A control method for automatic monitoring equipment of crop diseases and insect pests

Abstract

The present invention provides a control method for automatic monitoring equipment for crop diseases and insect pests, which relates to the technical field of equipment control. According to field crop data, monitoring links under the growth cycle are mined, and in combination with the set monitoring mode, the front-end sensor array of the automatic monitoring equipment is self-learned, and inspections are performed based on a preset path. The first sensor array is triggered to perform range monitoring control, and the second sensor array is triggered to perform directional monitoring control. The technical problems that the existing technology has insufficient intelligence and flexibility in the control of automatic monitoring equipment, and cannot adapt to efficient automatic monitoring and control of different growth periods and various pest and disease characteristics in a complex environment, resulting in limited accuracy and reliability of pest and disease monitoring are solved. The efficient automatic monitoring of pests and diseases is realized, and the accuracy and reliability of monitoring data in a complex environment are ensured.

Description

Technical Field

[0001] The invention relates to the technical field of equipment control, and in particular to a control method for automatic monitoring equipment for crop diseases and insect pests. Background Art

[0002] In agricultural production, pest and disease monitoring is a key link to ensure crop health and improve yield and quality. With the development of modern agricultural intelligence, the use of automated equipment for pest and disease monitoring has become a trend, but existing technologies face problems such as insufficient equipment monitoring accuracy, limited monitoring range, and poor adaptability to different environmental conditions.

[0003] Current pest and disease monitoring mostly relies on a single sensor or limited monitoring mode, which is difficult to meet the monitoring needs of multiple pests and diseases and different growth periods. Especially during the crop growth cycle, environmental conditions such as temperature and humidity are constantly changing, requiring equipment to have good adaptability and dynamic adjustment capabilities.

[0004] Therefore, the existing technology lacks intelligence and flexibility in the control of automatic monitoring equipment, and is unable to adapt to efficient automated monitoring and control of different growth stages and various pest and disease characteristics in complex environments, resulting in limited accuracy and reliability in pest and disease monitoring. Summary of the invention

[0005] The present application provides a control method for automatic monitoring equipment for crop diseases and pests, which is used to solve the technical problems in the prior art that the automatic monitoring equipment control is insufficient in intelligence and flexibility, and cannot adapt to efficient automated monitoring and control of different growth periods and various pest and disease characteristics in complex environments, resulting in limited accuracy and reliability in pest and disease monitoring.

[0006] In view of the above problems, the present application provides a control method for automatic monitoring equipment for crop diseases and insect pests.

[0007] In a first aspect, the present application provides a control method for automatic monitoring equipment for crop diseases and insect pests, the method comprising:

[0008] Based on the field crop data, the monitoring links under the growth cycle are mined through phenological statistical analysis, wherein each link node in the monitoring link contains control conditions and logic conditions;

[0009] Setting a monitoring mode, wherein the monitoring mode includes a first range monitoring and a second orientation monitoring, wherein the second orientation monitoring includes a sensing orientation and a position orientation;

[0010] Fitting the monitoring mode and the monitoring link, performing self-learning on the front-end sensor array of the automatic monitoring device, and initializing the sensor control module;

[0011] Control the automatic monitoring device to perform inspection based on a preset path, trigger the first sensor array to perform range monitoring control and trigger the second sensor array to perform directional monitoring control based on the sensor control module, wherein the monitoring control includes environmental error compensation based on an environmental state chain;

[0012] The preset path is constrained by a field monitoring grid, and the field monitoring grid can be dynamically divided and reconstructed based on a guiding strategy for cross-grid cross-monitoring.

[0013] In a second aspect, the present application provides a control system for automatic monitoring equipment for crop diseases and insect pests, the system comprising:

[0014] A monitoring link mining unit, the monitoring link mining unit is used to mine monitoring links under the growth cycle according to field crop data through phenological statistical analysis, wherein each link node in the monitoring link includes a control condition and a logic condition;

[0015] A monitoring mode setting unit, the monitoring mode setting unit is used to set a monitoring mode, wherein the monitoring mode includes a first range monitoring and a second directional monitoring, wherein the second directional monitoring includes a sensing orientation and a position orientation;

[0016] A sensor learning unit, the sensor learning unit is used to fit the monitoring mode and the monitoring link, perform self-learning on the front-end sensor array of the automatic monitoring device, and initialize the sensor control module;

[0017] A monitoring control unit, the monitoring control unit is used to control the automatic monitoring device to perform inspection based on a preset path, trigger the first sensor array to perform range monitoring control, and trigger the second sensor array to perform directional monitoring control based on the sensor control module;

[0018] The preset path is constrained by a field monitoring grid, and the field monitoring grid can be dynamically divided and reconstructed based on a guiding strategy for cross-grid cross-monitoring.

[0019] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0020] The embodiment of the present application provides a control method for automatic monitoring equipment for crop diseases and insect pests. According to field crop data, through phenological statistical analysis, the monitoring link under the growth cycle is mined, the monitoring mode is set, the monitoring mode and the monitoring link are fitted, the front-end sensor array of the automatic monitoring equipment is self-learned, and the sensor control module is initialized; the automatic monitoring equipment is controlled to perform inspections based on a preset path, and based on the sensor control module, the first sensor array is triggered to perform range monitoring control, and the second sensor array is triggered to perform directional monitoring control. Among them, the monitoring and control includes environmental error compensation based on the environmental state chain, which solves the technical problems existing in the prior art in terms of insufficient intelligence and flexibility in the control of automatic monitoring equipment, and the inability to adapt to efficient automatic monitoring and control of different growth periods and various pest and disease characteristics in complex environments, resulting in limited accuracy and reliability of pest and disease monitoring, thereby realizing efficient automatic monitoring of pests and diseases and ensuring the accuracy and reliability of monitoring data in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A schematic diagram of a control method for automatic monitoring equipment for crop pests and diseases is provided for this application;

[0022] Figure 2 A schematic diagram of a monitoring and control process in a control method for automatic monitoring equipment for crop diseases and insect pests is provided for this application;

[0023] Figure 3 A schematic diagram of the control system structure of an automatic monitoring device for crop diseases and insect pests is provided for this application.

[0024] Explanation of the reference numerals: monitoring link mining unit 11 , monitoring mode setting unit 12 , sensor learning unit 13 , monitoring control unit 14 . DETAILED DESCRIPTION

[0025] The present application provides a control method for automatic monitoring equipment for crop diseases and insect pests. According to field crop data, the monitoring links under the growth cycle are mined. In combination with the set monitoring mode, the front-end sensor array of the automatic monitoring equipment is self-learned, and inspections are performed based on a preset path. The first sensor array is triggered to perform range monitoring control, and the second sensor array is triggered to perform directional monitoring control. The method is used to solve the technical problems in the prior art that the intelligence and flexibility of the automatic monitoring equipment control are insufficient, and the efficient automated monitoring and control of different growth periods and various pest and disease characteristics in a complex environment cannot be adapted, resulting in limited accuracy and reliability of pest and disease monitoring.

[0026] Embodiment 1: Figure 1 As shown, the present application provides a control method for automatic monitoring equipment for crop diseases and insect pests, the method comprising:

[0027] S1: Based on the field crop data, through phenological statistical analysis, the monitoring link under the growth cycle is mined, wherein each link node in the monitoring link includes control conditions and logical conditions;

[0028] In an embodiment of the present application, the field crop data refers to relevant data about crop growth collected in the field environment of the target field to be monitored, including but not limited to the growth stage of the crop, the incidence of pests and diseases, and climatic conditions (such as temperature and humidity).

[0029] Then, a phenological statistical analysis is performed on the field crop data, that is, a statistical analysis is performed on the physiological characteristics, climatic conditions and pest and disease conditions of crops at different growth stages. By quantitatively analyzing the growth characteristics and pest and disease risks of crops, effective data support is provided for accurate monitoring of crops.

[0030] By conducting phenological statistical analysis, we can dig out the monitoring links under the crop growth cycle, which define the monitoring requirements and goals of each crop growth stage. Specifically, we divide the link nodes according to the growth cycle, and configure specific monitoring conditions and execution logic on each node to ensure that the automatic monitoring equipment can conduct targeted monitoring of pest and disease risks at each stage.

[0031] Specifically, each link node contains control conditions and logical conditions, where the control conditions define under what conditions the automatic monitoring device should start or adjust the monitoring parameters, for example, the monitoring device should perform high-frequency monitoring within a certain temperature range or humidity change range to better capture possible changes in pests and diseases. The logical conditions are the logical judgment criteria for the execution of the control conditions, which are used to refine the working mode of the automatic monitoring device in different states, for example, adjusting the monitoring frequency according to the trend of increasing temperature or decreasing humidity, or increasing the sensor resolution at nodes with higher pest and disease risks.

[0032] By constructing the monitoring link, the monitoring device can dynamically adapt the monitoring mode according to the growth characteristics of the crops, thereby improving the accuracy and timeliness of monitoring.

[0033] Wherein, each link node in the monitoring link includes control conditions and logic conditions, and step S1 of the present application also includes:

[0034] Divide the growth stages and conduct phenological statistics to determine the stage monitoring indicators, wherein the stage monitoring indicators are determined based on the types and distribution characteristics of pests and diseases; interact with the monitoring configuration information of the automatic monitoring equipment, perform parameter-control conversion on the stage monitoring indicators, and determine the control conditions; identify the stage-specific phenological statistical data and explore the logical conditions for self-regulation of sensor monitoring.

[0035] First, the growth stages of the crops are divided to determine the various stages of the crops in different growth cycles. Specifically, the growth stages of the crops can be divided into multiple stages according to the crop variety and growth characteristics, such as the germination period, the vegetative growth period, the flowering period and the maturity period, etc.; or divided into stages according to the evolutionary characteristics of pests and diseases, which is not specifically limited in the embodiments of the present application.

[0036] Further phenological statistics are conducted, that is, quantitative analysis of the climate, environmental factors and crop physiological characteristics of the divided growth stages is conducted to determine the specific monitoring indicators for each stage. For example, data mining can be performed based on recorded data of the same crop category and similar planting environment.

[0037] Next, according to the results of phenological statistics, stage monitoring indicators are set for the types and risks of pests and diseases that crops may encounter at different growth stages. For example, the stage monitoring indicators include but are not limited to information such as the type of pests and diseases, probability of occurrence, and distribution characteristics. Specific goals are set for the monitoring tasks at each stage based on these characteristics. For example, during the vegetative growth period of crops, common leaf pests may be monitored; while during the flowering period, more attention may be paid to the impact of flowering pests.

[0038] Among them, the pest and disease types refer to different types of pests and diseases that affect crops, and the distribution characteristics refer to the spatial distribution patterns of pests and diseases in the crop growing area. Based on the above information, accurate monitoring strategies can be formulated.

[0039] Subsequently, the monitoring configuration information of the automatic monitoring device is exchanged, that is, the monitoring hardware structure and software configuration are determined, and based on them, the monitoring indicators of each stage are converted into corresponding parameters under the control of the automatic monitoring device. For example, phenological statistics data and stage monitoring indicators are transmitted through the communication interface with the automatic monitoring device to ensure that the device can adapt to environmental changes and adjust the monitoring mode in real time. For example, if the probability of occurrence of a type of pest and disease is high at a certain stage, the device will adjust the monitoring frequency and the sensitivity of the sensor to ensure that high-risk areas receive sufficient attention. Parameter-control conversion means adjusting the parameter settings of the monitoring equipment according to the stage monitoring indicators in order to achieve accurate real-time monitoring.

[0040] Finally, the logical conditions for sensor monitoring self-adjustment refer to the logical method of dynamically adjusting the monitoring strategy based on phenological data, that is, the conditions and adjustment logic for determining whether to adjust the parameters and controls for the monitoring scenario. For example, if high temperatures occur during a certain growth period, the equipment may automatically increase the monitoring frequency according to climate changes, or adjust the working modes of different types of sensors according to climate conditions and types of pests and diseases, automatically adapt to environmental changes to improve monitoring results, that is, trigger the critical temperature value of the above adjustment, and the monitoring logic under the adjusted working mode.

[0041] The above adjustment process not only ensures the high efficiency of monitoring, but also can cope with complex environmental changes and ensure the stability and accuracy of the monitoring system.

[0042] Among them, to mine the logical conditions of sensor monitoring self-adjustment, step S1 of the present application also includes:

[0043] Traverse the phenological statistical data of the first growth stage, perform clustering based on the control and adjustment method, and determine a group of clusters; identify the group of clusters, explore the adjustment trigger conditions, and the linear parameter adjustment relationship with the monitoring parameters as the independent variables; establish a mapping between the first growth stage and the control and adjustment method, and between the adjustment trigger conditions and the linear parameter adjustment relationship as the logical conditions of the first growth stage.

[0044] First, the first growth stage is any growth stage under the monitoring link, and the phenological statistical data of the first growth stage is traversed, including the physiological changes, climatic conditions, environmental factors, etc. of the crops in this stage. The above factors jointly affect the growth of crops and the risks of diseases and pests they may encounter.

[0045] Arrange the adjustment methods existing in the phenological statistical data, and determine the corresponding trigger conditions for different adjustment methods. Specifically, the phenological statistical data are grouped based on the adjustment method, and the division results are used as the group of clusters. The adjustment methods of monitoring and control in the same group, that is, the monitoring and control strategies adopted are the same. For example, in hot weather, a more frequent monitoring frequency may be adopted, while in a high humidity environment, the sensitivity of the sensor may need to be adjusted. The purpose of clustering is to group similar growth environments and pest and disease types together so that targeted control and adjustment can be carried out in subsequent operations.

[0046] Among them, the adjustment trigger condition refers to the monitoring system should automatically activate the corresponding monitoring mode or adjust the parameter settings of the monitoring equipment when certain parameters reach a certain threshold according to these environmental characteristics and growth status. For example, if the crop is in a high temperature and drought environment, the system can automatically trigger more frequent humidity monitoring according to the set temperature threshold. The temperature threshold is the adjustment trigger condition in this environment, and triggering more frequent humidity monitoring is the adjustment method. In this environment, the linear relationship is based on the relationship between the excess amount of the temperature threshold and the adjustment scale. The linear relationship is the relationship between the change of the monitoring parameter and the occurrence of pests and diseases.

[0047] Furthermore, a mapping between the first growth stage and the control adjustment mode, the adjustment trigger condition and the linear parameter adjustment relationship is established as the first link node of the monitoring link. Similarly, according to the above steps, the node construction of each stage is completed to generate the monitoring link.

[0048] By constructing the monitoring link, the entire monitoring process will be more adaptive, and can dynamically adjust monitoring strategies and equipment parameters according to the specific needs of different crop growth stages, thereby improving monitoring accuracy and achieving precision agricultural management.

[0049] S2: Setting a monitoring mode, wherein the monitoring mode includes a first range monitoring and a second directional monitoring, wherein the second directional monitoring includes a sensing orientation and a position orientation;

[0050] S3: Fitting the monitoring mode and the monitoring link, performing self-learning on the front-end sensor array of the automatic monitoring device, and initializing the sensor control module;

[0051] Specifically, the first range monitoring refers to the full-area monitoring through a sensor array covering a wide area, with the purpose of quickly and extensively obtaining relevant data on crops and the environment. It is usually used to monitor large-scale environmental changes, such as climate change or potential large-scale spread of pests and diseases.

[0052] The second directional monitoring is more refined, focusing on the monitoring of specific areas or targets. Directional monitoring is divided into two modes: sensor orientation and position orientation. Among them, sensor orientation refers to the directional limitation of the sensor type, that is, based on the data monitored in the first range, the monitoring needs are determined, and then the corresponding sensor type in the sensor array is triggered for targeted perception to improve the accuracy of perception monitoring. The position orientation is that during the monitoring process, the sensor is adjusted according to the specific target it perceives to ensure that its monitoring focus is always concentrated on the key areas of pests or crop growth. For example, when a sensor recognizes signs of pests on crop leaves, it will automatically focus on that area, increasing the monitoring frequency and sensing accuracy.

[0053] Next, the monitoring mode and the monitoring link are fitted, that is, the monitoring link is used as the monitoring task requirement, the monitoring mode is used as the execution standard, and the monitoring mode is dynamically adjusted according to the growth stage of the crop and the current environmental status.

[0054] Furthermore, the front-end sensor array is an intelligent sensor installed in the automatic monitoring device, including multiple sensor types. Based on the monitoring mode and the monitoring link, the front-end sensor array of the automatic monitoring device is self-learned. Exemplarily, the working strategy of the sensor array is optimized based on the sample learning under the monitoring mode and the monitoring link, and the sensor control module is determined according to the learning results of the sensor array. It can adjust its monitoring strategy according to the performance in different environments, so that it can still provide high-precision monitoring results under changing environmental conditions. For example, the sensor can automatically adjust the monitoring sensitivity and range according to the growth of crops, and optimize the monitoring effect under different seasons and climate conditions.

[0055] In summary, it is possible to adaptively adjust the monitoring mode according to actual needs, thereby achieving accurate and flexible pest and disease monitoring, and significantly improving the efficiency and accuracy of crop health management.

[0056] S4: Control the automatic monitoring device to perform inspection based on a preset path, and based on the sensor control module, trigger the first sensor array to perform range monitoring control, and trigger the second sensor array to perform directional monitoring control;

[0057] In the embodiments of the present application, for farmland in a large area, in order to improve the monitoring efficiency, multiple automatic monitoring devices are generally configured. Specifically, based on the self-set division standard, the farmland is divided into multiple grids, and each grid is assigned an automatic monitoring device. Determine the inspection path of the automatic monitoring device configured in the first grid, that is, the preset path, and the automatic monitoring device moves in the field according to the predetermined route to gradually complete the coverage of the entire monitoring area. Specifically, in the process of setting the path, factors such as the distribution of crops, climatic conditions in the field, and crop growth stages may be considered to ensure the comprehensiveness and pertinence of the monitoring.

[0058] The core function of the sensor control module is to decide when to start which sensors for monitoring and adjust the working status of the sensors, such as sampling frequency, sensitivity, etc., based on the real-time environmental data and monitoring mode. Furthermore, based on the sensor control module, the first sensor array is triggered, that is, a group of sensors are started to perform monitoring tasks in a wide area. In the embodiment of the present application, the first sensor array is at least one fixed sensor with a large coverage area, which is suitable for rapid inspection of the entire field environment and provides an overall picture of crop health.

[0059] Then, after completing the range monitoring, the monitoring data is preliminarily judged. When there is abnormal data fluctuation, the sensor type that matches the abnormal feature is determined based on the specific abnormal feature, as the second sensor matrix, which is used to perform more detailed and directional monitoring of specific areas or targets. Directional monitoring may involve specific sensor types, such as infrared sensors, imaging sensors, or gas sensors, which are used to monitor detailed information such as pests and diseases on crop leaves, roots, or flowering periods. For example, if range monitoring finds an abnormality in a certain area, the directional monitoring array will be activated to focus on the crop leaves in the area to check whether there are signs of pests and diseases.

[0060] Through the coordination of range monitoring control and directional monitoring control, automatic monitoring equipment can achieve all-round and refined monitoring of crops. Dynamically adjust the monitoring mode to ensure that the equipment can collect data in the most effective way under different environments and monitoring requirements, thereby providing real-time and accurate basis for subsequent decision-making and intervention.

[0061] Among them, Figure 2 As shown, the first sensor array is triggered to perform range monitoring control, and the second sensor array is triggered to perform directional monitoring control. Step S4 of the present application also includes:

[0062] For the front-end sensor array, a first sensor array is divided, wherein the first sensor array is a fixed sensor type; based on the first sensor array, fuzzy scanning monitoring of a first range is performed to determine first sensor data; the first sensor data is transmitted back to perform sensor identification and directional monitoring control.

[0063] In the embodiment of the present application, the sensor array is divided into different sub-arrays according to the specific functional requirements of the front-end sensor array. Specifically, the first sensor array refers to a group of sensors specifically used for range monitoring, which have a wide coverage capability and can collect data in a large area. Among them, the first sensor array is a fixed type and does not flexibly switch the sensor type according to the scene.

[0064] Furthermore, based on the first sensor array, fuzzy scanning monitoring of the first range is performed, that is, a wide and fuzzy scan is performed in a predetermined area with a certain step size or time interval. The first range is the scanning coverage range of the first sensor array, which can quickly cover a larger monitoring area and provide preliminary data for subsequent more precise monitoring.

[0065] After the fuzzy scanning monitoring of the first range is completed, the first sensor data is determined, which refers to the sensor data collected by the fuzzy scanning, which is analyzed to provide a decision basis for whether subsequent directional monitoring or control is required.

[0066] Specifically, the first sensing data is transmitted back, that is, the monitoring data obtained from the first sensor array is uploaded to the central processor or cloud platform for analysis and identification to determine which areas or indicators are abnormal and whether there are potential risks of pests and diseases. Based on the identification results, specific areas or crops are selected for more precise directional monitoring. This may include activating a higher-precision sensor array, or adjusting the direction and position of monitoring in order to further focus on specific areas, such as crop leaves, roots, flowering period, etc., for in-depth monitoring.

[0067] In summary, it is possible to flexibly adjust monitoring strategies based on real-time data feedback, from range monitoring to targeted monitoring, to achieve efficient and accurate crop health management, and to promptly detect and respond to potential pest and disease threats.

[0068] Among them, the sensor identification and directional monitoring control, step S4 of this application also includes:

[0069] Determine the first sensor recognition result, determine the directional sensing type and the directional position; based on the directional sensing type, trigger the second sensor array, wherein the second sensor array is a non-directional sensor type; based on the directional position, control the second sensor array to perform directional monitoring.

[0070] First, the first sensor recognition results are determined and key features in the data are identified, especially potential signs of abnormal conditions or pests and diseases that may exist in the environment. For example, during range monitoring, the system may identify abnormal temperature and humidity values ​​in certain areas, or that the leaves of certain crops show abnormal growth patterns.

[0071] Based on the specific monitoring needs derived from the first sensor recognition result, it is determined which type of sensor to use for subsequent directional monitoring and the specific location that needs to be monitored. For example, if the recognition result shows that the humidity value in a certain area is too high, a sensor type that specifically monitors pests and diseases (such as a gas sensor, an imaging sensor, etc.) may be used for directional monitoring, and positioned at a specific crop or area in the area for detailed monitoring. Therefore, the directional sensing type refers to the type of sensor selected to perform directional monitoring, and the directional location refers to the specific area that needs further monitoring determined based on the recognition result.

[0072] Based on the directional sensing type, the second sensor array is triggered. The second sensor array belongs to the non-directional sensor type, that is, the sensor type for directional monitoring is specified according to the monitoring requirements determined by the first sensor data. Specifically, the combination of the second sensor array is different for different monitoring requirements. It can provide accurate monitoring data in a small range, helping the system to further confirm the specific manifestations of pests and diseases or other environmental abnormalities.

[0073] Finally, the directional position is used as a reference to guide the second sensor array to perform the directional monitoring task. Specifically, the second sensor array is directed to the specific position or area, and the position is monitored in more detail.

[0074] In summary, monitoring and control can flexibly and efficiently conduct targeted monitoring based on preliminary range monitoring, and achieve precise control of specific areas or crops. This step-by-step control not only improves the accuracy of monitoring, but also can adjust strategies in a timely manner according to actual monitoring results, thereby ensuring the scientific and efficient management of crop health.

[0075] Among them, the monitoring control has environmental error compensation based on the environmental state chain, and step S4 of this application also includes:

[0076] Based on the geographical location and climatic conditions of the crops, the field environmental characteristics are determined; the field environmental characteristics are traversed to determine a multi-level environmental state, wherein the multi-level environmental state is evaluated based on a baseline environmental state; the redundant fault-tolerant mechanism of the automatic monitoring equipment is obtained, and an environmental state chain is constructed in combination with the multi-level environmental state, wherein the environmental state chain is constructed based on the Markov principle to perform control compensation of environmental errors.

[0077] First, based on the geographical location and climatic conditions of the crops, that is, by combining the geographical location of the crop location (such as longitude and latitude, elevation, etc.) and the local climatic conditions (such as temperature, humidity, precipitation, wind speed, etc.), the overall environmental characteristics of the field are determined. Among them, the field environmental characteristics not only affect the growth of crops, but also directly affect the health of crops, the risk of pests and diseases, etc. The determination of the geographical location helps to understand the soil type and climate zone where the crops are located, while the climate conditions can provide real-time weather data, such as extreme weather events such as high temperature and heavy rain, which may have a significant impact on the growth of crops.

[0078] The multi-level environmental state refers to the different classifications and classifications of environmental conditions by the system. For example, different levels from the best state to the worst state. For example, in an environment suitable for crop growth, it can be defined as a "baseline environmental state"; when the temperature is too high, the humidity is too low, or the precipitation is insufficient, the environmental state may be assessed as "abnormal" or "bad".

[0079] Furthermore, obtaining the redundant fault-tolerant mechanism of the automatic monitoring device refers to the redundant design of the automatic monitoring device itself, which ensures that when the device or system fails, the monitoring task can be continued through the backup system or backup solution. For example, when certain sensors or communication modules fail, the backup sensors can automatically take over the monitoring task to ensure that the monitoring process is not interrupted. The redundant mechanism can significantly improve the reliability of the system and avoid the failure of the entire monitoring system due to the failure of a single component.

[0080] The environmental state chain is a chain structure constructed according to the transition between the multi-level environmental states. By analyzing the changing rules of the environmental state, the system can dynamically predict and adjust the monitoring strategy to adapt to different environmental changes. Specifically, the construction of the environmental state chain is based on the Markov principle, that is, the state at a certain moment is only related to the state at the previous moment, and has nothing to do with the previous historical state. Therefore, based on the current environmental state, the possible state at the next moment can be inferred, and corresponding measures can be taken accordingly.

[0081] During the monitoring process, the collection and analysis of environmental data may be affected by various factors, such as sensor errors, changes in the external environment, etc., which may lead to deviations in the monitoring data. To this end, the accuracy of the environmental state assessment and monitoring results is adjusted through the environmental error control compensation mechanism. For example, when the system detects that a certain error has occurred in the sensor, through the environmental state chain, the system can infer the true environmental state based on the previous state and perform error correction. This compensation mechanism can ensure that the system can still provide accurate monitoring results even when errors occur.

[0082] In summary, based on the geographical location and climatic conditions of the crops, the field environmental characteristics can be flexibly and accurately evaluated, and the growth status of the crops can be dynamically monitored. At the same time, the reliability and accuracy of the system can be improved through redundant fault tolerance and environmental error compensation mechanisms, ensuring the scientificity and efficiency of crop disease and pest monitoring and management.

[0083] The preset path is constrained by a field monitoring grid, and the field monitoring grid can be dynamically divided and reconstructed based on a guiding strategy for cross-grid cross-monitoring.

[0084] The application steps also include:

[0085] Obtain a field monitoring grid, wherein each automatic monitoring device corresponds to a monitoring grid; receive grid monitoring data and upload it to the cloud, conduct global analysis and cross-monitoring decision-making, and determine an interactive monitoring strategy, wherein the grid reconstruction strategy is an accompanying output strategy; based on the interactive monitoring strategy, guide the automatic monitoring device to perform automatic monitoring and control of pests and diseases.

[0086] Specifically, the field monitoring grid is a regular or irregular grid system divided according to factors such as crop planting distribution and field size and shape. Each grid represents a monitoring area, and each monitoring area is equipped with an automatic monitoring device. The monitoring path will be carried out within these grids to ensure that all monitoring points are covered. Through such a design, the system can systematically and comprehensively monitor and control each monitoring area.

[0087] Specifically, in the embodiment of the present application, after the automatic monitoring equipment completes the monitoring of each monitoring grid, the monitoring data will be uploaded to the cloud platform. The cloud platform performs a global analysis of the data of all grids, that is, the monitoring data of all areas are aggregated and analyzed to obtain a global monitoring result to determine the monitoring location that needs feedback adjustment.

[0088] At the same time, the field monitoring grid is not fixed, but can be dynamically adjusted according to actual conditions and needs. The cross-grid cross-monitoring guidance strategy involves global monitoring adjustments, that is, when there is feedback monitoring guidance at a certain location, feedback monitoring control is performed based on the nearest equipment at that location, the automatic monitoring equipment in the grid or the neighborhood grid, and it is used as the cross-grid cross-monitoring. In this case, the grid range is re-divided and adjusted for the current adjustment to improve the flexibility and globality of monitoring control.

[0089] Exemplarily, several grids related to feedback adjustment are re-divided according to the relative position of the current device to determine the grid reconstruction strategy, wherein the grid division adjustment is not required every time the interactive monitoring strategy is determined. Exemplarily, when the determined feedback device is a neighborhood grid device, that is, a nearby device, and the interactive monitoring strategy causes the grid to deviate far from the device itself, the grid reconstruction adjustment can be performed; otherwise, there is no need to perform grid adjustment, and timely adjustments are made according to actual conditions.

[0090] In summary, based on the interactive monitoring strategy, the automatic monitoring equipment is controlled to automatically monitor and control pests and diseases. Through technical means such as dynamic division of field monitoring grids, cross-monitoring decision-making and global analysis of cloud platforms, accurate pest and disease monitoring can be carried out in a wider range, while improving monitoring efficiency and accuracy.

[0091] The application steps also include:

[0092] Obtain remote monitoring access instructions; upload the remote monitoring access instructions to the cloud, analyze them in combination with the grid monitoring data, and determine the instruction execution device and execution strategy; based on the instruction execution device and the execution strategy, perform remote monitoring access instruction control.

[0093] Specifically, the remote monitoring access instruction is a remote monitoring access request from an external or superior monitoring center. The monitoring access instruction may include specific operation requirements, such as adjusting monitoring parameters, turning on a monitoring device, or reconfiguring the monitoring mode of a network sensor. The remote monitoring access instruction is transmitted to the control center or cloud platform of the automatic monitoring device through a communication network.

[0094] Combined with the grid monitoring data, determine whether the remote access instructions need to be executed, which automatic monitoring device executes the instructions, and how to execute these instructions. Formulate appropriate execution strategies based on the current status of the equipment in the entire field and the monitoring needs. For example, if there is a risk of pests and diseases in crops in certain grids, the system may instruct specific sensor arrays to start, or adjust the operating frequency and monitoring method of existing monitoring equipment. The formulation of this strategy ensures the efficiency and accuracy of monitoring tasks.

[0095] Finally, based on the instruction execution device, that is, the automatic monitoring device that executes the remote monitoring access instruction, and the execution strategy, that is, the execution method of the instruction, the remote monitoring access instruction control is performed. In summary, this solution realizes the functions of remote monitoring and dynamic adjustment of monitoring equipment through the combination of remote monitoring access instructions, cloud analysis and device control strategies, further improves the intelligence level and reaction speed of farmland pest and disease monitoring, and improves the responsiveness and reliability of the entire monitoring system.

[0096] The present application provides a method for controlling automatic monitoring equipment for crop diseases and insect pests, which has the following technical effects:

[0097] 1. Through dynamic division of monitoring grids and precise path planning, all monitoring areas are ensured to be fully covered, the monitoring effect is optimized, and the adaptability and intelligence of the system are enhanced:

[0098] 2. The sensor array continuously optimizes the monitoring strategy through self-learning and adjustment mechanisms, improving the system's ability to adapt to environmental changes and threats from pests and diseases.

[0099] 3. The error control mechanism based on the multi-level environmental state chain effectively reduces the interference of environmental factors on the monitoring results and improves the accuracy and reliability of the monitoring data.

[0100] 4. Through the global analysis and cross-monitoring of grid data in the cloud, the global optimization of the monitoring strategy is ensured, and the responsiveness and decision-making efficiency of the monitoring system are improved.

[0101] 5. Support remote access and command control, optimize device management and adjustment strategies, and improve the response speed and accuracy of remote operations.

[0102] Embodiment 2: Based on the same inventive concept as the control method for automatic monitoring equipment for crop pests and diseases in the above embodiment, Figure 3 As shown, the present application provides a control system for automatic monitoring equipment for crop diseases and insect pests, the system comprising:

[0103] A monitoring link mining unit 11, wherein the monitoring link mining unit 11 is used to mine monitoring links under a growth cycle according to field crop data through phenological statistical analysis, wherein each link node in the monitoring link includes a control condition and a logic condition;

[0104] A monitoring mode setting unit 12, wherein the monitoring mode setting unit 12 is used to set a monitoring mode, wherein the monitoring mode includes a first range monitoring and a second directional monitoring, wherein the second directional monitoring includes a sensing orientation and a position orientation;

[0105] A sensor learning unit 13, the sensor learning unit 13 is used to fit the monitoring mode and the monitoring link, perform self-learning on the front-end sensor array of the automatic monitoring device, and initialize the sensor control module;

[0106] A monitoring control unit 14, the monitoring control unit 14 is used to control the automatic monitoring device to perform inspection based on a preset path, trigger the first sensor array to perform range monitoring control, and trigger the second sensor array to perform directional monitoring control based on the sensor control module;

[0107] The preset path is constrained by a field monitoring grid, and the field monitoring grid can be dynamically divided and reconstructed based on a guiding strategy for cross-grid cross-monitoring.

[0108] Among them, the monitoring link mining unit 11 is also used to perform the following steps: divide the growth stage and perform phenological statistics to determine the stage monitoring indicators, wherein the stage monitoring indicators are determined based on the type and distribution characteristics of pests and diseases; interact with the monitoring configuration information of the automatic monitoring equipment, perform parameter control conversion on the stage monitoring indicators, and determine the control conditions; identify stage-by-stage phenological statistical data and mine the logical conditions for sensor monitoring self-regulation.

[0109] Among them, the monitoring link mining unit 11 is also used to perform the following steps: traverse the phenological statistical data of the first growth stage, cluster based on the control and adjustment method, and determine a group of clusters; identify the group of clusters, mine the adjustment trigger conditions, and the linear parameter adjustment relationship with the monitoring parameters as the independent variables; establish a mapping between the first growth stage and the control and adjustment method, and between the adjustment trigger conditions and the linear parameter adjustment relationship as the logical conditions of the first growth stage.

[0110] Among them, the monitoring and control unit 14 is also used to perform the following steps: dividing the front-end sensor array into a first sensor array, wherein the first sensor array is a fixed sensor type; performing fuzzy scanning monitoring of a first range based on the first sensor array to determine first sensor data; and transmitting the first sensor data back to perform sensor identification and directional monitoring and control.

[0111] Among them, the monitoring control unit 14 is also used to perform the following steps: determine the first sensor recognition result, determine the directional sensing type and directional position; based on the directional sensing type, trigger the second sensor array, wherein the second sensor array is a non-directional sensor type; based on the directional position, control the second sensor array to perform directional monitoring.

[0112] The system is also used to perform the following steps: obtaining a field monitoring grid, wherein each automatic monitoring device corresponds to a monitoring grid; receiving grid monitoring data and uploading it to the cloud, performing global analysis and cross-monitoring decision-making, and determining an interactive monitoring strategy, wherein the grid reconstruction strategy is a companion output strategy; based on the interactive monitoring strategy, guiding the automatic monitoring device to perform automatic monitoring and control of pests and diseases.

[0113] Among them, the monitoring and control unit 14 is also used to perform the following steps: determine the field environmental characteristics based on the crop geographical location and climatic conditions; traverse the field environmental characteristics to determine the multi-level environmental state, wherein the multi-level environmental state is evaluated based on the baseline environmental state; obtain the redundant fault-tolerant mechanism of the automatic monitoring equipment, and build an environmental state chain in combination with the multi-level environmental state, wherein the environmental state chain is constructed based on the Markov principle to perform control compensation of environmental errors.

[0114] Among them, the system is also used to execute the following steps: obtain remote monitoring access instructions; upload the remote monitoring access instructions to the cloud, analyze them in combination with the grid monitoring data, and determine the instruction execution device and execution strategy; based on the instruction execution device and the execution strategy, perform remote monitoring access instruction control.

[0115] Through the above detailed description of a control method for automatic monitoring equipment for crop diseases and insect pests in this specification, those skilled in the art can clearly understand the control method for automatic monitoring equipment for crop diseases and insect pests in this embodiment. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0116] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A control method for automatic monitoring equipment for crop diseases and insect pests, characterized in that: The method comprises: Based on the field crop data, the monitoring links under the growth cycle are mined through phenological statistical analysis, wherein each link node in the monitoring link contains control conditions and logic conditions; Setting a monitoring mode, wherein the monitoring mode includes a first range monitoring and a second orientation monitoring, wherein the second orientation monitoring includes a sensing orientation and a position orientation; Fitting the monitoring mode and the monitoring link, performing self-learning on the front-end sensor array of the automatic monitoring device, and initializing the sensor control module; Control the automatic monitoring device to perform inspection based on a preset path, trigger the first sensor array to perform range monitoring control and trigger the second sensor array to perform directional monitoring control based on the sensor control module, wherein the monitoring control includes environmental error compensation based on an environmental state chain; The preset path is constrained by the field monitoring grid, and the field monitoring grid can be dynamically divided and reconstructed based on the guidance strategy of cross-grid cross-monitoring; The first sensor array is triggered to perform range monitoring and control, and the second sensor array is triggered to perform directional monitoring and control, including: For the front-end sensor array, divide the first sensor array, wherein the first sensor array is a fixed sensor type; Perform fuzzy scanning monitoring of a first range based on the first sensor array to determine first sensing data; Transmitting the first sensor data back to perform sensor identification and directional monitoring and control; Wherein, the sensing identification and directional monitoring control includes: Determine the first sensor recognition result, determine the directional sensing type and directional position; Based on the directional sensing type, triggering a second sensor array, wherein the second sensor array is a non-directional sensor type; Based on the directional position, the second sensor array is controlled to perform directional monitoring.

2. A control method for automatic monitoring equipment for crop diseases and insect pests as claimed in claim 1, characterized in that: Each link node in the monitoring link includes control conditions and logic conditions, including: Divide the growth stages and conduct phenological statistics to determine the stage monitoring indicators, wherein the stage monitoring indicators are determined based on the types and distribution characteristics of pests and diseases; Interacting the monitoring configuration information of the automatic monitoring equipment, performing parameter control conversion on the monitoring indicators of the stage, and determining the control conditions; Identify phase-specific phenological statistics and explore the logical conditions for self-regulation of sensor monitoring.

3. A control method for automatic monitoring equipment for crop diseases and insect pests as claimed in claim 2, characterized in that: The logical conditions for mining sensor monitoring self-adjustment include: Traversing the phenological statistical data of the first growth stage, clustering based on the control and regulation methods, and determining a set of clusters; Identify the set of clusters, mine the adjustment trigger conditions, and the linear adjustment relationship with the monitoring parameters as independent variables; A mapping between the first growth stage and the control adjustment mode, the adjustment trigger condition and the linear parameter adjustment relationship is established as a logical condition for the first growth stage.

4. A control method for automatic monitoring equipment for crop diseases and insect pests as claimed in claim 1, characterized in that: After monitoring and control, including: Obtaining a field monitoring grid, wherein each automatic monitoring device corresponds to a monitoring grid; Receive grid monitoring data and upload it to the cloud, conduct global analysis and cross-monitoring decision-making, and determine interactive monitoring strategies, among which the grid reconstruction strategy is an accompanying output strategy; Based on the interactive monitoring strategy, the automatic monitoring equipment is guided to perform automatic monitoring and control of pests and diseases.

5. A control method for automatic monitoring equipment for crop diseases and insect pests as claimed in claim 1, characterized in that: Monitoring and control includes environmental error compensation based on the environmental state chain, including: Determine field environmental characteristics based on crop location and climatic conditions; Traversing the field environmental characteristics to determine a multi-level environmental state, wherein the multi-level environmental state is evaluated based on a baseline environmental state; The redundant fault-tolerant mechanism of the automatic monitoring device is obtained, and an environmental state chain is constructed in combination with the multi-level environmental state, wherein the environmental state chain is constructed based on the Markov principle and performs control compensation of environmental errors.

6. A control method for automatic monitoring equipment for crop diseases and insect pests as claimed in claim 4, characterized in that: The method further comprises: Get remote monitoring access instructions; Upload the remote monitoring access instruction to the cloud, analyze it in combination with the grid monitoring data, and determine the instruction execution device and execution strategy; Based on the instruction execution device and the execution strategy, instruction control of remote monitoring access is performed.

7. A control system for automatic monitoring equipment for crop diseases and insect pests, characterized in that: The system is used to execute a control method for automatic monitoring equipment for crop diseases and insect pests according to any one of claims 1 to 6, and the system comprises: A monitoring link mining unit, the monitoring link mining unit is used to mine monitoring links under the growth cycle according to field crop data through phenological statistical analysis, wherein each link node in the monitoring link includes a control condition and a logic condition; A monitoring mode setting unit, the monitoring mode setting unit is used to set a monitoring mode, wherein the monitoring mode includes a first range monitoring and a second directional monitoring, wherein the second directional monitoring includes a sensing orientation and a position orientation; A sensor learning unit, the sensor learning unit is used to fit the monitoring mode and the monitoring link, perform self-learning on the front-end sensor array of the automatic monitoring device, and initialize the sensor control module; A monitoring control unit, the monitoring control unit is used to control the automatic monitoring device to perform inspection based on a preset path, trigger the first sensor array to perform range monitoring control, and trigger the second sensor array to perform directional monitoring control based on the sensor control module; The preset path is constrained by a field monitoring grid, and the field monitoring grid can be dynamically divided and reconstructed based on a guiding strategy for cross-grid cross-monitoring.

Images