1124 results about "Insect pest" patented technology

Provided in the present invention are a creation method and apparatus for a tea leaf disease recognition model, and a device and a storage medium. The creation method comprises: acquiring a plurality of images of tea leaves, and disease and insect pest information corresponding to each image; generating a tea leaf disease recognition model, wherein the tea leaf disease recognition model includes a MobileNetV3 model, an ultra-lightweight attention model and a fully connected layer; and on the basis of the plurality of images of tea leaves and the disease and insect pest information corresponding to each image, training the tea leaf disease recognition model. The tea leaf disease recognition model can automatically recognize tea leaf diseases and insect pests.

The invention discloses a garlic disease and insect pest dynamic diagnosis system based on temperature and humidity time sequence data, relates to the technical field of agricultural information processing, and solves the problems that in the prior art, a fixed parameter model is prone to sensitivity sudden drop, false alarm sudden increase and systematic deviation under sudden or semi-sudden changes of field environment and management variables. According to the scheme, semantic processing of temperature and humidity and farming events is carried out through an acquisition module, a system coupling module carries out segmented identification on distribution mutation caused by environment and operation, a domain representation module constructs causal threatening features, a prediction calibration module carries out dual-path drift decomposition and rapid correction, and a prediction result is obtained. The sample adding and label collecting module generates anti-fact samples and actively collects labels, and the decision attribution module outputs a structured evidence chain; according to the method, the dynamic adaptive capacity and reliability of the diagnosis system under the conditions of non-stationary distribution and concept drift are remarkably improved.

The invention provides a whole-crop explainable disease and pest diagnosis method and system based on a multi-mode large model. The method comprises the following steps: constructing a knowledge extraction model of a two-way cross attention mechanism based on relation guidance, extracting structured knowledge from authoritative agricultural data, and constructing a pest and disease knowledge enhancement database to dynamically retrieve prior knowledge of a target crop; a hierarchical image processing strategy is adopted, and global, local and target area multi-level feature information is extracted from an input image; inputting and priori knowledge are integrated into a comprehensive diagnosis instruction, and a thinking chain guiding module is introduced to guide a large model to carry out multi-step reasoning according to a reasoning path; and performing unified reasoning by using the multi-modal large model, and outputting a disease and pest diagnosis result and a diagnosis basis thereof. The method does not need manual marking of multi-modal data or retraining, can realize efficient diagnosis of whole crop diseases and insect pests under the condition that the multi-modal data and computing resources are limited, has low cost, strong generalization ability and high interpretability, and is suitable for large-scale agricultural production practice.

The invention discloses a crop disease and insect pest image recognition algorithm based on dynamic adaptive multispectral fusion Transform, and belongs to the crossing field of agricultural information technology and computer vision. The objective of the invention is to solve the problems of insufficient multi-spectral feature fusion, poor complex background adaptability and insufficient precision in traditional recognition. Acquiring pest and disease damage images of crops in different wave bands (visible light, near-infrared light and the like) to construct a data set; through a dynamic adaptive fusion module, spectral weight distribution is learned in real time based on an attention mechanism, weights are adjusted according to spectral response differences of disease and insect pest areas, and accurate feature aggregation is achieved; the fusion features are input into an improved Transform model, a self-attention mechanism of crop semantic priori knowledge is introduced, focusing of key features of diseases and insect pests is enhanced, and background interference is inhibited; and finally outputting the disease and pest category and confidence. According to the method, through dynamic fusion and Transform cooperation, the recognition accuracy and robustness in a complex scene are improved, support is provided for early warning and prevention of diseases and insect pests, and the application value is remarkable.

The invention provides a multi-task identification method for strawberry diseases and insect pests, and belongs to the technical field of strawberry leaf disease identification. The method comprises the following steps: marking an enhanced original strawberry leaf image, and constructing a multi-task training data set; inserting a double attention unit on a semantic segmentation model decoder as a segmentation network, constructing a detection network based on a lightweight detection model, inputting a segmentation mask output by the segmentation network into the detection network to construct a cascade model, and performing preliminary training; performing multi-task joint learning on the cascade model; based on the multi-task data set, a progressive training strategy is combined with a cosine annealing learning rate adjustment strategy, and final training is carried out on the cascade model after joint learning; and inputting a to-be-detected strawberry leaf image into the finally trained cascade model, and outputting a disease type and a severity level. According to the method, the recognition sensitivity of tiny disease spots can be effectively improved, and the generalization ability of the model to complex illumination and shielding scenes is enhanced.

The invention relates to an intelligent monitoring system for prevention and control of diseases and insect pests for bean planting, in particular to the field of intelligent monitoring of prevention and control of agricultural diseases and insect pests, and can realize extremely early precise recognition and early warning of diseases and insect pests of bean crops. The weak lesion spectral features and the continuous deterioration trend of the plant can be sensitively captured in a stage which is difficult to perceive by naked eyes, real diseases and environmental interference are effectively distinguished, the system can automatically locate a suspicious lesion area by using a weak supervised learning mechanism and only needing image-level labeling, the dependence on expensive pixel-level labeling data is greatly reduced, and the accuracy of the system is improved. Finally, a high-confidence early warning signal is output through multi-source information collaborative decision, a scientific basis is provided for accurate and green prevention and control, blind pesticide application is effectively avoided, and crop health and yield are guaranteed.

The invention discloses a cross-architecture knowledge distillation method based on fruit and vegetable disease and insect pest image classification, and relates to the technical field of fruit and vegetable disease and insect pest image classification. Constructing a teacher network model based on visual Transform and a student network model based on a convolutional neural network; realizing logs distillation by utilizing a cross attention mechanism; intensifying the capture of global and local features by the student model through inter-sample and intra-sample relation distillation; and training the student network based on multi-loss weighted optimization to obtain a classification model with high precision and light weight. According to the method, the global perception ability and the deep semantic knowledge contained in the pre-trained visual Transform teacher model are efficiently migrated to the lightweight convolutional neural network student model, so that the recognition ability and the classification performance of the student model on complex pest and disease damage characteristics are remarkably improved.

The invention discloses a pheromone binding protein derived peptide capable of effectively monitoring sex pheromones of fall webworms and a biosensor, and belongs to the field of biosensors. At present, methods such as sample plot survey and sex traps commonly used in fall webworm monitoring have the problems of poor timeliness, high labor cost, insufficient data continuity and the like. In order to solve the problem, the pheromone binding protein-derived peptide provided by the invention has an amino acid sequence as shown in SEQ ID NO: 2, the biosensor comprises a substrate and an interdigital electrode, a single-walled carbon nanotube is attached to the electrode, and the electrode is also connected with the pheromone binding protein-derived peptide. The sensor can specifically detect sex pheromones of fall webworms, has no response to 17 plant volatile matters, and can detect sex pheromones released by as low as five live female fall webworms under laboratory conditions. The method has application potential in the fields of early pest monitoring, prevention and control efficiency improvement, ecological safety guarantee and the like.

The invention relates to the technical field of agricultural disease and insect pest monitoring, and discloses a rubber tree disease and insect pest collaborative monitoring and early warning method and system based on multi-source fusion, and the method comprises the steps: collecting multi-source data, and obtaining remote sensing, unmanned aerial vehicle, ground sensor and manual inspection data; data fusion, wherein a fusion feature set is generated through preprocessing, space-time alignment and deep learning feature fusion; intelligent early warning is carried out, a basic model is constructed based on fusion features, and risk level, region and time early warning is generated through real-time data dynamic correction; cooperative prevention and control, pushing of early warning and scheduling of intelligent equipment, and feedback of a prevention and control effect optimization model; the system comprises a multi-source data acquisition module, a data fusion processing module, an intelligent early warning analysis module and a collaborative prevention and control linkage module. The problems of data isolation, early warning lag and prevention and control disjunction are solved, monitoring comprehensiveness, early warning accuracy and prevention and control timeliness are improved, and support is provided for sustainable development of the rubber industry.

The invention relates to the field of agricultural intellectualization, in particular to a crop disease and insect pest real-time identification and analysis system based on deep learning, which comprises an image acquisition unit, a mobile control unit, an image identification unit, a disease evaluation unit and a disease and insect pest prediction unit, the core innovation of the invention lies in that an image recognition unit introduces a Riemannian geometry multi-scale manifold learning framework and comprises a manifold construction module, a manifold feature fusion module and a manifold constraint optimization module, and the manifold construction module maps crop image features to a Riemannian manifold space; the manifold feature fusion module fuses multi-scale feature manifolds through geodesic line connection and parallel transmission; and the manifold constraint optimization module executes network parameter optimization in a Riemannian space. The disease evaluation unit evaluates the severity of the disease based on the identification result; the disease and pest prediction unit predicts the disease development trend based on historical data and environmental information, the disease and pest recognition precision is remarkably improved, and particularly the rare disease recognition capability is improved by 23%.

The invention discloses a method for identifying insect pests of tobacco leaves. The method comprises the following steps: S1, acquiring near infrared spectrum data and visible light image data of the tobacco leaves; s2, pre-processing parameters are dynamically adjusted according to the data quality indexes, smoothing processing and derivative calculation are carried out on the near infrared spectrum data, and spectrum feature vectors are obtained; s3, processing the visible light image data through a feature extraction algorithm to generate an image feature vector; s4, splicing the preprocessed spectral feature vector and the preprocessed image feature vector to form a fused feature vector; s5, a convolutional neural network model is used to process the fusion feature vector, and the convolutional neural network model comprises an attention mechanism so as to identify the insect pest type; and S6, outputting a pest recognition result. The method can solve the problems that in the prior art, the morphological characteristics of the tobacco diseases cannot be comprehensively captured due to data singleness, near infrared spectrum data are easily interfered by environmental factors, and the characteristics are lost after preprocessing, so that the accuracy of identifying the insect pests of the tobacco is improved.

The invention discloses a fruit bagging device and a bagging system, and belongs to the technical field of agricultural automation. The fruit bagging device is novel and reasonable in structure, the paper bag binding mechanism and the paper bag taking mechanism are arranged on the main body rack in an integrated mode at the same time, the ingenious matching design of the paper bag binding mechanism and the paper bag taking mechanism is utilized, automatic bagging can be achieved, and efficient and accurate fruit bagging can be achieved in combination with an intelligent control system. The production efficiency is remarkably improved, the time and labor cost required by manual operation are reduced, the protection degree of the fruits is improved, and the fruits are prevented from being affected by diseases and insect pests and environmental factors in the growth process. In addition, due to automatic bagging operation, the damage rate of the fruits is reduced, the consistency of the appearance and quality of the fruits is ensured, and the market competitiveness is enhanced. The bagging system provided by the invention comprises the fruit bagging device and has all the characteristics of automatic bagging of the fruit bagging device.

The invention provides an automatic plant maintenance method and device based on multi-AI model collaboration, belongs to the technical field of intelligent plant maintenance, and solves the technical problem that the intelligent result of automatic maintenance is inaccurate due to lack of precise data support in existing plant maintenance. The method comprises the following steps: performing parallel processing on acquired data by utilizing a multi-AI model; the multi-AI model comprises a plurality of sub-models and a structured cooperative processing module; the sub-model comprises a plant health status evaluation sub-model; a disease identification sub-model; a pest recognition sub-model; an environment suitability analysis sub-model; a plant growth state stage identification sub-model; generating a unified data contract by using an information summarization formatting method; performing environment conflict detection, forming an intelligent maintenance executable strategy, converting an equipment instruction, executing automatic control and supervision, performing periodic monitoring management and adaptive adjustment, and outputting an intelligent maintenance result report. The system is suitable for automatic plant maintenance based on computer vision, the Internet of Things technology and the automatic control technology.

The invention relates to a landscaping plant disease and insect pest distribution data statistical method, which comprises the following steps: acquiring multi-source parameter data in real time on the basis of an environmental induction factor having a causal relationship with disease and insect pest occurrence, constructing an inducement fluctuation trend judgment relationship, and dynamically judging whether a disease and insect pest distribution data statistical task is triggered or not in a statistical period; after the statistical task is triggered, statistical layering processing is conducted on the same plant species, and the pest exposure rate, the occurrence frequency and the recovery duration of each layered population are calculated respectively; carrying out continuous, stage and wandering behavior recognition on insect pest types in combination with distribution evolution characteristics of insect pests in time and space dimensions in a historical statistical period; identifying a statistical blind area for an area with data missing in the statistical period; and constructing a pest and disease damage accumulated threshold value judgment relation, when a certain pest and disease damage statistical value exceeds a set threshold value, triggering an early warning prompt, and marking a corresponding risk level and a disposal priority in a statistical result.

The invention relates to the technical field of pest prediction, in particular to a pest occurrence environment threshold prediction method and system based on a knowledge graph, and the method comprises the following steps: obtaining parameters such as air temperature, humidity, illumination and rainfall through a sensor, generating time series data through sliding window standardization, and extracting sensitive factors through K mean value recognition mutation; the equal-frequency box is combined with the behavior log to generate threshold mapping, the random forest analyzes a triggering sequence to construct a causal chain, and the triple is embedded into the map to update edge weight matching to generate a prediction path map. According to the method, environment sequence features are extracted through a sliding window, mutation events are clustered and recognized, pest sensitive factors are screened, five-level threshold values are established in a binning mode, behavior nodes are mapped, a causal chain node sequence is generated through a random forest model, a knowledge graph is constructed through triples, dynamic update weights are embedded, real-time data are matched, and nonlinear association is carried out. The sudden change behavior relationship is identified, and the early warning precision and response efficiency are improved.

The invention provides a trichoderma maple fungicide, a microbial granular fertilizer as well as a preparation method and application of the trichoderma maple fungicide and the microbial granular fertilizer, and relates to the field of microorganisms. The acer rubrum fungicide contains acer rubrum RA with the preservation number of CGMCC No.35889. The acer rubrum fungicide has the capability of decomposing inorganic phosphorus, is wide in phosphorus dissolving range, can decompose tricalcium phosphate, ferric phosphate and aluminum phosphate, and particularly still has the very strong capability of decomposing the inorganic phosphorus under the low-temperature condition; the strain has the capability of producing siderophore and IAA at low temperature; the strain has an inhibition effect on various pathogenic bacteria causing field crop diseases. The microbial granular fertilizer provided by the invention contains various biostimulant substances, can promote crop growth, improve plant stress resistance and improve plant resistance to plant diseases and insect pests, and field tests prove that the microbial granular fertilizer can significantly promote crop growth and improve crop yield.

The invention provides a wormwood planting fertilizer and application thereof, and belongs to the technical field of agricultural planting. The wormwood planting fertilizer is prepared from the following components in parts by weight: 10 to 15 parts of humic acid, 5 to 8 parts of amino acid, 2 to 3 parts of wormwood extract A, 3 to 5 parts of wormwood extract B, 15 to 20 parts of nitrogen-phosphorus-potassium compound fertilizer, 0.01 to 0.03 part of sodium selenite, 0.02 to 0.05 part of zinc sulfate, 0.3 to 0.5 part of cellulose nanocrystal, 0.01 to 0.03 part of malic acid and 0.1 to 0.2 part of sodium alginate. By means of the two-dimensional design that components synergistically enhance absorption and the planting process is matched with the growth rhythm, the problems that in traditional fertilization, nutrients are unbalanced, the selenium and zinc utilization rate is low, and pest and disease damage prevention and control are difficult are solved, efficient absorption of wormwood on microelements, accurate supply of nutrients and reduction of the pesticide use amount are achieved, and the yield of the wormwood is increased. The yield and the medicinal quality are synergistically improved.

The invention discloses paenibacillus sp. H31, which is preserved in the China Center for Type Culture Collection (CCTCC), the preservation number is CCTCC NO: M 20252669, and the preservation date is November 24, 2025. The invention further discloses a preparation method of the paenibacillus sp. The paenibacillus H31 disclosed by the invention not only has broad-spectrum disease-resistant activity on pathogenic fungi of various plants, but also has a remarkable growth-promoting effect on pepper, so that the paenibacillus H31 can be widely applied to prevention and treatment of agricultural diseases and insect pests, and sustainable development of green agricultural production is promoted. In addition, the paenibacillus H31 also has the effects of hydrolyzing proteinase and cellulose and decomposing ferritin, so that the paenibacillus H31 also can be applied to the scenes of industrial production and the like.

The invention relates to an insect pest detection processing method, system and device, and belongs to the field of insect pest detection.The method comprises the steps that a crop image in a target area is collected, black spot recognition and malformation recognition are conducted on the crop image, and black spot parameters and malformation parameters are obtained; according to the black spot parameter and the malformation parameter, calculating to obtain a first insect pest parameter, and configuring an insect body detection range and an insect body detection scale; collecting a detection image set, and carrying out insect body recognition to obtain an insect body recognition result; and processing according to the insect body identification result to obtain a second insect pest parameter, and calculating to obtain an insect pest parameter as an insect pest detection processing result in combination with the first insect pest parameter. According to the method, the technical problems of inaccurate detection and low treatment efficiency caused by the fact that pest distribution characteristics are not considered in mangosteen pest detection in the prior art are solved, and the technical effects of analyzing the pest distribution characteristics through crop pest symptoms, optimizing a detection strategy and improving pest detection accuracy and treatment efficiency are achieved.

The invention provides an insect pest prediction method based on PSO-LSTM, belongs to the technical field of agricultural information, and aims to solve the problems that a single machine learning model is adopted in a traditional insect pest prediction method, the long-term modeling capability of time sequence data is insufficient, the complex nonlinear relation between the number of insect pests and meteorological factors is difficult to capture, and the prediction precision is low. Comprising the following steps: S1, collecting insect pest data and establishing a multivariable time sequence data set; s2, data preprocessing; s3, feature selection; and S4, establishing an insect pest prediction model, optimizing the insect pest prediction model by using a PSO module, and obtaining a prediction value of the number of insect pests at the next moment based on the optimized insect pest prediction model.

The invention discloses an early-stage intelligent monitoring system for citrus reiculata Blanco canopy diseases and insect pests based on multispectral imaging, and belongs to the technical field of agricultural information. The system comprises a multispectral imaging module, a three-dimensional point cloud acquisition module, a data fusion module, a time sequence data analysis module, an intelligent identification module and a monitoring result output module. The method comprises the following steps: synchronously acquiring a multispectral image and laser radar point cloud data of a citrus reiculata tree canopy, and generating a point cloud model through spatial registration fusion; continuously recording model data of a plurality of time points, and extracting a time sequence feature vector; identifying disease and pest types and severity by using a deep learning model; and outputting a result to the user terminal. According to the invention, the problem that large-range and high-precision early monitoring of diseases and insect pests of citrus reiculata canopies is difficult to realize in the prior art is solved, early discovery, precise positioning and trend early warning of the diseases and insect pests are realized through air-space-ground integrated data fusion and intelligent analysis, and the intelligent level of orchard management and the disease and insect pest control efficiency are effectively improved.

The invention discloses a generative AI-based disease and insect pest identification evaluation and multi-modal question and answer method, and relates to the technical field of crop disease and insect pest prevention, and the method comprises the steps: obtaining multi-modal data containing a standardized image and a structured text feature; utilizing a pre-trained pest and disease target detection model to identify the spatial position of a pest and disease target in the image, and cutting to obtain a target area image; a color feature vector and a shape feature vector of the target area are extracted, text features are combined, semantic enhancement and cross-modal alignment are performed through generative AI, and an explicit feature vector of diseases and insect pests is constructed; matching and analyzing with a preset disease and pest knowledge base, and identifying disease and pest types; quantifying the damage degree of the diseases and pests according to the characteristic parameter change characteristics to obtain a damage grade judgment result; generating a question-answer reply based on the type identification result and the hazard level; according to the method, the problems that the disease and pest recognition accuracy is limited, the harm degree is difficult to quantify and intelligent multi-modal decision question and answer support cannot be provided are solved.

The invention relates to the technical field of intelligent agriculture, and discloses a farmland pest image recognition inspection robot which comprises a moving and navigation platform, a wide-area sensing and screening system, a multifunctional diagnosis and marking mechanical arm and a data processing and control unit. The wide-area sensing and screening system of the robot is used for primarily screening images to lock suspicious target plants; an active physiological probe and an in-situ micro-marking nozzle module are integrated at the tail end of the multifunctional diagnosis and marking mechanical arm. The method comprises the following steps: performing contact measurement on a suspicious target plant to obtain multi-modal physiological information and performing preliminary diagnosis; when the diagnosis state is suspected, performing in-situ micro-labeling on the plant; and after a preset time interval, repositioning the plant and retesting. According to the method, wide-area image screening and contact type time sequence physiological diagnosis are combined, and the accuracy of disease and pest diagnosis, the early warning capability and the decision reliability are remarkably improved.

The invention discloses an AI visual identification-based landscaping pest and disease damage intelligent monitoring and early warning system, and particularly relates to the technical field of AI visual identification pest and disease damage, and the system comprises the steps: obtaining time sequence visual image data, space-time labels and environment sensing data of a target garden area; inputting the time sequence visual image data into a pre-trained disease and insect pest AI identification model, and outputting an identification result; calculating initial occurrence density and local diffusion trend parameters of disease and pest species, and generating a spatial distribution thermodynamic diagram; constructing a multi-factor risk assessment model; dynamically generating a graded early warning signal; according to the invention, the landscaping pest and disease damage intelligent monitoring and early warning system is constructed through the multi-source heterogeneous data acquisition module, the feature extraction and identification module, the data aggregation and space association module, the multi-factor risk assessment and time sequence prediction module and the dynamic early warning and decision support module; the problems of single monitoring dimension, weak data fusion and space association capability, fragmentation of decision support information and the like are solved.

The invention relates to a multifunctional pseudomonas Y2-2 and application thereof, the strain is a multifunctional microbial strain, can effectively utilize microorganisms to solve the problem of heavy metal environmental pollution remediation, can also restrain various plant diseases and insect pests, and is classified and named as Pseudomonas sp. The strain is preserved in China General Microbiological Culture Collection Center (CGMCC) on April 21, 2025, the address is Institute of Microbiology, Chinese Academy of Sciences, No.3, No.1 Yard, Beichen West Road, Chaoyang District, Beijing, and the preservation number is CGMCC No.34287. The method can effectively utilize microorganisms to repair heavy metal environmental pollution, can inhibit various plant diseases and insect pests, is good in effect and high in efficiency, and has practical popularization and application values.

The invention relates to the technical field of image processing, in particular to a flower disease and insect pest monitoring method based on machine vision, and the method comprises the steps: obtaining a candidate pseudo boundary set in a gray level image of a to-be-monitored flower leaf, and obtaining a gray level distribution feature of a pixel point in a local analysis region of each candidate pseudo boundary; obtaining a vein feature index of each candidate pseudo-boundary according to the linear structure feature of each candidate pseudo-boundary and the linear structure feature of each candidate pseudo-boundary; according to the vein feature index and the direction feature of each candidate pseudo boundary, screening in the candidate pseudo boundary set to obtain at least one pseudo boundary; in the process of carrying out region segmentation on the gray level image by using the watershed algorithm, the initial distance of each pixel point after distance transformation is obtained, adaptive distance compensation is carried out on the initial distance of each pixel point according to the position relation between each pixel point and each pseudo boundary, the compensation distance is obtained, complete segmentation of a scab region is realized, and the scab image segmentation efficiency is improved. And a reliable quantitative basis is provided for flower disease and pest monitoring and prevention decision making.

The invention relates to a lightweight multi-scene disease and pest detection method and system based on RT-DETR. According to the scheme, firstly, a standardized image processing link is constructed, multi-band feature extraction is carried out on an input image by using a convolutional backbone network introduced with wavelet transform, an effective receptive field is expanded in a frequency domain through wavelet decomposition and an inverse reconstruction mechanism, and feature capture of a tiny insect pest target is enhanced while calculation redundancy is reduced. Furthermore, a bidirectional feature pyramid network including global and local double-branch collaborative modeling is adopted, cross-level dynamic interaction and gating fusion are performed on multi-scale features, and environmental noise interference such as veins and illumination under a complex farmland background is effectively inhibited. And finally, establishing a homography mapping model from a pixel plane to a geographic space according to camera calibration parameters, converting a visual detection result into a spatial distribution diagram layer with latitude and longitude information, and realizing dimension crossing of pest and disease damage monitoring from single-point identification to region-level risk assessment.

The present invention relates to microencapsulated preparations comprising biopesticide, bio-fungicide, and plant growth promoting agents and uses thereof, as well as to methods for controlling pests and for producing said preparations for managing insect pests. In particular, the invention relates to microencapsulated preparations comprising at least one insect-pathogenic (entomopathogenic) fungus selected from Metarhizium spp. and Beauveria bassiana, and at least one pathogenic Bacillus spp. bacterial strain, preparations and particles comprising these, their use on plant material, methods for controlling pests therewith, and processes for their production.

The invention discloses a remote monitoring system for agricultural product pests in a hot area, and relates to the technical field of agricultural pest monitoring, and the system comprises a sensing module, a communication module, a data processing module and an application module. The temperature and humidity compensation sub-module is arranged in the sensing module, and the sampling frequency of the infrared sensor and the exposure time of the camera are dynamically adjusted in combination with environmental parameters collected by the temperature and humidity sensor, so that sensor performance degradation caused by a high-temperature and high-humidity environment is avoided, and the accuracy of collected data is ensured; the problem that a sensor in an existing system is easily influenced by the environment is solved, an agricultural product growth-insect pest coupling digital twinborn model is constructed through a data processing module, insect pest diffusion and crop damage conditions are simulated by using a deep reinforcement learning algorithm, and dynamic prevention and control suggestions are generated, so that accurate prediction of insect pest trends is realized; the problem that an existing system cannot provide effective prevention and control suggestions is solved, reliable support is provided for hot-area agricultural product pest prevention and control, and the yield and quality of hot-area agricultural products are guaranteed.

The invention discloses an intelligent monitoring method and device based on multi-modal information fusion, and the method comprises the steps: (1) collecting multi-modal data; (2) carrying out self-adaptive preprocessing on the microwave signal; (3) video image self-adaptive preprocessing; (4) multi-domain feature extraction; and (5) carrying out weighted fusion classification output. The method and the system are suitable for monitoring main grain storage pests such as maize weevil and grain beetles in the scenes of national grain depots and civil granaries, can realize real-time identification, positioning and counting of pests from the surface layer of a grain pile to the depth of 0.5 m, and solve the problems of insufficient performance of a single-mode sensor (vision, radar and acoustics) and poor adaptability of a multi-mode fusion environment in the prior art. The method adapts to intelligent transformation of the existing granary, and meets the requirements of high precision, full coverage and strong robustness of modern grain storage.