Field pest control method and system

Abstract

The embodiment of the invention provides a field pest control method and system. The method comprises the following steps: acquiring disease and insect pest image information at a preset sampling frequency in a preset time period through at least one image acquisition unit deployed in a field to obtain an image information sequence; the method comprises the following steps: acquiring field pest sound data through at least one movable sound monitoring unit to obtain a sound information sequence; and based on the image information sequence and the sound information sequence, determining management and control parameters of diseases and insect pests of the field. The system comprises an image acquisition unit, a sound monitoring unit and a data processing unit.

Description

Technical Field

[0001] This manual relates to the agricultural field, and in particular to a method and system for the control of pests and diseases in fields. Background Technology

[0002] In agricultural production, the monitoring and control of field pests and diseases typically rely on remote sensing, drone aerial photography, and surveillance to obtain images of field pests and diseases, and then further analyze these images by extracting features. However, these methods are easily affected by climate and adverse weather conditions, and are mainly used to monitor large areas of farmland; they may not be able to accurately identify and assess the development trend of pests and diseases in the field.

[0003] Pest and disease management in fields still faces some challenges. Because pests and diseases may behave differently in different geographical locations and growing environments, traditional monitoring methods are unable to provide accurate data for specific fields, thus affecting the early identification and effective control of pests and diseases.

[0004] Therefore, it is necessary to provide a better method for the management of field pests and diseases to overcome the limitations of existing technologies. Summary of the Invention This specification provides one or more embodiments of a method for controlling pests and diseases in farmland. The method includes: acquiring pest and disease image information at a preset sampling frequency within a preset time period using at least one image acquisition unit deployed in the field, obtaining an image information sequence; the number of image acquisition units is determined based on the number of plants in the field; the shooting accuracy of the image acquisition units is determined based on weather conditions; and the preset sampling frequency is related to the growth stage of the plants. Acquiring sound data of pests and diseases in the field using at least one mobile sound monitoring unit, obtaining a sound information sequence; the number of at least one mobile sound monitoring unit is determined based on the image information sequence. Based on the image information sequence and the sound information sequence, determining control parameters for pests and diseases in the field, the control parameters including at least the type of insecticide and / or pesticide, the single application amount, and the application frequency.

[0005] One or more embodiments of this specification provide a field pest and disease control system, including an image acquisition unit, a sound monitoring unit, and a data processing unit. The image acquisition unit is configured to acquire pest and disease image information at a preset sampling frequency within a preset time period to obtain an image information sequence. The number of image acquisition units is determined based on the number of plants in the field. The shooting accuracy of the image acquisition units is determined based on weather conditions. The preset sampling frequency is related to the growth stage of the plants. The sound monitoring unit is configured to acquire sound data of field pests and diseases to obtain a sound information sequence. The number of sound monitoring units is determined based on the image information sequence. The data processing unit is configured to determine control parameters for field pests and diseases based on the image information sequence and the sound information sequence. The control parameters include at least the type of insecticide and / or pesticide, the amount applied at one time, and the application frequency.

[0006] This specification provides one or more embodiments of a field pest and disease control device, including a processor, which is used to execute the above-described field pest and disease control method.

[0007] This specification provides one or more embodiments of a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes the above-described method for controlling field pests and diseases. Attached Figure Description

[0008] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0009] Figure 1 These are schematic diagrams illustrating application scenarios of a field pest and disease control system based on some embodiments of this specification;

[0010] Figure 2 This is an exemplary flowchart of a field pest and disease control method according to some embodiments of this specification;

[0011] Figure 3 This is an exemplary flowchart illustrating the determination of the number of sound monitoring units in a field pest and disease control method according to some embodiments of this specification;

[0012] Figure 4 This is an exemplary flowchart illustrating a specific method for determining the number of sound monitoring units according to some embodiments of this specification;

[0013] Figure 5 This is an exemplary flowchart illustrating the determination of pest and disease control parameters according to some embodiments of this specification;

[0014] Figure 6This is an exemplary flowchart illustrating a specific method for determining pest and disease control parameters according to some embodiments of this specification;

[0015] Figure 7 This is a schematic diagram of the structure of a field pest and disease control system according to some embodiments of this specification. Detailed Implementation

[0016] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0017] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0018] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0019] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0020] Figure 1 This is a schematic diagram illustrating the application scenarios of a field pest and disease control system according to some embodiments of this specification.

[0021] In some embodiments, the field pest and disease control system 100 may include an image acquisition unit 110, a sound monitoring unit 120, a data processing unit 130, and a communication device 140.

[0022] The image acquisition unit 110 is configured to acquire images of field pests and diseases and generate an image information sequence. The image acquisition unit 110 can transmit the acquired image information sequence to the data processing unit 130 via the communication device 140.

[0023] The sound monitoring unit 120 is configured to acquire sound data related to field pests and diseases, convert it into digital signals, and generate a sound information sequence. It may include a high-sensitivity microphone that converts sound signals into electrical signals; the microphone can sense sound fluctuations in the environment and convert them into corresponding voltage signals. It may include preprocessing circuitry for enhancing and filtering the sound signals acquired from the microphone; an analog-to-digital converter to convert analog sound signals into digital signals for subsequent digital signal processing; and control circuitry and interfaces, a power management module, etc. The sound monitoring unit 120 can transmit the acquired sound information sequence to the data processing unit 130 via a communication device 140.

[0024] The data processing unit 130 is configured to determine control parameters for field pests and diseases based on image and sound information sequences. The data processing unit 130 may include a central processing unit, data storage, bus, input and output interfaces, data processing and analysis software, and graphic display devices, etc., for receiving, processing, and analyzing data from the image acquisition unit 110 and the sound monitoring unit 120, and determining control parameters such as the type of pest control organism and / or pesticide, the single application rate, and the application frequency based on the analysis results.

[0025] The communication device 140 is configured to enable data transmission and communication between various units and devices within the field pest and disease control system 100, as well as data interaction with external devices or networks.

[0026] It should be understood that Figure 1 The field pest and disease control system 100 and its components shown can be implemented in various ways. For example, in some embodiments, the image acquisition unit 110 and the sound monitoring unit 120 can be integrated into the same device. In some embodiments, data communication between the communication device 140 and the various units can be implemented via wired means or wireless means (including but not limited to Wi-Fi, Bluetooth, NFC, cellular networks and / or wireless sensor networks, etc.).

[0027] It should be noted that the above description of the field pest and disease control system 100 and its components is for convenience only and should not be construed as limiting this specification to the scope of the embodiments described. It is understood that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the various modules or construct subsystems connected to other modules without departing from these principles. In some embodiments, Figure 1The image acquisition unit 110, sound monitoring unit 120, data processing unit 130, and communication device 140 disclosed herein can be different components of a system, or a single module that implements the functions of two or more of the aforementioned components. For example, the components can share a single storage module, or each component can have its own separate storage module. Such variations are all within the scope of protection of this specification.

[0028] Figure 2 This is an exemplary flowchart illustrating a field pest and disease control method according to some embodiments of this specification. In some embodiments, process 200 may be executed by a field pest and disease control system 100. Figure 2 As shown, process 200 includes the following steps.

[0029] Step 210: Acquire pest and disease image information to obtain an image information sequence. In some embodiments, step 210 may be performed by the image acquisition unit 110.

[0030] In some embodiments, the field pest and disease control system 100 can acquire pest and disease image information at a preset sampling frequency within a preset time period by at least one image acquisition unit deployed in the field, thereby obtaining an image information sequence.

[0031] The image information sequence refers to a series of pest and disease-related image data acquired by the image acquisition unit 110 within a preset time period and at a preset sampling frequency. This image data can be used to analyze and monitor the health status of plants in the field, the occurrence and spread of pests and diseases, etc.

[0032] For example, suppose five image acquisition units are deployed in a field, and each unit collects image information at a sampling frequency of once per hour per day. Then, within a preset time period (such as one week), a total of five image sequences will be obtained. Each image sequence contains a series of consecutive image frames acquired at a preset sampling frequency. These image frames can be used to observe information such as plant growth status, leaf color changes, and the appearance of lesions or insect damage.

[0033] In some embodiments, the number of image acquisition units is determined based on the number of plants in the field. For example, a standard configuration of one image acquisition unit per 200 plants can be used to ensure that every plant is monitored.

[0034] In some embodiments, the shooting accuracy of the image acquisition unit is determined based on weather conditions. For example, on cloudy days, when the lighting is poor, it is necessary to appropriately increase the shooting accuracy to obtain higher resolution images of pests and diseases.

[0035] In some embodiments, the preset sampling frequency is related to the growth stage of the plant. The impact of growth and development quality on the final yield and quality varies at different stages of plant growth and development. Based on this impact, different preset sampling frequencies can be manually set for each growth and development stage. Generally, the period of vigorous plant growth is also a period of relatively severe pest and disease outbreaks. During periods of rapid pest and disease development or severe disease outbreaks, the preset sampling frequency should be set relatively high (e.g., collecting pest and disease images 2-3 times per hour) to promptly capture changes and developments in pests and diseases.

[0036] Step 220: Acquire sound data of field pests and diseases to obtain a sound information sequence. In some embodiments, step 220 may be performed by the sound monitoring unit 120.

[0037] In some embodiments, the field pest and disease control system 100 can acquire field pest and disease sound data through at least one movable sound monitoring unit 120 to obtain a sound information sequence; the number of at least one movable sound monitoring unit 120 is determined based on the image information sequence.

[0038] The portable sound monitoring unit 120 offers flexibility in its placement within the field. It can be deployed in areas where pest and disease problems occur or where pest and disease infestations are severe.

[0039] The image information sequence can intuitively reflect the pest and disease problem, so the location of the sound monitoring unit 120 can be determined based on the image information sequence.

[0040] The sound information sequence is a series of sound data related to pests and diseases collected by the sound monitoring unit 120 at a preset sampling frequency over a certain period of time. This sound data can be used to analyze and monitor the sound characteristics, activity patterns, and trends of pests and diseases.

[0041] For example, the sound information sequence may include aphid sound information sequence. Aphids are one of the common pests in farmland. Aphid sound information sequence may include the sound of aphids vibrating their antennae, the sound of their mouthparts inserting into plant tissue, and the sound of aphids rubbing together. These sounds can be recorded by the sound monitoring unit 120 and form a series of sound information sequences.

[0042] For example, sound information sequences can include sound information sequences of plants infected by pathogens. When some pathogens infect plants, plant tissues may produce specific sound responses. For instance, when leaf mold infects a leaf, the leaf may produce a trembling sound or other abnormal sounds. These sounds can be collected and formed into a series of sound information sequences.

[0043] Step 230: Determine the control parameters for field pests and diseases. In some embodiments, step 230 can be performed by the control parameter generation module 132 in the data processing unit 120. More information about the control parameter generation module 132 can be found in [link to relevant documentation]. Figure 7 And related explanations.

[0044] In some embodiments, the control parameter generation module 132 can determine control parameters for pests and diseases in the field based on image information sequences and sound information sequences.

[0045] Control parameters refer to quantifiable indicators or variables used for monitoring, evaluation, and adjustment during pest and disease management and control. These parameters are typically related to the occurrence, spread, and impact of pests and diseases, and are used to guide and optimize pest and disease management strategies and control measures. In some embodiments, a set of control parameters includes at least the type of insecticide and / or pesticide, the single application rate, and the application frequency. For example, in controlling aphids, a set of control parameters includes at least: one or more of carbamates, organophosphates, or synthetic carbamates; 200 grams of pesticide per acre of farmland according to the pesticide label instructions; and spraying every 7 to 10 days based on aphid population monitoring, etc.

[0046] For specific methods on determining control parameters, see [link to relevant documentation]. Figure 5 Related descriptions.

[0047] In the monitoring and identification of pests and diseases, the analysis of image and sound information sequences can accurately determine the type, severity, and distribution of pests and diseases. It can also quantitatively assess their density and distribution, and reveal their activity patterns and trends. This helps in determining appropriate pest and disease control parameters for field applications based on the analysis results.

[0048] The methods provided in some embodiments of this specification allow for different management and control measures in different areas, with varying control parameters. For example, the application of biological and / or chemical pesticides to different areas can be tailored to the type, development trend, and severity of pests and diseases, employing different methods such as pesticides, fertilizers, organic fertilizers, or biological pesticides (e.g., frogs). Furthermore, the application rate and frequency can vary across different areas; for areas less severely affected by pests and diseases, the application frequency can be appropriately reduced. This differentiated management of pesticide application in different areas avoids overuse and waste, helps maintain biodiversity, and enables real-time monitoring and precise control of pests and diseases.

[0049] It should be noted that the above description of methods for controlling field pests and diseases is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to the methods for controlling field pests and diseases under the guidance of this specification. However, these modifications and changes are still within the scope of this specification. For example, high-definition video of crops in the field can be recorded at the location where pests and diseases occur, and image and audio information sequences can be obtained from the video.

[0050] Figure 3 This is an exemplary flowchart illustrating the determination of the number of sound monitoring units in a field pest and disease control method according to some embodiments of this specification. In some embodiments, process 300 may be executed by the image information processing module 131 in the data processing unit 130. More information about the image information processing module 131 can be found in [link to relevant documentation]. Figure 7 and related explanations. For example... Figure 3 As shown, process 300 includes the following steps.

[0051] Step 310: Determine the image features of the field. In some embodiments, the image information processing module 131 may determine the image features of the field based on an image information sequence.

[0052] Field image features refer to quantifiable features extracted from field images during image processing and analysis to describe the characteristics and attributes of the fields. These features can include information such as shape, color, texture, and edges, and are used for the classification, identification, and analysis of fields.

[0053] For example, shape features of field images can include area, perimeter, and aspect ratio; color features can include average color, hue histogram, saturation, and brightness; texture features can include gray-level co-occurrence matrix, texture orientation histogram, and global texture features; and edge features can include edge intensity, edge density, and edge histogram.

[0054] Determining the image features of farmland based on image information sequences requires image processing and analysis of each image to extract relevant feature information. Image preprocessing first includes noise removal, correction of geometric distortion, and contrast adjustment to ensure image quality and consistency. Then, image segmentation techniques such as thresholding, edge detection, and region growing can be used to extract the farmland regions from the entire image. The segmented farmland regions can be binarized mask images. Finally, different methods (such as scale-invariant feature transformation, color space conversion, Gabor filters, and / or Sobel operators) can be used on the segmented images to extract shape, color, texture, and edge features.

[0055] Step 320: Determine the number of sound monitoring units. In some embodiments, the image information processing module 131 may determine the number of sound monitoring units based on image features of the field.

[0056] In some embodiments, the image information processing module 131 can determine the number of sound monitoring units by comparing preset image features of a field under normal conditions with actual image features of the same field. For example, image features of the same field and the same crop under normal conditions in the past can be retrieved as preset image features of the field.

[0057] The actual image features of the field and the preset image features of the same field can be vectorized, and the distance d1 between the vectors can be calculated (including but not limited to Euclidean distance, Manhattan distance, and / or cosine similarity). If d1 is greater than a first preset threshold, the field may be susceptible to pests or diseases; otherwise, the field is in normal condition. The first preset threshold can be set manually or automatically based on historical experience.

[0058] For fields in normal condition, a mobile sound monitoring unit can be set up. For fields potentially susceptible to pests and diseases, the number of sound monitoring units for that field can be determined based on the vector distance (d1) between the actual image features of the current field and preset image features, using a preset correspondence. The preset correspondence is defined as "the correspondence between the vector distance between the actual image features of the current field and preset image features and the number of sound monitoring units for the field," and both are positively correlated.

[0059] Figure 4 This is an exemplary flowchart illustrating a specific method for determining the number of sound monitoring units according to some embodiments of this specification. Figure 4 As shown, process 400 includes the following steps. In some embodiments, process 400 may be executed by data processing unit 130.

[0060] Step 410: Establish a field pest and disease image database. In some embodiments, the data processing unit 130 can establish a field pest and disease image database, recording historical feature images of fields affected by various pests and diseases and the features corresponding to those historical feature images.

[0061] The field pest and disease image database records characteristic images and corresponding image features of fields historically affected by various pests and diseases, such as images of rice affected by rice planthoppers and images of grape leaves affected by red spider mites, as well as the characteristics after the infestation.

[0062] Step 420: Determine the current pest and disease characteristics and reliability of the field. In some embodiments, the data processing unit 130 may determine the current pest and disease characteristics and reliability of the field based on the degree of difference between the image features of the field and the image features in the field pest and disease image database.

[0063] Pest and disease characteristics include the type and intensity of the pests and diseases (e.g., the estimated number of pests).

[0064] To determine the characteristics of pests and diseases, we can first extract actual image features from the actual images (this can be achieved using existing technologies such as image recognition). Then, we vectorize and normalize the two sets of features (the actual image features of the field; and the historical image features of the same field recorded in the field pest and disease image database). Next, we calculate the distance d2 between the normalized vectors (d1 reflects the difference between the two sets of image features). If d2 is less than a second preset threshold (for example, the distance d2 between the actual image features of the field and the historical image features of "grape leaves infested by spider mites" is less than the second preset threshold), the field is matched with the corresponding pest and disease species, thus determining the current pest and disease characteristics. The second preset threshold can be set manually or automatically based on historical experience.

[0065] For the current actual types of pests and diseases, we can first calculate and select the historical feature image (called the "target feature image") that has the smallest distance d2 between the actual image features and the historical image features contained in the field pest and disease image database. Then, the types of pests and diseases contained in the target feature image are taken as the current actual types of pests and diseases.

[0066] The current actual intensity of pests and diseases can be determined through the following steps.

[0067] Image features include one or more sub-feature indicators (e.g., color, morphology). The first step is to calculate the proportion of each sub-feature indicator in the actual image, denoted as [p]. 11 ,p 12 ,…,p 1m ], where m represents the number of sub-feature indicators; for one or more sub-feature indicators, the overall proportion P1 is calculated based on the preset weights.

[0068] The second step is to calculate the proportion of each sub-feature index in the actual image for the target feature image, denoted as [p]. 21 ,p 22 ,…,p 2m For one or more sub-feature indicators, calculate the overall proportion P2 based on preset weights.

[0069] The third step is to estimate the current actual pest and disease intensity N1 using the following formula:

[0070] N1=P1 / P2×N2 (1)

[0071] Where N2 represents the pest and disease intensity of the target feature image.

[0072] Taking spider mite infestation as an example, we can select red dot areas (or brown lesions, etc.) on the leaves as the infested area. Then, we calculate the proportion of red dots (or brown lesions, etc.) in that area relative to the entire leaf area to obtain the color feature percentage in the actual image, for example, 80%. In the target feature image in the database that best matches the actual image of the field, the color feature percentage of the image infested with spider mites is 20%. The database indicates that there are 15 actual spider mites in that image. Therefore, we can estimate the number of spider mites in the actual image to be: 15 / 20% × 80% = 60.

[0073] Reliability characterizes the reliability of current pest and disease characteristics.

[0074] Regarding the determination of the reliability of pest and disease data, conf represents the current reliability of the pest and disease data. It is related to the degree of difference in normalized image features d2, and also to the combined proportion P of one or more features. The reliability can be determined based on the following formula:

[0075] conf=w1×(1-d2)+w2×P (2)

[0076] Here, w1 and w2 are the weighting coefficients for the degree of difference and the combined proportion of one or more features, respectively, and w1 and w2 can be obtained by presetting.

[0077] Step 430: Determine the number of sound monitoring units. In some embodiments, the data processing unit 130 may determine the number of sound monitoring units based on the types of pests and diseases in the field and their reliability.

[0078] The data processing unit 130 can classify pests and diseases based on the degree of damage, and obtain the damage level of the pests and diseases, such as high, medium and low.

[0079] In some embodiments, the data processing unit 130 can determine the number of movable sound monitoring units based on the hazard level and reliability of pest characteristics, using a preset correspondence. The preset correspondence is between the hazard level and reliability of pest types and the number of movable sound monitoring units, and can be manually preset in advance based on demand. The number of movable sound monitoring units is positively correlated with both the hazard level and reliability of pest types.

[0080] The method of determining the number of sound monitoring units based on field image features provides a comprehensive and accurate means for the detection and monitoring of pests and diseases.

[0081] In some embodiments, the number of movable sound monitoring units is also positively correlated with the current crop density in the field, which is determined based on a sequence of image information.

[0082] Crop density refers to the number of plants grown per unit area of ​​farmland. Excessive crop density can obstruct sound propagation and create more interference. Therefore, the higher the crop density, the more sound monitoring units need to be deployed.

[0083] In some embodiments, the data processing unit 130 can identify and calculate the area of ​​blank regions in the actual image based on existing technologies such as image recognition, and then calculate the crop density. For example, the crop density can be calculated based on the following formula:

[0084]

[0085] Where ρ is the crop density, S is the total area of ​​the actual image, and S b This represents the area of ​​the blank region.

[0086] The data processing unit 130 can also determine crop density by other means (such as obtaining the number of seeds per unit area).

[0087] By linking the number of mobile sound monitoring units to the crop density in the field and determining the crop density based on image information sequences, the number of mobile sound monitoring units can be automatically set, improving the accuracy of pest and disease detection.

[0088] In summary, by determining the image features of the field based on image information sequences and then determining the number of sound monitoring units based on these features, precise control of field pests and diseases can be achieved, thereby improving the efficiency of pest and disease control.

[0089] Figure 5 This is an exemplary flowchart illustrating the determination of pest and disease control parameters according to some embodiments of this specification. Figure 5 As shown, process 500 includes the following steps. In some embodiments, process 500 may be executed by the control parameter generation module 132 in the data processing unit 130. More information about the control parameter generation module 132 can be found in [link to relevant documentation]. Figure 7 And related explanations.

[0090] Step 510: Estimate the amount of original pest control organisms remaining in the field. In some embodiments, the control parameter generation module 132 can estimate the amount of original pest control organisms remaining in the field based on image information sequences and sound information sequences.

[0091] Primitive pest control organisms refer to organisms that naturally exist in farmland and have a natural enemy or antagonistic effect on pests in crops. These can be insects, mites, spiders, parasitic nematodes, and other organisms that prey on, parasitize, or compete with pests.

[0092] In some embodiments, the control parameter generation module 132 can observe changes in the ecological environment and biological species in the field by analyzing image information sequences. For example, through image detection and recognition algorithms, the presence of different types of insects, mites, spiders, and other primitive pest control organisms can be identified. Using image processing technology, their numbers, distribution, and activity can be analyzed and predicted.

[0093] Sound sequences can provide additional clues about biological activity in fields. For example, certain primitive pests, such as spiders and bees, emit specific sounds for hunting or communication with other individuals. By analyzing sound sequences, these specific sound patterns can be detected and identified, thereby inferring the presence and activity of these primitive pests.

[0094] In some embodiments, the control parameter generation module 132 can extract multiple dimensions of sound features collected by each sound monitoring unit based on the sound information sequence; and estimate the amount of original pest control organisms remaining in the field based on the image information sequence and the multiple dimensions of sound features collected by each sound monitoring unit.

[0095] In some embodiments, the control parameter generation module 132 can extract feature parameters from various dimensions of the original insecticidal biological sound data, including time domain, frequency domain, and spatial domain. Examples include insect chirping, wing-flying sounds, and gnawing sounds monitored by different sound monitoring units.

[0096] Temporal features refer to the characteristics of a sound signal's changes along the time axis. These features can include the sound signal's amplitude, energy, waveform, duration, and period. There are various temporal feature extraction algorithms, such as peak detection, average value, short-time energy, and zero-crossing rate methods.

[0097] Frequency domain features refer to the variation characteristics of a sound signal along the frequency axis. Frequency domain features can include the sound signal's spectrum, harmonics, frequency, energy, etc. Frequency domain feature extraction algorithms include methods such as Fast Fourier Transform, Wavelet Transform, and spectral analysis.

[0098] Spatial characteristics refer to the spatial variation of sound signals. Spatial characteristics can include the location and distance of the sound source of insect pest sounds. For example, sound monitoring units are located at the four corners of a field, and the sound source is located in the middle of the field. First, the sound propagation distance is calculated using the location of the sound monitoring units and the sound propagation time. Then, using multiple sound propagation distances, the sound source location is determined. That is, the time when the sound is detected by the first sound monitoring unit is t1, ..., the time when the sound is detected by the fourth sound monitoring unit is t4. Based on the sound propagation time and speed, the sound propagation distances l1 to l4 can be calculated. Based on l1 to l4 and the location of the sound monitoring units, the sound source location can be determined.

[0099] Features extracted from multiple dimensions such as time domain, frequency domain, and spatial domain can be fused to obtain a comprehensive feature vector. For example, time domain features, frequency domain features, and spatial domain features can be weighted and averaged, and the weights can be preset.

[0100] After obtaining the comprehensive sound features, a target feature vector can be constructed based on the image features and comprehensive sound features obtained from the field image information sequence. Based on the target feature vector, a reference vector that meets preset requirements is obtained by matching it in the pest control biological feature database. The preset requirement can be minimizing the vector distance to the target feature vector. The pest control biological feature database includes multiple sets of reference vectors and their corresponding pest species and survival rates. The reference vectors are constructed based on historical image features and historical comprehensive sound features.

[0101] The insect species corresponding to the reference vector are taken as the current actual insect species to be controlled. For one or more feature indicators in the target feature vector, calculate the overall proportion P3 based on preset weights; for one or more feature indicators in the reference vector, calculate the overall proportion P4 based on preset weights; use the following formula to estimate the current actual insect species remaining N4:

[0102] N4 = P4 / P3 × N3 (4)

[0103] Where N3 represents the number of insecticidal organisms remaining in the reference vector database.

[0104] Using image and sound information sequences to estimate the amount of primordial pests remaining in the field can combine multi-source information to more comprehensively and accurately estimate the amount of primordial pests remaining in the field, laying a solid foundation for precise control of pest and disease management costs.

[0105] Step 520: Predict future pest and disease characteristics of the field. In some embodiments, the control parameter generation module 132 can predict the future pest and disease characteristics of the field based on the amount of original pest control organisms remaining in the field.

[0106] Future pest and disease characteristics refer to the specific properties or manifestations of pest and disease problems that may appear or worsen in the future. Examples include pesticide resistance, newly emerging pest and disease species, adaptive changes in pathogens or pests, the frequency and / or severity of pest and disease increases, and other difficult-to-control pest and disease characteristics. For instance, a pathogen may develop resistance to a specific pesticide, leading to a weakening or ineffectiveness of traditional pesticides in controlling that pathogen. Another example is new insect species exhibiting a higher feeding preference for certain crops, resulting in new pest and disease problems, and so on.

[0107] In some embodiments, future pest and disease characteristics include at least one type and intensity of pest and disease at a future point in time (e.g., expressed as an estimated number of pests). For example, at 13:15:00 on the 15th of next month, it is estimated that 12 types of pests will appear in the field, with a quantity of 30 to 40 of each or all of them.

[0108] There is a correlation between the retention of primary pest control organisms and the future pest and disease characteristics of the field. When the retention of primary pest control organisms is high, pests and diseases can be better controlled; conversely, if the retention of primary pest control organisms is low, future pest and disease problems may be exacerbated.

[0109] In some embodiments, the control parameter generation module 132 can divide the field into multiple regions and construct a field region map.

[0110] A field area map is a data structure consisting of nodes and edges, which can include multiple nodes and multiple edges connecting multiple nodes.

[0111] Nodes in a field area map refer to multiple regions formed after the field is divided. Node characteristics include: area; image features; sound features (derived from image information sequences and sound monitoring sequences); and the species and abundance of the original pests. For a detailed explanation of each node's specific characteristics, please refer to the preceding description.

[0112] The edges in a field area map refer to the edges between adjacent nodes. The characteristics of the edges include the density of crops planted at the boundary between adjacent nodes. The denser the crops at the boundary, the more frequently pests move back and forth between the two field areas.

[0113] In some embodiments, the control parameter generation module 132 can predict the future pest and disease characteristics of the field based on the field area map and the pest and disease prediction model.

[0114] In some embodiments, the pest and disease prediction model can be a graph neural network model, whose input is a field area map and whose output is the future pest and disease characteristics of each node.

[0115] The pest and disease prediction model can be trained using a large number of first training samples with first training labels. The first training samples are historical field area maps, and the first training labels are the actual results of historical pest and disease characteristics at different nodes in the historical field area maps.

[0116] In some embodiments of this specification, by constructing field area maps and using pest and disease prediction models to predict pest and disease characteristics, the spatial relationships and topological structures between fields can be better considered, thereby improving the accuracy and precision of pest and disease characteristic prediction.

[0117] In some embodiments, the node characteristics of nodes in the field area map also include seasonal climate and temperature. Seasonal climate and temperature characteristics can be obtained through weather stations, weather sensors, weather data sources, weather forecasts, and statistical analysis based on historical weather data and field geographical location information.

[0118] Using seasonal climate and temperature as node characteristics in field area maps allows for a more comprehensive consideration of the impact of environmental factors on pests and diseases, which helps to better formulate pest and disease control strategies and implement corresponding management measures under different seasons and climatic conditions.

[0119] In other embodiments, the node features of a node in the field area map also include the current pest and disease characteristics and reliability of the current node. For methods of obtaining the current pest and disease characteristics and reliability of the current node, please refer to [link to documentation / reference]. Figure 4 Description of step 420.

[0120] By using the current pest and disease characteristics and reliability of the current node as the node characteristics of the field area map, real-time monitoring and feedback of pests and diseases can be achieved, and the credibility assessment of the prediction results can be provided, further improving the accuracy of pest and disease prediction.

[0121] Step 530: Determine the control parameters for pests and diseases in the field. In some embodiments, the control parameter generation module 132 can determine the control parameters for pests and diseases in the field based on the future pest and disease characteristics of the field.

[0122] Figure 6 This is an exemplary flowchart illustrating a specific method for determining pest and disease control parameters according to some embodiments of this specification. Figure 6 As shown, process 600 includes the following steps. In some embodiments, process 600 may be executed by data processing unit 130.

[0123] Step 610: Generate several sets of candidate control parameters. In some embodiments, the data processing unit 130 may generate several sets of candidate control parameters for at least one area of ​​the field.

[0124] Candidate control parameters can be generated based on historical control parameters for the region. First, multiple sets of historical control parameters within a historical time period are obtained, and their average value is calculated as the historical control parameter average. Using the historical control parameter average as a benchmark, and with the control parameter fluctuation threshold as the positive and negative range of change, multiple sets of control parameters are randomly generated as candidate control parameters for the region. The control parameter fluctuation threshold can be set manually or automatically based on historical experience. For detailed explanations of control parameters, please refer to the previous sections. Figure 2 The description of step 230 is as follows. Step 620: Predict the pest and disease elimination effect. In some embodiments, the data processing unit 130 can predict the pest and disease elimination effect after controlling a preset time length based on each set of candidate control parameters.

[0125] The pest and disease control effect refers to the degree to which the control measures taken reduce or eliminate pests and diseases after a preset time period. The data processing unit 130 can evaluate the pest and disease control effect by comparing the pest and disease occurrence at the end of the preset time with the initial pest and disease situation.

[0126] In some embodiments, the pest and disease control effect can be expressed as the rate of decrease in the number of pests. The rate of decrease can be calculated using the following formula:

[0127]

[0128] Where, p d n is the rate of decline. p1 n represents the number of pests before control measures were implemented. p2 The number of pests after a predetermined timeframe for implementing control measures. For example, if the number of planthoppers decreases from 40 to 10, the decrease rate is (40-10) / 40×100%, which is a decrease rate of 75%.

[0129] In some embodiments, the data processing unit 130 can predict the pest and disease elimination effect through an effect prediction model.

[0130] The effect prediction model can be a neural network model. The input is the future pest and disease characteristics of different regions, each set of candidate control parameters, and the preset time length. The output is the pest and disease elimination effect (e.g., the pest and disease reduction rate) of the target region after the preset time length, where the target region is the field area where the pest and disease elimination effect is desired.

[0131] The effectiveness prediction model can be trained using a large number of second training samples with secondary training labels. The second training samples consist of historical control parameters from historically effective control periods, the duration of control measures during those periods, and future pest and disease characteristics in different regions based on those historically effective control periods. Here, an effective control period refers to a control experience period that reduces pests and diseases while minimizing impact on the ecological environment and crops. The second training label is the historical actual pest and disease reduction rate corresponding to the second training sample.

[0132] In some embodiments, the output of the pest and disease prediction model (future pest and disease characteristics) can be used as the input of the effect prediction model, and the effect prediction model and the pest and disease prediction model can be jointly trained together.

[0133] In some embodiments, the samples for joint training include historical control parameters, historical control duration, and field area maps based on historical control periods from selected historical effective control periods. The field area maps based on historical control period data are input into the pest and disease prediction model to obtain the future pest and disease characteristics output by the model based on historical control periods. These future pest and disease characteristics are then used as training samples, along with the selected historical control parameters and historical control duration from the selected historical effective control periods, and input into the effect prediction model to obtain the pest and disease reduction rate output by the effect prediction model. A loss function is constructed based on the actual pest and disease reduction rate of the historical control period and the pest and disease reduction rate output by the effect prediction model. The parameters of both the pest and disease prediction model and the effect prediction model are updated synchronously. By continuously updating the parameters, the trained pest and disease prediction model and the effect prediction model are obtained.

[0134] In some embodiments, the inputs to the effect prediction model also include the current pest and disease characteristics and reliability in the field, and the remaining amount of the original pest control organisms in the field. For methods of obtaining the current pest and disease characteristics and reliability, and the remaining amount of the original pest control organisms in the field, see [link to relevant documentation]. Figure 4 Step 420 and Figure 5 The description of step 510 in the text.

[0135] Step 630: Determine the control parameters for pests and diseases in the area. In some embodiments, the data processing unit 130 may determine the control parameters for pests and diseases in the area based on the pest and disease elimination effect corresponding to each set of candidate control parameters and the control cost corresponding to each set of candidate control parameters.

[0136] Control costs refer to the total cost of implementing specific pest and disease control measures, including labor costs, biological costs, and chemical costs. Labor costs can be determined based on the wages of personnel for a predetermined number of hours; biological costs can be calculated using the following formula:

[0137]

[0138] Among them, C b Let n be the biological cost, n be the number of biological species, and c be the biological cost. bi Let q be the unit price of the i-th organism. bi Let be the quantity of the i-th type of organism. The unit price of each organism can be obtained in advance.

[0139] Chemical costs can be calculated using the following formula:

[0140]

[0141] Among them, C h Let m be the chemical cost, t be the type of chemical, and f be the preset time duration. j Let q be the frequency of application of the j-th chemical drug. hj c represents the single dosage of the j-th chemical drug. hj Let be the unit price of the j-th chemical. The unit price of each chemical can be obtained in advance.

[0142] Provided that the predicted pest and disease elimination effect (the rate of pest and disease reduction) meets the requirements (the rate of reduction is greater than the third preset threshold), the control parameter with the lowest control cost can be selected as the final pest and disease control parameter. The third preset threshold can be set manually or automatically.

[0143] The methods for determining pest and disease control parameters provided in some embodiments of this specification can accurately predict the remaining amount of the original pest control organisms, thereby predicting future pest and disease characteristics in the field and laying a solid foundation for ultimately determining the most effective pest and disease control parameters. This helps to understand the development trend of pests and diseases in advance, minimize control costs, reduce crop losses, and promote the sustainable development of agricultural production.

[0144] In some embodiments, the field pest and disease control system includes an image acquisition unit. For an introduction to the image acquisition unit, please refer to [link to relevant documentation]. Figure 2 A detailed description of step 210 in process 200 is shown below.

[0145] In some embodiments, the field pest and disease control system includes a sound monitoring unit. For an introduction to the sound monitoring unit, please refer to [link to relevant documentation]. Figure 2 A detailed description of step 220 in process 200 is shown below.

[0146] In some embodiments, the field pest and disease control system also includes a data processing unit. For an introduction to the data processing unit, please refer to [link to relevant documentation]. Figures 3-6 The document provides a detailed description of the data processing from the image acquisition unit and the sound monitoring unit.

[0147] In some embodiments, the field pest and disease control system also includes communication equipment. The communication equipment is responsible for sending the image data and sound data acquired from the image acquisition unit and the sound monitoring unit to the data processing unit.

[0148] The field pest and disease control systems described in some embodiments of this specification have comprehensive pest and disease monitoring capabilities, precise data processing and parameter determination, adaptive sampling frequency and number of monitoring units, and efficient data interaction and communication. These features help farmers or field managers to more accurately monitor, analyze, and control pests and diseases in the field, thereby improving crop health and yield.

[0149] Figure 7 This is a schematic diagram of the structure of a field pest and disease control system according to some embodiments of this specification. For example... Figure 7 As shown, the data processing unit 130 includes an image information processing module 131.

[0150] In some embodiments, the image information processing module 131 determines the image features of the field based on the image information sequence, and determines the number of at least one movable sound monitoring unit based on the image features of the field. For details regarding the image information processing module 131, see [link to relevant documentation]. Figure 3 Description of the number of sound monitoring units.

[0151] like Figure 7 As shown, the data processing unit 130 also includes a control parameter generation module 132.

[0152] In some embodiments, the control parameter generation module 132 estimates the remaining amount of primary pest control organisms in the field based on image and sound information sequences; predicts future pest and disease characteristics of the field based on the remaining amount of primary pest control organisms, wherein the future pest and disease characteristics include at least one pest and disease type and intensity at a future time point; and determines control parameters for pests and diseases in the field based on the future pest and disease characteristics. For details regarding the control parameter generation module 132, please refer to [link to relevant documentation]. Figure 5 Description of parameters for determining pest and disease control.

[0153] In some embodiments, the control parameter generation module is further configured to generate several sets of candidate control parameters for at least one area of ​​the field; predict the pest and disease elimination effect after a preset time period based on each set of candidate control parameters; and determine the control parameters for pests and diseases in the area based on the pest and disease elimination effect corresponding to each set of candidate control parameters and the control cost corresponding to each set of candidate control parameters. For more details, please refer to [link to relevant documentation]. Figure 6 A description of the specific methods for determining pest and disease control parameters.

[0154] This specification provides one or more embodiments of a field pest and disease control system, including a processor for executing field pest and disease control methods.

[0155] This specification also provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes a method for controlling field pests and diseases.

[0156] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0157] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0158] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0159] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0160] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0161] For each patent, patent application, patent application publication, and other material, such as articles, books, specifications, publications, and documents, referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0162] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and are considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. A method for controlling pests and diseases in fields, comprising: At least one image acquisition unit deployed in the field acquires pest and disease image information at a preset sampling frequency within a preset time period to obtain an image information sequence; the number of image acquisition units is determined based on the number of plants in the field; the shooting accuracy of the image acquisition units is determined based on weather conditions; the preset sampling frequency is related to the growth stage of the plants. Field pest and disease sound data are acquired by at least one mobile sound monitoring unit to obtain a sound information sequence; the number of the at least one mobile sound monitoring unit is determined based on the image information sequence. Based on the image information sequence and the sound information sequence, control parameters for pests and diseases in the field are determined. The control parameters include at least the type of insecticide and / or pesticide, the amount applied at one time, and the application frequency.

2. The method for controlling field pests and diseases as described in claim 1, wherein the number of the at least one movable sound monitoring unit is determined based on the image information sequence, including: Based on the image information sequence, determine the image features of the field; The number of the at least one movable sound monitoring unit is determined based on the image features of the field.

3. The method for controlling pests and diseases in fields as described in claim 1, wherein determining the control parameters for pests and diseases in the field based on the image information sequence and the sound information sequence includes: Based on the image information sequence and the sound information sequence, the amount of original pest control organisms remaining in the field is estimated. Based on the amount of original pest control organisms remaining in the field, the future pest and disease characteristics of the field are predicted. The future pest and disease characteristics include at least one type and intensity of pest and disease at a future point in time. Based on the future pest and disease characteristics of the field, determine the pest and disease control parameters for the field.

4. The method for controlling pests and diseases in fields as described in claim 3, wherein determining the control parameters for pests and diseases in the field based on the future pest and disease characteristics of the field includes: For at least one area of ​​the field, generate several sets of candidate control parameters; Predict the pest and disease elimination effect after controlling a preset time based on each set of candidate control parameters; Based on the pest and disease elimination effect corresponding to each set of candidate control parameters and the control cost corresponding to each set of candidate control parameters, control parameters for pests and diseases in the region are determined.

5. A field pest and disease control system, comprising an image acquisition unit, a sound monitoring unit, and a data processing unit; The image acquisition unit is configured to acquire pest and disease image information at a preset sampling frequency within a preset time period to obtain an image information sequence; the number of image acquisition units is determined based on the number of plants in the field; the shooting accuracy of the image acquisition unit is determined based on weather conditions; the preset sampling frequency is related to the growth stage of the plants. The sound monitoring unit is configured to acquire sound data of field pests and diseases to obtain a sound information sequence; the number of the sound monitoring units is determined based on the image information sequence. The data processing unit is configured to determine control parameters for pests and diseases in the field based on the image information sequence and the sound information sequence. The control parameters include at least the type of insecticide and / or pesticide, the amount applied at one time, and the application frequency.

6. The field pest and disease control system as described in claim 5, wherein the data processing unit includes an image information processing module, and the image information processing module is configured to: Based on the image information sequence, determine the image features of the field; Based on the image features of the field, the number of at least one movable sound monitoring unit is determined.

7. The field pest and disease control system as described in claim 5, wherein the data processing unit includes a control parameter generation module, and the control parameter generation module is configured to: Based on the image information sequence and the sound information sequence, the amount of original pest control organisms remaining in the field is estimated. Based on the amount of original pest control organisms remaining in the field, the future pest and disease characteristics of the field are predicted. The future pest and disease characteristics include at least one type and intensity of pest and disease at a future point in time. Based on the future pest and disease characteristics of the field, determine the pest and disease control parameters for the field.

8. The field pest and disease control system as described in claim 7, wherein the control parameter generation module is further configured to determine control parameters for the field pests and diseases based on the future pest and disease characteristics of the field, including: For at least one area of ​​the field, generate several sets of candidate control parameters; Predict the pest and disease elimination effect in at least one area of ​​the field after controlling the preset time based on each set of candidate control parameters; Based on the pest and disease elimination effect corresponding to each set of candidate control parameters and the control cost corresponding to each set of candidate control parameters, control parameters for pests and diseases in the region are determined.

9. A field pest and disease control device, comprising a processor, the processor being used to execute the field pest and disease control method as described in any one of claims 1 to 4.

10. A computer-readable storage medium storing computer instructions, wherein when a computer reads the computer instructions in the storage medium, the computer executes the field pest and disease control method as described in any one of claims 1 to 4.

Images