A pest control equipment spraying management system based on machine learning

Abstract

This invention relates to the field of pest control technology, and more particularly to a pest control equipment spraying management system based on machine learning. The system includes: an equipment data acquisition module for acquiring pest control equipment data and target area images within a monitoring period; a real-time data acquisition module for real-time acquisition of pest control target location data and target area environmental data; a region level analysis module for dividing the target area into various pest control zones, classifying each zone into levels, and constructing a pest control spraying index; an environmental monitoring module for analyzing the volatility anomalies in each pest control zone; a pest control target analysis module for analyzing the target density anomalies in each pest control zone; a spraying management module for generating spraying management plans for each pest control zone; and a pesticide efficacy monitoring module for optimizing the spraying management plans for each pest control zone. This invention effectively improves the spraying efficiency of pest control equipment.

Description

Technical Field

[0001] This invention relates to the field of pest control technology, and in particular to a pest control equipment spraying management system based on machine learning. Background Technology

[0002] Traditional pest control methods typically rely on manual experience to set fixed spraying parameters, such as dosage, frequency, and timing. However, this method struggles to adapt to complex and changing environmental conditions (such as weather variations and different crop growth stages), easily leading to resource waste, environmental pollution, and impacts on non-target organisms. With the development of smart technologies and data analytics capabilities, it has become possible to use machine learning models to predict optimal spraying strategies, improving efficiency and reducing side effects.

[0003] Chinese Patent Publication No. CN115779113A discloses a terminal disinfection robot and a terminal disinfection system, belonging to the field of disinfection technology. The terminal disinfection robot includes a central control module, a spray disinfection module, a mist disinfection module, a reagent preparation module, an environmental sensing module, an intelligent analysis module, a path planning module, a power supply module, and a movement module. The environmental sensing module, intelligent analysis module, and reagent preparation module work together to automatically detect indoor spaces and objects, automatically calculate the required disinfection volume and surface area, calculate the required reagent dosage, and automatically prepare the reagent in automatic mode. Then, the spray disinfection module and mist disinfection module are used to achieve surface disinfection and air disinfection. However, this invention's disinfection process involves uniform spraying to achieve a disinfection effect, but it does not analyze the distribution of the actual disinfection targets, thus failing to achieve precise and efficient disinfection and exhibiting low spraying efficiency. Summary of the Invention

[0004] The purpose of this invention is to provide a machine learning-based pesticide spraying management system to solve at least one of the problems existing in the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A machine learning-based pesticide spraying management system, characterized in that it includes:

[0007] The equipment data acquisition module is used to acquire data from the disinfection equipment and images of the target area during the monitoring period;

[0008] The real-time data acquisition module is used to collect real-time data on the location of the disinfection target and the environmental data of the target area;

[0009] The regional level analysis module is used to divide the target area according to the target area image to obtain each disinfection area, and to classify each disinfection area according to the quantity of stored items in each disinfection area. It is also used to construct a disinfection spraying index based on the level classification results.

[0010] The environmental monitoring module is used to analyze the volatility anomalies of each disinfection area based on the environmental data of the target area and the pesticide spraying index within the monitoring period;

[0011] The disinfection target analysis module is used to analyze the anomalies in target density in each disinfection area based on the disinfection target location data and the disinfection spraying index;

[0012] The spraying management module is used to generate spraying management plans for each disinfection area based on the analysis results of volatility anomalies and target density anomalies in each disinfection area.

[0013] The efficacy monitoring module is used to optimize the spraying management plan for each disinfection area based on the activity frequency of the disinfection targets in each disinfection area after the spraying cycle.

[0014] Furthermore, the region level analysis module includes a region division unit, which is used to calculate the minimum vertical line segment length Lx and the minimum horizontal line segment length Wx;

[0015] The region division unit uses the rectangle formed by the minimum vertical line segment length Lx and the minimum horizontal line segment length Wx as the division unit to divide the target region image to obtain each elimination region D(i).

[0016] Furthermore, the regional level analysis module also includes a level division unit. The level division unit is used to calculate the storage density ρ(i) of each disinfection area based on the quantity of stored items in each disinfection area, and to classify each disinfection area according to ρ(i). Then, a disinfection spraying index is constructed based on the level division results: if ρ(i) < N1, the level division unit classifies the disinfection area into level three and sets the disinfection spraying index to P1; if N1 ≤ ρ(i) < N2, the level division unit classifies the disinfection area into level two and sets the disinfection spraying index to P2; if ρ(i) ≥ N2, the level division unit classifies the disinfection area into level one and sets the disinfection spraying index to P3; where N1 is the first preset storage density and N2 is the second preset storage density.

[0017] Furthermore, the environmental monitoring module includes a temperature anomaly analysis unit, which is used to compare the temperature t(i) of each disinfection area within the monitoring period with the preset evaporation temperature T to determine the temperature anomaly of each disinfection area. The temperature anomaly of each disinfection area includes normal and abnormal. When the temperature of each disinfection area is normal, the temperature anomaly coefficient is set to WD1(i); when the temperature of each disinfection area is abnormal, the temperature anomaly coefficient is set to WD2(i).

[0018] Furthermore, the environmental monitoring module also includes a humidity anomaly analysis unit, which is used to compare the humidity s(i) of each disinfection area within the monitoring period with each preset evaporation humidity to determine the humidity anomaly of each disinfection area. The humidity anomaly of each disinfection area includes normal and abnormal. When the humidity of the disinfection area is abnormal, the humidity anomaly coefficient is set to SD1(i); when the humidity of the disinfection area is normal, the humidity anomaly coefficient is set to SD2(i).

[0019] Furthermore, the environmental monitoring module also includes a volatilization anomaly analysis unit, which is used to analyze the volatilization anomaly of each disinfection area based on the temperature anomaly analysis results, humidity anomaly analysis results, and disinfection spraying index construction results of each disinfection area within the monitoring period. The analysis results of the volatilization anomaly of each disinfection area include normal and abnormal.

[0020] Furthermore, the disinfection target analysis module includes a density anomaly analysis unit, which is used to calculate the target density ρm(i) of each disinfection area based on the disinfection target location data, and compare ρm(i) with the preset target density P to determine the target density anomaly of each disinfection area. The target density anomaly of each disinfection area includes normal target density and abnormal target density.

[0021] Furthermore, the pest control target analysis module also includes a drug resistance analysis unit. The drug resistance analysis unit is used to analyze the drug resistance of the pest control targets in each pest control area based on the adult insect ratio μ(i) of the pest control targets in each pest control area. The drug resistance of the pest control targets in each pest control area includes normal and abnormal. When the drug resistance of the pest control area is abnormal, the preset target density is adjusted to P(i).

[0022] Furthermore, the spraying management module is used to generate a spraying management plan for each disinfection area based on the analysis results of volatilization anomalies and target density anomalies within the monitoring period:

[0023] If the target density in the disinfection area is normal, the spraying management module determines that the active disinfection target in the disinfection area is normal, sets the spraying cycle of the disinfection area to XT1(i), sets XT1(i) = XT0, sets the spraying amount of the disinfection area to PY1, and sets PY1(i) = PY0 × [Lx × Wx];

[0024] If the volatilization of the target area is abnormal and the target density of the disinfection area is abnormal, the spraying management module determines that the disinfection of the disinfection area is abnormal and sets the disinfection cycle of the disinfection area to XT2(i). XT2(i) is set to XT0×{1-[a1×temperature anomaly coefficient+a2×humidity anomaly coefficient-B×disinfection spraying index] / B×disinfection spraying index}. The spraying amount of the disinfection area is set to PY2(i). PY2(i) is set to PY0×[Lx×Wx]×exp[P×disinfection spraying index-ρm(i)].

[0025] If the evaporation in the target area is normal and the target density in the disinfection area is abnormal, the spraying management module determines that the active disinfection target in the disinfection area is abnormal, and sets the disinfection cycle of the disinfection area to XT3(i), setting XT3(i) = XT0, and sets the spraying amount of the disinfection area to PY3(i), setting PY3(i) = PY0 × exp[P × disinfection spraying index - ρm(i)];

[0026] Where XT0 is the initial disinfection cycle and PY0 is the initial spraying density.

[0027] Furthermore, the efficacy monitoring module is used to compare the activity frequency v(i) of the disinfection target in each disinfection area after the spraying cycle with the activity frequency V of the preset disinfection target to determine the abnormality of the activity frequency of the disinfection target in the disinfection area. The abnormality of the activity frequency of the disinfection target in the disinfection area includes normal and abnormal. When the activity frequency of the disinfection target in the disinfection area is abnormal, the spraying amount of the disinfection area is optimized to PYd(i)', where d is a numerical subscript and d = 1, 2, 3.

[0028] Compared with the prior art, the beneficial effects of the present invention are as follows: by dividing the target area into regions, the abnormality of volatility and the abnormality of the density of the disinfection target are specifically analyzed according to the division results, so as to determine whether the liquid is affected by the environment, and analyze the differences in the required amount of disinfectant in each disinfection area. Then, the spraying process of the disinfection equipment is managed according to the analysis results, so as to achieve precise and efficient disinfection of the disinfection equipment. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a schematic diagram of the structure of the pesticide spraying management system based on machine learning in this embodiment.

[0031] Figure 2 This is a schematic diagram of the regional level analysis module in this embodiment.

[0032] Figure 3 This is a schematic diagram of the environmental monitoring module in this embodiment.

[0033] Figure 4 This is a schematic diagram of the target analysis module for elimination in this embodiment. Detailed Implementation

[0034] To more clearly illustrate the present invention, the following description, in conjunction with preferred embodiments and accompanying drawings, further clarifies the invention. Similar components in the drawings are indicated by the same reference numerals. Those skilled in the art should understand that the specific description below is illustrative rather than restrictive and should not be construed as limiting the scope of protection of the present invention.

[0035] It should be noted that although the terms first, second, third, etc., may be used in the embodiments of this application for description, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of this application, first can also be referred to as second, and similarly, second can also be referred to as first.

[0036] Specifically, the machine learning-based pest control system described in this embodiment is applied to the spraying management of pest control robots in food distribution areas; the pest control targets of the pest control robots described in this embodiment are small or medium-sized insects such as cockroaches; the even-numbered pest control robots in this embodiment have the function of real-time image recognition of small or medium-sized insects such as cockroaches.

[0037] Please see Figure 1 As shown, it is a schematic diagram of the structure of the pesticide spraying management system based on machine learning in this embodiment, including:

[0038] The equipment data acquisition module is used to acquire disinfection equipment data and target area images within the monitoring period; the disinfection equipment data specifically includes the initial disinfection cycle and initial spray density of the disinfection equipment; the target area image is a grayscale image of the target area.

[0039] Specifically, this embodiment does not impose specific limitations on the duration of the monitoring period, which can be freely set by those skilled in the art, as long as the requirements for the duration of the monitoring period are met. In this embodiment, the duration of the monitoring period is 10 minutes. This embodiment also does not impose specific limitations on the method of acquiring data from the disinfection equipment, which can be freely set by those skilled in the art, as long as the requirements for acquiring data from the disinfection equipment are met. In this embodiment, the data is acquired through user interaction input. This embodiment captures multiple grayscale images by setting multiple cameras on the ceiling of the target area, and combines the multiple grayscale images into an image of the target area. It is worth noting that in this embodiment, the frequency of acquiring the target area image is periodic, based on the duration of the monitoring period.

[0040] Please continue reading. Figure 1 As shown, the system also includes a real-time data acquisition module, which is used to collect real-time target location data and target area environmental data; the target location data includes the target location coordinates and the number of targets, the targets being specifically small and medium-sized insects such as cockroaches; the target area environmental data includes environmental humidity data, environmental temperature data, and the activity frequency of the targets.

[0041] Specifically, this embodiment does not specifically limit the process of collecting the location data of the disinfection target. Those skilled in the art can set it freely, as long as the requirements for collecting the location data of the disinfection target are met. In this embodiment, the disinfection target is identified in the target area image by YOLOv5 technology, and the location coordinates of the disinfection target in the target area image are recorded. The activity frequency of the disinfection target is also statistically analyzed based on the recording results. In this embodiment, the environmental data of the target area is collected in real time by intelligent sensors to collect environmental humidity data and environmental temperature data.

[0042] Please continue reading. Figure 1 As shown, the system also includes a regional level analysis module, which is connected to the device number acquisition module. The regional level analysis module is used to divide the target area according to the target area image to obtain each disinfection area, and classify each disinfection area according to the number of stored items in each disinfection area, and construct a disinfection spraying index based on the classification results.

[0043] Please see Figure 2 As shown, the regional level analysis module includes a regional division unit, which is used to divide the target region according to the target region image;

[0044] The region division unit divides the target region image into minimum rectangles. The analysis process of the minimum rectangle is as follows: The region division unit projects the target region image onto a Cartesian coordinate system and calculates the minimum vertical line segment length Lx and the minimum horizontal line segment length Wx, setting Lx = min{L(y)} and Wx = min{W(x)}. The region division unit uses the rectangle formed by the minimum vertical line segment length Lx and the minimum horizontal line segment length Wx as the division unit to divide the target region image, obtaining each disinfection region D(i), where L(y) represents the length of the y-th vertical line segment, W(x) represents the length of the x-th horizontal line segment, and D(i) represents the ith disinfection region, i = 1, 2, 3... N, where N is the number of disinfection regions. By analyzing the length and width of the minimum rectangle of the target region image, the division unit is obtained, and the target region is divided to achieve accurate division of the disinfection region, thereby improving the accuracy of spraying management of each disinfection region in the target region.

[0045] Specifically, the "projection of the target area image onto a Cartesian coordinate system" described in this embodiment is as follows: a Cartesian coordinate system is established with the lower left vertex of the image as the origin, the positive direction of the horizontal coordinate from left to right, and the positive direction of the vertical coordinate from bottom to top, with pixels as the unit length.

[0046] Please continue reading. Figure 2 As shown, the regional level analysis module also includes a level division unit, which is connected to the regional division unit. The level division unit is used to calculate the storage density ρ(i) of each disinfection area based on the quantity of stored items in each disinfection area, and sets ρ(i) = N(i) / [Lx×Wx];

[0047] The grading unit classifies each disinfection area according to the storage density calculation results, and constructs a disinfection spraying index based on the grading results to quantify the disinfection difficulty of each disinfection area: if ρ(i) < N1, the grading unit classifies the disinfection area into level three and sets the disinfection spraying index to P1, where P1 = exp[ρ(i) - N1]; if N1 ≤ ρ(i) < N2, the grading unit classifies the disinfection area into level two and sets the index to P2, where P2 = 1; if ρ(i) ≥ N2, the level division unit divides the disinfection area into level one, and sets the disinfection spraying index to P3, which is set as P3 = ln{e + [ρ(i) - N2] / N2}; where N1 is the first preset storage density, N2 is the second preset storage density, N1 < N2, and e is the natural logarithm; by comparing and analyzing the storage quantity of each disinfection area, the disinfection difficulty level of each disinfection area is determined, and then the disinfection spraying index is set to quantify the difficulty, thus realizing the accurate judgment of the environmental anomaly and target density anomaly of each disinfection area.

[0048] Specifically, this embodiment does not impose specific limitations on the values ​​of the first preset storage density N1 and the second preset storage density N2. Those skilled in the art can set them freely, as long as the value requirements of the first preset storage density N1 and the second preset storage density N2 are met. In this embodiment, the first preset storage density N1 can be set to 2 units / square meter, and the second preset storage density N2 can be set to 5 units / square meter.

[0049] Please continue reading. Figure 1 As shown, the system also includes an environmental monitoring module, which is used to analyze the volatility anomalies of each disinfection area based on the environmental data of the target area and the disinfection spraying index within the monitoring period.

[0050] Please see Figure 3 As shown, the environmental monitoring module includes a temperature anomaly analysis unit, which compares the temperature t(i) of each disinfection area within the monitoring period with the preset evaporation temperature T, and analyzes the temperature anomaly of each disinfection area based on the comparison results to determine the impact of temperature on the efficacy of the sprayed pesticide, and constructs a temperature anomaly coefficient: if t(i) < T, the temperature anomaly analysis unit determines that the temperature of each disinfection area within the monitoring period is normal, and sets the temperature anomaly coefficient as WD1(i), with WD1(i) = 0; if t(i) ≥ T, the temperature anomaly analysis unit determines that the temperature of each disinfection area within the monitoring period is abnormal, and sets the temperature anomaly coefficient as WD2(i), with WD2(i) = [t(i) - T] / T; where t(i) is the temperature of the i-th disinfection area within the monitoring period; by judging the local temperature of each disinfection area, the temperature anomaly of each minimum spraying area is analyzed, and the situation of reduced effective pesticide quantity due to temperature is judged, thereby improving the accuracy of pesticide spraying management of each disinfection area in the target area.

[0051] Specifically, this embodiment does not impose specific limitations on the value of the preset evaporation temperature T. Those skilled in the art can set it freely, as long as the value requirement of the preset evaporation temperature T is met. In this embodiment, the preset evaporation temperature T is 30°C.

[0052] Please continue reading. Figure 3As shown, the environmental monitoring module also includes a humidity anomaly analysis unit, which compares the humidity s(i) of each disinfection area within the monitoring period with each preset evaporation humidity, analyzes the humidity anomaly of each disinfection area based on the comparison results, and constructs a humidity anomaly coefficient: if s(i) < S1 or s(i) ≥ S2, the humidity anomaly analysis unit determines that the humidity of the disinfection area is abnormal within the monitoring period, and sets the humidity anomaly coefficient to SD1(i), setting SD1(i) = |s(i) - [S1 + S2] / 2| / {[S1 + S2] / 2}; if S 1≤s(i)<S2, the humidity anomaly analysis unit determines that the humidity of the disinfection area is normal within the monitoring period, and sets the humidity anomaly coefficient to SD2(i), setting SD2(i)=0; where S1 is the first preset evaporation humidity, S2 is the second preset evaporation humidity, S1<S2; by comparing and judging the local humidity of each disinfection area, the effect of the medicine in each disinfection area is analyzed, and the situation of reduced effective medicine concentration or less attached medicine due to humidity is analyzed, thereby improving the accuracy of spraying management of each disinfection area in the target area.

[0053] Specifically, in this embodiment, the values ​​of the first preset evaporation humidity S1 and the second preset evaporation humidity S2 are determined according to the optimal humidity of the environment for spraying the medicine. Those skilled in the art can freely set the first preset evaporation humidity S1 and the second preset evaporation humidity S2 according to the optimal humidity of the environment for spraying the medicine, as long as the value requirements of the first preset evaporation humidity S1 and the second preset evaporation humidity S2 are met. In this embodiment, the first preset evaporation humidity S1 is set to 70% of the optimal humidity of the environment for spraying the medicine, and the second preset evaporation humidity S2 is set to 120% of the optimal humidity of the environment for spraying the medicine.

[0054] Specifically, the environmental monitoring module further includes a volatilization anomaly analysis unit, which is connected to the temperature anomaly analysis unit and the humidity anomaly analysis unit. The volatilization anomaly analysis unit analyzes the volatilization anomaly of each disinfection area based on the temperature anomaly analysis results, humidity anomaly analysis results, and the disinfection spraying index construction results within the monitoring period. If a1 × temperature anomaly coefficient + a2 × humidity anomaly coefficient < B × disinfection spraying index, the volatilization anomaly analysis unit determines that the volatilization of the disinfection area is normal within the monitoring period; if a1 × temperature anomaly coefficient + a2 × humidity anomaly coefficient ≥ B × disinfection spraying index, the volatilization anomaly analysis unit determines that the volatilization of the disinfection area is abnormal within the monitoring period. Here, B is a preset volatilization anomaly index, a1 is the temperature weight, a2 is the humidity weight, and a1 + a2 = 1. By comprehensively analyzing the volatilization anomaly of each disinfection area based on the two aspects that have the greatest impact on drug volatilization—temperature and humidity—the accuracy of the analysis of drug volatilization anomalies in each disinfection area is improved.

[0055] Specifically, this embodiment does not impose specific limitations on the value of the preset volatility anomaly index B. Those skilled in the art can set it freely, as long as the value requirement of the preset volatility anomaly index B is met. In this embodiment, the preset volatility anomaly index B is set to 0.5.

[0056] Please continue reading. Figure 1 As shown, the system also includes a pest control target analysis module, which is connected to the real-time data acquisition module and the regional level analysis module. The pest control target analysis module is used to analyze the target density anomalies in each pest control area based on the pest control target location data, and to adjust the analysis process of the target density anomalies in each pest control area according to the proportion of adult insects in the pest control target.

[0057] Please see Figure 4 As shown, the disinfection target analysis module includes a density anomaly analysis unit, which is used to calculate the target density ρm(i) of each disinfection area based on the disinfection target location data. ρm(i) is set to mn(i) / [Lx×Wx], where mn(i) is the number of disinfection targets in the i-th disinfection area.

[0058] The density anomaly analysis unit is used to compare ρm(i) with the preset target density P, and analyze the anomaly of the target density in each disinfection area based on the comparison result, so as to achieve accurate comparison and judgment of the density of the disinfection target in each disinfection area: if ρm(i) ≥ P × disinfection spraying index, the density anomaly analysis unit determines that the target density of the disinfection area is abnormal; if ρm(i) < P × disinfection spraying index, the density anomaly analysis unit determines that the target density of the disinfection area is normal; by judging the disinfection target density of each disinfection area within the monitoring period, it is determined whether the number of disinfection targets in each disinfection area has reached the disinfection standard, thereby improving the accuracy of spraying management of each disinfection area in the target area; it can be understood that the method of obtaining the number mn(i) of the disinfection target in the i-th disinfection area in this embodiment is to judge whether the positioning coordinates of the disinfection target belong to the i-th disinfection area, and count the number of positioning coordinates of the disinfection target belonging to the i-th disinfection area as mn(i).

[0059] Specifically, this embodiment does not impose specific limitations on the value of the preset target density P. Those skilled in the art can set it freely, as long as the value requirement of the preset target density P is met. For example, the preset target density P can be set to 4 units / square meter.

[0060] Please continue reading. Figure 4As shown, the pest control target analysis module also includes a pesticide resistance analysis unit, which is connected to the volatility anomaly analysis unit. The pesticide resistance analysis unit is used to analyze the pesticide resistance of the pest control targets in each pest control area based on the proportion μ(i) of adult insects in each pest control area, and to adjust the analysis process of target density anomalies based on the analysis results: if μ(i) < U, the pesticide resistance analysis unit determines that the pesticide resistance of the pest control area is normal and no adjustment is made; if μ(i) ≥ U, the pesticide resistance analysis unit determines that the pesticide resistance of the pest control area is abnormal and adjusts the preset target density to P(i), where P(i) = P × [μ(i) - U] / U; where U is the preset proportion of adult insects in the pest control target; by comparing the numerical values ​​of the proportion of adult insects in each pest control area, the influence of the proportion of adult insects on whether the normal application of pesticides in each pest control area can achieve the pest control target is analyzed, which improves the accuracy of the analysis of target density anomalies, and thus improves the accuracy of the spraying management of each pest control area in the target area.

[0061] Specifically, this embodiment does not impose specific limitations on the value of the preset target adult insect ratio U. Those skilled in the art can set it freely, as long as the value requirement of the preset target adult insect ratio U is met. In this embodiment, the preset target adult insect ratio U is set to 0.4.

[0062] Please continue reading. Figure 1 As shown, the system also includes a spraying management module, which is connected to the environmental monitoring module and the pest control target analysis module. The spraying management module is used to generate a spraying management plan for each pest control area based on the analysis results of volatilization anomalies and target density anomalies within the monitoring period.

[0063] If the target density in the disinfection area is normal, the spraying management module determines that the active disinfection target in the disinfection area is normal, sets the spraying cycle of the disinfection area to XT1(i), sets XT1(i) = XT0, sets the spraying amount of the disinfection area to PY1, and sets PY1(i) = PY0 × [Lx × Wx];

[0064] If the volatilization of the target area is abnormal and the target density of the disinfection area is abnormal, the spraying management module determines that the disinfection of the disinfection area is abnormal and sets the disinfection cycle of the disinfection area to XT2(i). XT2(i) is set to XT0×{1-[a1×temperature anomaly coefficient+a2×humidity anomaly coefficient-B×disinfection spraying index] / B×disinfection spraying index}. The spraying amount of the disinfection area is set to PY2(i). PY2(i) is set to PY0×[Lx×Wx]×exp[P×disinfection spraying index-ρm(i)].

[0065] If the evaporation in the target area is normal and the target density in the disinfection area is abnormal, the spraying management module determines that the active disinfection target in the disinfection area is abnormal, and sets the disinfection cycle of the disinfection area to XT3(i), setting XT3(i) = XT0, and sets the spraying amount of the disinfection area to PY3(i), setting PY3(i) = PY0 × exp[P × disinfection spraying index - ρm(i)];

[0066] Where XT0 is the initial disinfection cycle and PY0 is the initial spraying density;

[0067] The spraying management module is also used to output the disinfection cycle and spraying amount of each disinfection area as the spraying management plan for each disinfection area to the user; through comprehensive analysis of the environment and disinfection targets, it lists and judges the impact of various abnormal states on the spraying process of the disinfection equipment, and provides corresponding spraying plans, thereby improving the accuracy of spraying management of each disinfection area in the target area.

[0068] Specifically, this embodiment does not impose specific limitations on the values ​​of the initial disinfection cycle XT0 and the initial spray density PY0. Those skilled in the art can freely limit these values, as long as the value requirements of the initial disinfection cycle XT0 and the initial spray density PY0 are met. In this embodiment, the initial disinfection cycle XT0 and the initial spray density PY0 are obtained through user interaction input.

[0069] Please continue reading. Figure 1 As shown, the system also includes a pesticide efficacy monitoring module. The pesticide efficacy monitoring module is used to optimize the spraying management plan of each disinfection area based on the activity frequency v(i) of the disinfection targets in each disinfection area after the spraying cycle, so as to achieve continuous optimization of the disinfection equipment: if v(i) < V, the pesticide efficacy monitoring module determines that the activity frequency of the disinfection targets in the disinfection area is normal and no optimization is performed; if v(i) ≥ V, the pesticide efficacy monitoring module determines that the activity frequency of the disinfection targets in the disinfection area is abnormal, and optimizes the spraying amount of the disinfection area to PYd(i)', setting PYd(i)' = PYd(i) × exp{[v(i) - V] / V};

[0070] Wherein, V is the activity frequency of the preset disinfection target; by analyzing the spraying effect of the disinfection equipment, the spraying management plan for each disinfection area is optimized, thereby improving the accuracy of the analysis of the spraying management plan for each disinfection area, and thus improving the accuracy of the spraying management of each disinfection area in the target area.

[0071] Specifically, this embodiment does not impose any restrictions on the value of the activity frequency V of the preset disinfection target. Those skilled in the art can set it freely, as long as the value requirement of the activity frequency V of the preset disinfection target is met. In this embodiment, the value of the activity frequency V of the preset disinfection target is 0.1 times / minute.

[0072] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. A pest control equipment spraying management system based on machine learning, characterized in that, include: The equipment data acquisition module is used to acquire data from the disinfection equipment and images of the target area during the monitoring period; The real-time data acquisition module is used to collect real-time data on the location of the disinfection target and the environmental data of the target area; The regional level analysis module is used to divide the target area according to the target area image to obtain each disinfection area, and to classify each disinfection area according to the quantity of stored items in each disinfection area. It is also used to construct a disinfection spraying index based on the level classification results. The environmental monitoring module is used to analyze the volatility anomalies of each disinfection area based on the environmental data of the target area and the pesticide spraying index within the monitoring period; The disinfection target analysis module is used to analyze the anomalies in target density in each disinfection area based on the disinfection target location data and the disinfection spraying index; The spraying management module is used to generate spraying management plans for each disinfection area based on the analysis results of volatility anomalies and target density anomalies in each disinfection area. The efficacy monitoring module is used to optimize the spraying management plan for each disinfection area based on the activity frequency of the disinfection targets in each disinfection area after the spraying cycle. The regional level analysis module also includes a level division unit. The level division unit is used to calculate the storage density ρ(i) of each disinfection area based on the quantity of stored items in each disinfection area, and to classify each disinfection area according to ρ(i). Then, a disinfection spraying index is constructed based on the level division results: if ρ(i) < N1, the level division unit divides the disinfection area into three levels and sets the disinfection spraying index to P1; if N1 ≤ ρ(i) < N2, the level division unit divides the disinfection area into two levels and sets the disinfection spraying index to P2; if ρ(i) ≥ N2, the level division unit divides the disinfection area into one level and sets the disinfection spraying index to P3; where N1 is the first preset storage density, N2 is the second preset storage density, P1 = exp[ρ(i) - N1], P2 = 1, P3 = ln{e + [ρ(i) - N2] / N2}; The pest control target analysis module also includes a drug resistance analysis unit. The drug resistance analysis unit is used to analyze the drug resistance of the pest control targets in each pest control area based on the proportion μ(i) of adult pests in each pest control area. The drug resistance of the pest control targets in each pest control area includes normal and abnormal. When the drug resistance of the pest control area is abnormal, the preset target density is adjusted to P(i), and P(i) is set as P×[μ(i)-U] / U; where U is the preset proportion of adult pests in the pest control area, and P is the preset target density before adjustment. The spraying management module is used to generate spraying management plans for each disinfection area based on the analysis results of volatility anomalies and target density anomalies in each disinfection area during the monitoring period. If the target density in the disinfection area is normal, the spraying management module determines that the active disinfection target in the disinfection area is normal, sets the spraying cycle of the disinfection area to XT1(i), sets XT1(i)=XT0, sets the spraying amount of the disinfection area to PY1(i), sets PY1(i)=PY0×[Lx×Wx], where Lx is the minimum vertical line segment length and Wx is the minimum horizontal line segment length; If the volatilization of the target area is abnormal and the target density of the disinfection area is abnormal, the spraying management module determines that the disinfection of the disinfection area is abnormal and sets the disinfection cycle of the disinfection area to XT2(i). XT2(i) is set as XT0 × {1 - [a1 × temperature anomaly coefficient + a2 × humidity anomaly coefficient - B × disinfection spraying index] / B × disinfection spraying index}. The spraying amount of the disinfection area is set as PY2(i). PY2(i) is set as PY0 × [Lx × Wx] × exp[P × disinfection spraying index - ρm(i)]; where B is the preset volatilization anomaly index, a1 is the temperature weight, a2 is the humidity weight, and a1 + a2 = 1. If the evaporation in the target area is normal and the target density in the disinfection area is abnormal, the spraying management module determines that the active disinfection target in the disinfection area is abnormal, and sets the disinfection cycle of the disinfection area to XT3(i), setting XT3(i)=XT0, and sets the spraying amount of the disinfection area to PY3(i), setting PY3(i)=PY0×exp[P×disinfection spraying index-ρm(i)]; Where XT0 is the initial disinfection cycle, PY0 is the initial spray density, and ρm(i) is the target density of each disinfection area; The efficacy monitoring module is used to compare the activity frequency v(i) of the disinfection target in each disinfection area after the spraying cycle with the preset activity frequency V of the disinfection target to determine the abnormality of the activity frequency of the disinfection target in the disinfection area. The abnormality of the activity frequency of the disinfection target in the disinfection area includes normal and abnormal. When the activity frequency of the disinfection target in the disinfection area is abnormal, the spraying amount of the disinfection area is optimized to PYd(i)', which is set as PYd(i)=PYd(i)×exp{[v(i)-V] / V}, where d is a numerical subscript and d=1,2,3.

2. The pesticide spraying management system based on machine learning according to claim 1, characterized in that, The regional level analysis module includes a regional division unit, which is used to calculate the minimum vertical line segment length Lx and the minimum horizontal line segment length Wx; The region division unit uses the rectangle formed by the minimum vertical line segment length Lx and the minimum horizontal line segment length Wx as the division unit to divide the target region image to obtain each elimination region D(i).

3. The pesticide spraying management system based on machine learning according to claim 2, characterized in that, The environmental monitoring module includes a temperature anomaly analysis unit, which compares the temperature t(i) of each disinfection area within the monitoring period with the preset evaporation temperature T to determine the temperature anomaly of each disinfection area. The temperature anomaly of each disinfection area includes normal and abnormal. When the temperature of each disinfection area is normal, the temperature anomaly coefficient is set to WD1(i); when the temperature of each disinfection area is abnormal, the temperature anomaly coefficient is set to WD2(i). If t(i) < T, the temperature anomaly analysis unit determines that the temperature of each disinfection area within the monitoring period is normal and sets the temperature anomaly coefficient to WD1(i), setting WD1(i) = 0; if t(i) ≥ T, the temperature anomaly analysis unit determines that the temperature of each disinfection area within the monitoring period is abnormal and sets the temperature anomaly coefficient to WD2(i), setting WD2(i) = [t(i) - T] / T; where t(i) is the temperature of the i-th disinfection area within the monitoring period.

4. The pesticide spraying management system based on machine learning according to claim 3, characterized in that, The environmental monitoring module also includes a humidity anomaly analysis unit, which compares the humidity s(i) of each disinfection area within the monitoring period with each preset evaporation humidity to determine the humidity anomaly of each disinfection area. The humidity anomaly of each disinfection area includes normal and abnormal. When the humidity of a disinfection area is abnormal, the humidity anomaly coefficient is set to SD1(i); when the humidity of a disinfection area is normal, the humidity anomaly coefficient is set to SD2(i). If s(i) < S1 or s(i) ≥ S2, the humidity anomaly analysis unit determines... The humidity of the disinfection area is abnormal within a certain monitoring period, and the humidity abnormality coefficient is set as SD1(i), where SD1(i) = |s(i) - [S1 + S2] / 2| / {[S1 + S2] / 2}. If S1 ≤ s(i) < S2, the humidity abnormality analysis unit determines that the humidity of the disinfection area is normal within the monitoring period, and sets the humidity abnormality coefficient as SD2(i), where SD2(i) = 0. Here, S1 is the first preset evaporation humidity, S2 is the second preset evaporation humidity, and S1 < S2.

5. The pesticide spraying management system based on machine learning according to claim 4, characterized in that, The environmental monitoring module also includes a volatilization anomaly analysis unit. This unit analyzes the volatilization anomalies of each disinfection area based on the temperature anomaly analysis results, humidity anomaly analysis results, and disinfection spraying index construction results within the monitoring period. The analysis results of the volatilization anomalies of each disinfection area include normal and abnormal. If a1×temperature anomaly coefficient + a2×humidity anomaly coefficient < B×disinfection spraying index, the volatilization anomaly analysis unit determines that the volatilization of the disinfection area is normal within the monitoring period. If a1×temperature anomaly coefficient + a2×humidity anomaly coefficient ≥ B×disinfection spraying index, the volatilization anomaly analysis unit determines that the volatilization of the disinfection area is abnormal within the monitoring period.

6. The pesticide spraying management system based on machine learning according to claim 5, characterized in that, The disinfection target analysis module includes a density anomaly analysis unit. The density anomaly analysis unit is used to calculate the target density ρm(i) of each disinfection area based on the disinfection target location data, and compare ρm(i) with the preset target density P to determine the target density anomaly of each disinfection area. If ρm(i) ≥ P × disinfection spraying index, the density anomaly analysis unit determines that the target density of the disinfection area is abnormal; if ρm(i) < P × disinfection spraying index, the density anomaly analysis unit determines that the target density of the disinfection area is normal. ρm(i) is set to mn(i) / [Lx × Wx], where mn(i) is the number of disinfection targets in the i-th disinfection area.

Images