prediction reaches the minimum value of the preset accuracy rate, output the corresponding daytime pest prediction index. The daytime pest prediction index has a corresponding pest state. Therefore, different pest states correspond to multiple different pest prediction indexes. Similarly, using the nighttime pest sample, predicting the pest quantity through the nighttime Markov prediction function. When the predicted state probability of the pest quantity reaches the preset expected probability, output the corresponding nighttime pest prediction index.

[0046] Further, according to the real-time mode of the dosage adjustment module, that is, the normal working mode, input the daytime pest prediction index or the nighttime pest prediction index into the dosage adjustment module for dosage conversion, that is, match the dosage according to the pest prediction index, and obtain the corresponding daytime dosage or nighttime dosage to adjust the daytime pest control dosage or the nighttime pest control dosage.

[0047] Further, step P50 of the embodiment of the present application further includes:

[0048] P54: Establish a siamese network. Among them, the siamese network establishes an automatic switching ratio between day and night by comparing the similarity of the two sets of prediction results of the daytime pest prediction index and the nighttime pest prediction index.

[0049] P55: Generate an automatic control model according to the automatic switching ratio between day and night, and automatically adjust the disinfection dosage of the dosage adjustment module with the automatic control model.

[0050] It should be understood that multiple historical pest prediction results of the daytime pest prediction index and the nighttime pest prediction index are respectively extracted, and similarity comparisons are made pairwise based on the daytime and nighttime prediction indexes. Among them, every two similarity comparison indexes are prediction indexes at adjacent times. Finally, calculate the similarity degree between the daytime pest prediction index and the nighttime pest prediction index, and establish an automatic switching ratio between day and night based on this, such as 4:5. Further, generate an automatic control model according to the automatic switching ratio between day and night. Through the automatic control model, referring to the automatic switching ratio between day and night, automatically adjust the disinfection dosage of the dosage adjustment module, which can improve the efficiency and accuracy of dosage adjustment.

[0051] P60: Adjust the nighttime pest control dosage of the disinfection liquid tank connected to the dosage adjustment module according to the nighttime dosage.

[0052] Specifically, with reference to the nighttime dosage, the dosage adjustment module adjusts the spraying dosage of the corresponding disinfection liquid tank connected thereto to perform nighttime pest control. The dosage adjustment modules of different disinfection dosage regulators are connected to different disinfection liquid tanks. The disinfection liquid tank is a tank for storing disinfection agents and can adjust the flow rate through a spraying device. When the spraying amount reaches the dosage, the disinfection stops. Depending on the differences in pest types at different locations, the disinfection agents stored in different disinfection liquid tanks may be different.

[0053] Further, step P60 of the embodiment of the present application further includes:

[0054] P61: Obtain the disinfection agent information in the disinfection liquid tank and the vegetation growth information corresponding to the disinfection range of the corresponding disinfection dosage regulator;

[0055] P62: Perform influence degree identification according to the vegetation growth information and the disinfection agent information to obtain a drug-growth influence index;

[0056] P63: Identify the protection liquid threshold according to the drug-growth influence index, obtain the dosage of the drug corresponding to the preset growth influence index, and output the first constrained dosage. Among them, the first constrained dosage is stored in the dosage adjustment module to limit the real-time dosage to be less than the first constrained dosage.

[0057] Optionally, extract the disinfection agent information stored in the disinfection liquid tank, including the type of the disinfection agent, the pest type it targets, the applicable plant type, etc., and extract the vegetation growth information in the disinfection range corresponding to the disinfection dosage regulator at each distribution point in the target forest area, such as the growth stage, growth rate, health status, etc. of the vegetation. Further, perform influence degree identification according to the vegetation growth information and the disinfection agent information, that is, judge the influence degree of the disinfection agent used in each local area on the growth status of the vegetation according to the production situation of the vegetation in each local area, and generate a drug-growth influence index according to the influence degree of different dosages on the vegetation. The drug-growth influence index includes multiple stage indexes.

[0058] Further, identify the protection liquid threshold according to the drug-growth influence index, that is, extract the influence degree of different dosages on the vegetation in different growth stages from the drug-growth influence index, and set the dosage threshold of the drug that can automatically protect the vegetation according to different growth stages of the vegetation as the protection liquid threshold. Exemplarily, the protection liquid thresholds in different stages such as the growth period and the maturity period are different.

[0059] Further, select an index that has the least or less impact on vegetation growth as the preset growth impact index, extract the dosage of the medicine corresponding to the preset growth impact index as the first constrained dosage, and store the first constrained dosage in the corresponding dosage adjustment module. During the actual pest control process, limit the real-time dosage to be less than the first constrained dosage to avoid the impact of the pest control agent on vegetation growth.

[0060] Further, the embodiment of the present application further includes step P70, and step P70 further includes:

[0061] P71: When the mode is in the daytime pest control mode, predict and convert the daytime pest types through the dosage adjustment module, and output the daytime dosage;

[0062] P72: Adjust the daytime pest control dosage of the pest control liquid tank connected to the dosage adjustment module according to the daytime dosage.

[0063] In a possible embodiment of the present application, when the pest control mode is in the daytime pest control mode, predict and convert the daytime pest types through the dosage adjustment module to obtain the daytime pest prediction index, and obtain the daytime dosage according to the daytime pest prediction index. Then, with reference to the daytime dosage, adjust the spraying amount of the pest control liquid tank through the dosage adjustment module to perform daytime pest control, improve the accuracy of daytime pest control, and reduce the impact of the pest control liquid on vegetation.

[0064] In summary, the embodiment of the present application has at least the following technical effects:

[0065] The present application collects the disease image dataset of the target forest area, connects the pest control dosage regulator, receives the disease image dataset through the data receiving module, performs pest group identification, and the mode switching module switches between the daytime / nighttime pest control modes. The dosage adjustment module predicts and converts the daytime / nighttime pest types, outputs the daytime / nighttime dosage, and adjusts the daytime / nighttime pest control dosage of the pest control liquid tank.

[0066] It achieves the technical effect of accurately and comprehensively controlling forest pests and diseases by intelligently regulating the pest control dosage without affecting vegetation growth.

[0067] Embodiment 2

[0068] Based on the same inventive concept as the method for intelligently regulating the pest control dosage of forest pests and diseases in the foregoing embodiment, as Figure 4 shown, the present application provides a system for intelligently regulating the pest control dosage of forest pests and diseases. The system in the embodiment of the present application and the method embodiment are based on the same inventive concept. Among them, the system includes:

[0069] Disease image dataset acquisition module 11, which is used to collect diseased leaves in the target forest area to obtain a disease image dataset;

[0070] Disinfection dosage regulator connection module 12, which is used to connect the disinfection dosage regulator. The disinfection dosage regulator includes a data receiving module, a mode switching module, and a dosage adjustment module;

[0071] Pest sample output module 13, which is used to identify pest groups with the disease image dataset when the data receiving module receives the disease image dataset, and output daytime pest samples and nighttime pest samples;

[0072] Disinfection mode switching module 14, which is used to collect environmental information, judge whether to enter the nighttime mode according to the indicators of the environmental information, and when entering the nighttime mode, adjust the switch from the daytime disinfection mode to the nighttime disinfection mode according to the mode switching module;

[0073] Nighttime dosage output module 15, which is used to predict and convert the types of nighttime pests through the dosage adjustment module when the mode is in the nighttime disinfection mode, and output the nighttime dosage. Among them, the dosage adjustment module is obtained by establishing a siamese network training with the daytime pest samples and the nighttime pest samples;

[0074] Disinfection dosage adjustment module 16, which is used to adjust the nighttime disinfection dosage of the disinfection liquid tank connected to the dosage adjustment module according to the nighttime dosage.

[0075] Further, the disinfection dosage regulator connection module 12 is also used to perform the following steps:

[0076] Obtain the operable disinfection range of the disinfection dosage regulator;

[0077] P22: Distribute the target forest area with the operable disinfection range to obtain multiple distribution nodes, and a corresponding disinfection dosage regulator is set on each distribution node;

[0078] P23: Establish an equipment communication interface according to the disinfection dosage regulator, and communicate the interfaces of each disinfection dosage regulator with the total control center for unified management and control of the target forest area.

[0079] Further, the disinfection dosage regulator connection module 12 is also used to perform the following steps:

[0080] Synchronously monitor the real-time status of each disinfection and sterilization dosage regulator. If the real-time status of at least one disinfection and sterilization dosage regulator is different from that of other disinfection and sterilization dosage regulators, generate a first synchronization instruction, where the status of each disinfection and sterilization dosage regulator includes a daytime disinfection mode and a nighttime disinfection mode;

[0081] P25: According to the first synchronization instruction, perform mode synchronization switching on the disinfection and sterilization dosage regulators that are not in the same state.

[0082] Further, the nighttime dosage output module 15 is further configured to perform the following steps:

[0083] Establish Markov prediction functions with the daytime pest samples and the nighttime pest samples as two sets of input data respectively;

[0084] P52: Among them, the Markov prediction function is to predict the pest quantity based on the daytime pest samples, and output a daytime pest prediction index when reaching a preset expected probability, and predict the pest quantity based on the nighttime pest samples, and output a nighttime pest prediction index when reaching the preset expected probability;

[0085] P53: According to the real-time mode of the dosage adjustment module, input the daytime pest prediction index or the nighttime pest prediction index into the dosage adjustment module for dosage conversion, and output the corresponding daytime dosage or nighttime power consumption.

[0086] Further, the nighttime dosage output module 15 is further configured to perform the following steps:

[0087] Establish a Siamese network, where the Siamese network establishes an automatic switching ratio between daytime and nighttime by comparing the similarity of the two sets of prediction results of the daytime pest prediction index and the nighttime pest prediction index;

[0088] P55: Generate an automatic control model according to the automatic switching ratio between daytime and nighttime, and automatically adjust the disinfection and sterilization dosage of the dosage adjustment module with the automatic control model.

[0089] Further, the disinfection and sterilization dosage adjustment module 16 is further configured to perform the following steps:

[0090] Obtain the disinfection and sterilization agent information in the disinfection liquid tank, and the vegetation growth information corresponding to the disinfection range corresponding to the disinfection and sterilization dosage regulator;

[0091] P62: Identify the influence degree according to the vegetation growth information and the disinfection and sterilization agent information, and obtain the agent-growth influence index;

[0092] P63: Identify the threshold of the protection liquid based on the medicament - growth impact index, obtain the dosage of the medicament corresponding to the preset growth impact index, and output the first constrained dosage. The first constrained dosage is stored in the dosage adjustment module to limit the real - time dosage to be less than the first constrained dosage.

[0093] Further, the system further includes:

[0094] A daytime dosage output module, which is used to predict and convert the daytime pest types through the dosage adjustment module and output the daytime dosage when the mode is in the daytime disinfection mode.

[0095] A daytime disinfection dosage adjustment module, which is used to adjust the daytime disinfection dosage of the disinfection liquid tank connected to the dosage adjustment module according to the daytime dosage.

[0096] It should be noted that the above - mentioned order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above - mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be executed in a different order from that in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0097] The above - mentioned are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0098] This specification and the drawings are only exemplary descriptions of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A method for intelligently regulating the dosage of pesticides for killing forest pests and diseases, characterized in that, The method includes: Collecting diseased leaves in the target forest area to obtain a diseased image dataset; Connecting a disinfection and sterilization drug dosage regulator, which includes a data receiving module, a mode switching module, and a drug dosage adjustment module; When the data receiving module receives the diseased image dataset, identifying pest groups with the diseased image dataset, and outputting daytime pest samples and nighttime pest samples; Collecting environmental information, judging whether to enter the nighttime mode according to the indicators of the environmental information, and when entering the nighttime mode, adjusting from the daytime disinfection and sterilization mode to the nighttime disinfection and sterilization mode according to the mode switching module; When the mode is in the nighttime disinfection and sterilization mode, predicting and converting the nighttime pest types through the drug dosage adjustment module to output the nighttime drug dosage, where the drug dosage adjustment module is obtained by establishing and training a siamese network with the daytime pest samples and the nighttime pest samples; Adjusting the nighttime disinfection and sterilization drug dosage of the disinfection liquid tank connected to the drug dosage adjustment module according to the nighttime drug dosage; The drug dosage adjustment module is obtained by establishing and training a siamese network with the daytime pest samples and the nighttime pest samples. The method includes: Establishing Markov prediction functions respectively with the daytime pest samples and the nighttime pest samples as two groups of input data; Among them, the Markov prediction function predicts the pest quantity based on the daytime pest samples, and outputs the daytime pest prediction index when reaching the preset expected probability, and predicts the pest quantity based on the nighttime pest samples, and outputs the nighttime pest prediction index when reaching the preset expected probability; According to the real-time mode of the drug dosage adjustment module, inputting the daytime pest prediction index or the nighttime pest prediction index into the drug dosage adjustment module for drug dosage conversion, and outputting the corresponding daytime drug dosage or nighttime drug dosage; The method further includes: Establishing a siamese network, where the siamese network establishes an automatic switching ratio between day and night by comparing the similarity of the two groups of prediction results of the daytime pest prediction index and the nighttime pest prediction index; Generating an automatic control model according to the day-night automatic switching ratio, and automatically adjusting the disinfection and sterilization drug dosage of the drug dosage adjustment module with the automatic control model.

2. The method according to claim 1, wherein The method further includes: When the mode is in the daytime disinfection and sterilization mode, predicting and converting the daytime pest types through the drug dosage adjustment module to output the daytime drug dosage; Adjusting the daytime disinfection and sterilization drug dosage of the disinfection liquid tank connected to the drug dosage adjustment module according to the daytime drug dosage; 3. The method according to claim 2, characterized in that, The method further includes: Obtaining the disinfection and sterilization agent information in the disinfection liquid tank, and the vegetation growth information corresponding to the disinfection and sterilization range of the disinfection and sterilization drug dosage regulator; Identifying the influence degree according to the vegetation growth information and the disinfection and sterilization agent information to obtain a drug-growth influence index; Identifying the protection liquid threshold according to the drug-growth influence index, obtaining the drug dosage corresponding to the preset growth influence index, and outputting a first constraint drug dosage, where the first constraint drug dosage is stored in the drug dosage adjustment module to limit the real-time drug dosage to be less than the first constraint drug dosage.

4. The method according to claim 1, characterized in that, The method further includes: Obtain the operable disinfection and sterilization range of the disinfection and sterilization dosage regulator; Distribute the target forest area according to the operable disinfection and sterilization range to obtain a plurality of distribution nodes, wherein a corresponding disinfection and sterilization dosage regulator is set on each distribution node; Establish an equipment communication interface according to the disinfection and sterilization dosage regulator, and communicate the interfaces of each disinfection and sterilization dosage regulator with the central control center for unified management and control of the target forest area.

5. The method according to claim 4, wherein The method further includes: Synchronously monitor the real-time status of each disinfection and sterilization dosage regulator. If the real-time status of at least one disinfection and sterilization dosage regulator is different from that of other disinfection and sterilization dosage regulators, generate a first synchronization instruction, wherein the status of each disinfection and sterilization dosage regulator includes a daytime disinfection and sterilization mode and a nighttime disinfection and sterilization mode; Perform mode synchronization switching on the disinfection and sterilization dosage regulators that are not in the same state according to the first synchronization instruction.

6. A system for intelligently regulating the dosage of pesticides for forest pest control, characterized in that, The system includes: A disease image dataset acquisition module, which is used to collect disease images of diseased leaves in the target forest area to obtain a disease image dataset; A disinfection and sterilization dosage regulator connection module, which is used to connect the disinfection and sterilization dosage regulator. The disinfection and sterilization dosage regulator includes a data reception module, a mode switching module, and a dosage adjustment module; A pest sample output module, which is used to identify pest groups with the disease image dataset when the data reception module receives the disease image dataset, and output daytime pest samples and nighttime pest samples; A disinfection and sterilization mode switching module, which is used to collect environmental information, judge whether to enter the nighttime mode according to the indicators of the environmental information, and adjust the switching from the daytime disinfection and sterilization mode to the nighttime disinfection and sterilization mode according to the mode switching module when entering the nighttime mode; A nighttime dosage output module, which is used to predict and convert the nighttime pest types through the dosage adjustment module when the mode is in the nighttime disinfection and sterilization mode, and output the nighttime dosage, wherein the dosage adjustment module is obtained by establishing a siamese network training with the daytime pest samples and the nighttime pest samples; A disinfection and sterilization dosage adjustment module, which is used to adjust the nighttime disinfection and sterilization dosage of the disinfection liquid tank connected to the dosage adjustment module according to the nighttime dosage.

Images