Garden plant risk grading early warning method and system based on artificial intelligence

Abstract

The invention provides a garden plant risk grading early warning method and system based on artificial intelligence. Wherein vibration and temperature data of a running part of target equipment are collected in real time through an environment adaptation type sensor to serve as initial detection data. And establishing a compensation calculation model based on the temperature distribution characteristics of the sensor protection layer and the detection area, dynamically calculating temperature compensation parameters, and generating standardized detection data for eliminating the influence of the environment temperature. And matching the standardized data with historical fault features in the abnormal vibration feature database to form an analysis model. And the system inputs the comprehensive feature set into an analysis model for matching analysis, and finally generates early warning information with a grading response function in combination with material performance change data and real-time lubrication state data of the equipment component. According to the scheme provided by the embodiment of the invention, full-process automatic processing from data acquisition to intelligent early warning can be realized.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent device status monitoring and fault warning, and in particular to an artificial intelligence-based garden plant risk grading warning method and system. Background Art

[0002] In modern garden maintenance, plant diseases and pests and abnormal growth problems need to be accurately identified and warned of risks at an early stage. Traditional manual inspections are inefficient, and existing technologies are difficult to achieve automated abnormality detection of multiple plant species in complex natural environments (such as light changes, canopy occlusion, etc.). There is an urgent need for an intelligent monitoring solution that can integrate spectral feature analysis, has strong environmental adaptability, and supports graded warnings.

[0003] At present, there is a plant health monitoring system based on drone multispectral imaging, which collects vegetation indices (such as NDVI) and combines them with preset thresholds to determine abnormal areas. The system uses fixed-band reflectance analysis to identify typical problems such as abnormal chlorophyll content and generate a preliminary abnormal distribution map.

[0004] However, this solution only relies on static threshold judgment and cannot adapt to the differences in spectral characteristics caused by different plant species, growth stages and dynamic environmental changes; and it lacks the ability to predict abnormal evolution trends, making it difficult to distinguish temporary stress responses from actual risks, resulting in a high false alarm rate and insufficient warning timeliness. Summary of the invention

[0005] The present application provides a garden plant risk grading and early warning method and system based on artificial intelligence, which is used to solve the problems of high false alarm rate and insufficient early warning timeliness in the prior art.

[0006] In the first aspect, the present application provides a risk classification and early warning method for garden plants based on artificial intelligence, comprising: By deploying a drone cluster in the garden area, images of the target plant coverage area are collected to obtain the reflectance spectrum data of the plant canopy; Through the pre-constructed plant abnormal spectrum database, based on the spectrum change characteristic curves and reflection intensity threshold data corresponding to different plant types under abnormal growth conditions, the chlorophyll content data in the reflection spectrum data is analyzed to generate growth abnormality characteristic data; Based on the artificial intelligence algorithm, according to the continuous change characteristics of the abnormal growth characteristic data, the abnormal area in the plant canopy is identified, and the surrounding area corresponding to the abnormal area is verified to screen out the potential risk area; Matching the spatial distribution density of the potential risk area with the evolution process data corresponding to the historical abnormal cases stored in the plant abnormal spectrum database, and correcting the diffusion probability of the potential risk area under the local climate environment based on the matching result to generate a risk distribution map containing multiple warning levels; According to the risk distribution map, a processing suggestion plan matching each warning level is output.

[0007] Optionally, for each plant type, a plant abnormal spectrum database is pre-constructed, which contains spectrum change characteristic curves and reflection intensity threshold data in multiple continuous band intervals of the plant type under abnormal growth conditions; The reflectance spectrum data is divided into a plurality of sub-band data segments according to the band interval division rule of the spectrum change characteristic curve in the plant abnormal spectrum database; Determine whether the fluctuation direction of the reflection intensity sequence of each sub-band data segment is consistent with the preset direction of the spectral change characteristic curve, and compare whether the mean value of the reflection intensity data of each sub-band data segment exceeds the upper limit or lower limit of the reflection intensity threshold data, so as to mark it as a primary deviation segment or a secondary deviation segment; Extracting at least two specific sub-band data segments associated with the chlorophyll content data in the reflectance spectrum data from the plant abnormal spectrum database, and determining whether the reflectance intensity difference between the at least two specific sub-band data segments exceeds the reflectance intensity threshold data, so as to mark them as chlorophyll abnormal segments; According to the proportion of the first-level deviation segments, the second-level deviation segments and the chlorophyll abnormality segments, growth abnormality characteristic data including band deviation type and intensity information are generated.

[0008] Optionally, a first sub-band interval and a second sub-band interval associated with the chlorophyll content data in the reflectance spectrum data are pre-set in the plant abnormal spectrum database; Extracting two corresponding specific sub-band data segments from the plurality of sub-band data segments according to the first sub-band interval and the second sub-band interval; Calculating the reflection intensity difference between the two specific sub-band data segments, and determining whether the positive and negative signs of the reflection intensity difference are consistent with the sign direction in the reflection intensity threshold data range; If the positive and negative signs of the reflection intensity difference are consistent with the preset sign direction, and the reflection intensity difference exceeds the upper limit or lower limit of the reflection intensity threshold data, the two specific sub-band data segments are marked as chlorophyll anomaly segments.

[0009] Optionally, the abnormal growth characteristic data is calculated using an artificial intelligence algorithm according to a time series for continuous change characteristics at three consecutive time points and the degree of deviation between the current characteristic value and the normal reference value; Marking points whose continuous change characteristics exceed a first threshold and whose deviation degree exceeds a second threshold as abnormal points, and performing spatial clustering on the abnormal points to form abnormal areas in the plant canopy; An annular verification zone is formed by expanding the abnormal area by a preset distance, and the number of abnormal points in the annular verification zone is counted. When the ratio exceeds the verification threshold, it is determined to be a valid abnormal area; The risk index is calculated based on the anomaly intensity of the core area of ​​the effective anomaly area, the anomaly diffusion degree of the verification zone and the deterioration trend in the time series, and the area where the risk index exceeds the warning value is screened out as a potential risk area.

[0010] Optionally, the evolution process data corresponding to each historical abnormal case is extracted from the plant abnormal spectrum database, and the evolution process data includes the initial abnormal density distribution, the density change trend of each evolution stage and the corresponding environmental parameter change curve; Perform a multi-dimensional comparison between the density distribution map of the potential risk area and the evolution process data of each historical case to determine an initial matching coefficient, and mark the historical case whose initial matching coefficient exceeds a preset benchmark value as a candidate case; Matching the risk area characteristics of the candidate case with the evolution process data corresponding to the historical case in stages, and calculating the evolution matching degree of the candidate case; The evolution matching degree of the candidate case is taken as the matching result.

[0011] Optionally, obtaining a reflection intensity sequence of the plurality of sub-band data segments within a corresponding band interval, extracting a change in adjacent data points in the reflection intensity sequence, and calculating a distribution ratio of positive and negative signs of the change; The positive and negative sign distribution ratio is compared with the preset allowable direction range in the spectral change characteristic curve, and when the positive and negative sign distribution ratio exceeds the allowable direction range, it is determined that the direction is inconsistent, otherwise it is determined that the direction is consistent; Calculate the reflection intensity averages of the plurality of sub-band data segments, and obtain the upper limit and lower limit of the corresponding band interval in the reflection intensity threshold data; When the fluctuation direction is consistent with the preset direction and the mean exceeds the upper limit or lower limit, it is marked as a first-level deviation segment. When the fluctuation direction is inconsistent with the preset direction and the mean exceeds the upper limit or lower limit, it is marked as a second-level deviation segment.

[0012] Optionally, based on the matching results, the diffusion probability of the potential risk area under the local climate environment is corrected, and according to the comparison relationship between the corrected diffusion probability and the preset risk threshold, three warning levels of high, medium and low are divided, and a risk distribution map corresponding to the warning level is generated.

[0013] In the second aspect, the present application provides a risk classification and early warning system for garden plants based on artificial intelligence, comprising: An acquisition module is used to collect images of the target plant coverage area through a drone cluster deployed in the garden area to obtain reflectance spectrum data of the plant canopy; A generation module is used to analyze the chlorophyll content data in the reflectance spectrum data based on the spectral change characteristic curves and reflectance intensity threshold data corresponding to different plant types under abnormal growth conditions through a pre-constructed plant abnormal spectrum database to generate abnormal growth characteristic data; A screening module, for identifying abnormal areas in the plant canopy based on an artificial intelligence algorithm according to the continuous change characteristics of the abnormal growth characteristic data, and verifying the surrounding areas corresponding to the abnormal areas to screen out potential risk areas; The generating module is also used to match the spatial distribution density of the potential risk area with the evolution process data corresponding to the historical abnormal cases stored in the plant abnormal spectrum database, and to correct the diffusion probability of the potential risk area under the local climate environment based on the matching result to generate a risk distribution map containing multiple warning levels; The output module is used to output processing suggestions matching each warning level according to the risk distribution map.

[0014] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an artificial intelligence-based garden plant risk grading and early warning method as described in the first aspect above.

[0015] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program. When the computer program is executed by a computer, it implements an artificial intelligence-based garden plant risk grading and early warning method as described in the first aspect.

[0016] In an embodiment of the present application, a drone cluster is deployed in a garden area to collect images of the target plant coverage area to obtain reflectance spectrum data of the plant canopy; through a pre-constructed plant abnormal spectrum database, based on the spectral change characteristic curves and reflection intensity threshold data corresponding to different plant types under abnormal growth conditions, the chlorophyll content data in the reflectance spectrum data is analyzed to generate growth abnormality feature data; based on the continuous change characteristics of the growth abnormality feature data based on an artificial intelligence algorithm, the abnormal area in the plant canopy is identified, and the surrounding area corresponding to the abnormal area is verified to screen out potential risk areas; the spatial distribution density of the potential risk area is matched with the evolution process data corresponding to the historical abnormal cases stored in the plant abnormal spectrum database, and the diffusion probability of the potential risk area under the local climate environment is corrected based on the matching result to generate a risk distribution map containing multiple warning levels; according to the risk distribution map, a processing suggestion scheme matching each warning level is output.

[0017] The technical solution of this application has the following beneficial effects: This application collects plant canopy reflectance spectral data through a cluster of drones, combines it with a pre-built plant anomaly spectral database to analyze chlorophyll content and generate growth anomaly feature data, uses AI algorithms to identify abnormal areas and verify and screen potential risk areas, matches the distribution density of risk areas with historical case evolution data and corrects the diffusion probability based on local climate, and finally generates a graded warning risk distribution map and corresponding treatment plan, realizing full-process automated management from plant health monitoring, accurate anomaly identification, dynamic risk prediction to intelligent maintenance decision-making, significantly improving the accuracy of garden plant disease warning and maintenance efficiency.

[0018] Furthermore, a database containing multi-band spectral change characteristic curves and reflection intensity threshold data under abnormal conditions is pre-built for different plant types. The collected reflection spectrum data is divided into sub-band data segments according to the database rules, and the fluctuation direction consistency and mean of each sub-band reflection intensity sequence are judged in turn to mark the deviation level. The chlorophyll-related sub-bands are extracted for difference comparison to mark the abnormal segments, and finally the growth abnormality feature data containing band deviation feature information is generated based on the number of each type of deviation segment. This method realizes the accurate identification and quantitative evaluation of growth abnormalities of different plants through multi-band spectral feature analysis combined with dynamic threshold judgment, effectively distinguishes normal physiological changes from pathological abnormalities, provides objective and quantifiable feature basis for plant health status diagnosis, and significantly improves the accuracy and reliability of abnormality detection.

[0019] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 A flow chart of a risk classification and early warning method for garden plants based on artificial intelligence provided by the present application is shown; Figure 2 A schematic diagram of the structure of a risk classification and early warning system for garden plants based on artificial intelligence provided by the present application is shown; Figure 3 A schematic diagram of the structure of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0023] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0024] Researchers have found that the current garden plant health monitoring mainly relies on manual inspections or single spectral index analysis, which has problems such as low detection efficiency, inability to distinguish plant species-specific abnormalities, and lack of ability to predict disease spread trends. Based on this, a garden plant risk grading and early warning method based on artificial intelligence is provided, which can achieve accurate identification of plant abnormalities, risk spread prediction and graded early warning through multi-spectral feature analysis and historical case matching. The technical solution of this application can be applied to intelligent monitoring and maintenance management of plant health in scenes such as urban gardens, botanical gardens, and ecological protection areas. It can realize accurate identification and intelligent diagnosis of plant growth abnormalities, greatly improve the accuracy and reliability of disease detection; it can scientifically predict the trend of disease spread and evaluate the risk level, and provide forward-looking early warning for garden maintenance; through intelligent graded early warning and disposal suggestions, it can significantly improve the accuracy and management efficiency of garden maintenance, and effectively solve the problems of low efficiency, high false alarm rate, and lack of predictability in traditional monitoring methods.

[0025] The entire research and development process reflects a series of steps from the construction of a plant-specific spectral database, multi-dimensional abnormal feature analysis to intelligent risk prediction and graded early warning. It aims to overcome the problems of low detection efficiency, high false alarm rate, and lack of predictiveness in existing monitoring schemes, so as to achieve accurate diagnosis of the health status of garden plants, scientific assessment of disease risks, and intelligent management of maintenance decisions.

[0026] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0027] Figure 1 A flowchart of a risk classification and early warning method for garden plants based on artificial intelligence is provided for the embodiment of the present application, such as Figure 1 As shown, the method includes: 101. By deploying a drone cluster in the garden area, image acquisition is performed on the target plant coverage area to obtain reflectance spectrum data of the plant canopy; In this step, drone swarm refers to a collaborative operation system consisting of multiple drones equipped with multispectral or hyperspectral imaging devices.

[0028] The target plant coverage area refers to the distribution range of specific garden plants that need to be monitored; the plant canopy refers to the leaf community structure of the uppermost layer of plants.

[0029] The plant canopy refers to the leaf community structure at the top of the plant that receives light, and its spectral characteristics can intuitively reflect the physiological state of the plant.

[0030] Reflectance spectrum data refers to the continuous spectral characteristic curve data formed by the reflectivity of the plant canopy to light of different wavelengths, which contains spectral information of multiple bands such as visible light and near infrared.

[0031] In the embodiment of the present application, a drone cluster equipped with a hyperspectral imager is first deployed in the garden area, and systematic image acquisition of the target plant coverage area is performed through a preset route and a collaborative control strategy. Then, the sensor carried by the drone acquires the multispectral reflectance data of the plant canopy in the visible light-near infrared band range, and records the environmental parameters such as the lighting conditions and shooting angle during the acquisition to ensure data consistency. Finally, the original spectral data is subjected to radiation correction and geometric correction processing to generate standardized reflectance spectral data, which provides a data basis for the subsequent plant growth status analysis.

[0032] In the ecological restoration area of ​​a wetland park, multiple drones equipped with hyperspectral cameras were deployed to conduct periodic inspections of reed communities according to a preset grid. During periods of stable light, the drone swarm simultaneously collects visible light and near-infrared band data at a fixed height, while recording real-time light conditions. The collected raw data is processed by professional software to eliminate the influence of atmospheric scattering, and ultimately generates a canopy reflectance data set containing multiple spectral channels, ensuring that the spatial resolution meets the needs of fine monitoring.

[0033] 102. Analyze the chlorophyll content data in the reflectance spectrum data based on the spectral change characteristic curves and reflection intensity threshold data corresponding to different plant types under abnormal growth conditions through a pre-constructed plant abnormal spectrum database to generate abnormal growth characteristic data; In this step, the plant abnormal spectrum database refers to an expert knowledge base established through long-term observations that contains typical spectral features of various types of garden plants under different abnormal growth conditions.

[0034] Plant types refer to different types of garden ornamental plants classified by family and genus; abnormal growth status refers to abnormal growth conditions of plants suffering from pests and diseases, nutrient deficiencies, water stress, etc.

[0035] The spectral change characteristic curve refers to the dynamic change law of the reflectance spectral characteristics of plants during abnormal development.

[0036] Reflection intensity threshold data refers to the reference standard value determined through big data statistical analysis to determine whether the spectral data is abnormal.

[0037] Chlorophyll content data refers to the core physiological index that reflects the photosynthesis capacity and health status of plants.

[0038] Growth abnormality characteristic data refers to structured diagnostic data obtained through multi-dimensional analysis that quantitatively characterizes the type and degree of plant abnormalities.

[0039] In the embodiment of the present application, a pre-constructed plant abnormal spectrum database is first called, which contains standard spectral change characteristic curves and reflection intensity threshold data of different plant types under various growth abnormalities. The reflection spectrum data obtained in step 101 is input into the database comparison system, and the reflectance characteristics of the chlorophyll sensitive band are analyzed in detail. The degree of deviation between the current chlorophyll content data and the healthy reference value is calculated through a professional algorithm, and an abnormality judgment is made in combination with the reflection intensity threshold data. The final output includes growth abnormality characteristic data of abnormality type, abnormality degree and spatial position information, and the data format is fully compatible with the database storage structure.

[0040] For the reed community in the wetland park, the system called a pre-established plant abnormal spectrum library, which contains characteristic spectral curves of reeds under various typical stress conditions. Through comparative analysis, it was found that the reflectance changes in specific bands of the current collected data were significantly different from those of healthy samples, which was consistent with certain pollution or disease characteristics. The system automatically calculates the vegetation index, marks areas where the reflectance exceeds the normal range as abnormal, and generates a file containing location information and abnormality scores.

[0041] 103. Identify the abnormal area in the plant canopy according to the continuous change characteristics of the abnormal growth characteristic data based on an artificial intelligence algorithm, and verify the surrounding area corresponding to the abnormal area to screen out potential risk areas; In this step, the artificial intelligence algorithm refers to a plant anomaly recognition model built using deep learning technology, which can automatically learn the changing patterns of plant abnormality characteristics.

[0042] Abnormal growth characteristic data refers to a standardized structured data set that contains plant physiological indicators in multiple dimensions.

[0043] The continuous change feature refers to the dynamic evolution of plant abnormalities in a time series, and the abnormal area in the plant canopy refers to the spatial range of possible health problems identified by the algorithm.

[0044] The peripheral area refers to the buffer zone that expands outward from the abnormal area and is used to verify the diffusion trend of the anomaly.

[0045] Potential risk areas refer to abnormal ranges that are confirmed to require special attention after multiple verifications.

[0046] In the embodiment of the present application, a convolutional neural network (CNN) is first used to perform spatiotemporal analysis on the continuous change characteristics of the growth anomaly feature data, and the abnormal patch area in the canopy is located by continuously monitoring the spectral change trend (such as the reflectivity decreasing day by day) within the period. Then, the spectral similarity of the pixels in the surrounding area corresponding to the abnormal area is verified, and the isolated noise points are eliminated in combination with the spatial gradient changes of the vegetation index (such as NDVI). Finally, the boundaries of the contiguous abnormal area are delineated through morphological processing, and the potential risk areas that need to be focused on are screened out based on the abnormal area ratio and aggregation, so as to avoid the interference of misjudgment of a single detection.

[0047] Taking a certain reed canopy as an example, the artificial intelligence model detected that the vegetation index in a specific area during continuous monitoring continued to decline, exceeding the health threshold. Through image segmentation technology, it was found that the abnormal area showed diffusion characteristics, and there was a similar spectral trend in the surrounding buffer zone. After morphological processing, it was confirmed that the area of ​​the core abnormal area accounted for a significant proportion and was highly overlapped with the diseased area in the visible light image. The system eventually listed the area as a high-risk area for priority treatment, while eliminating misjudgments caused by other short-term interference.

[0048] 104. Match the spatial distribution density of the potential risk area with the evolution process data corresponding to the historical abnormal cases stored in the plant abnormal spectrum database, and modify the diffusion probability of the potential risk area under the local climate environment based on the matching result to generate a risk distribution map containing multiple warning levels; In this step, the spatial distribution density of potential risk areas refers to the distribution density of abnormal areas within a unit area.

[0049] The plant anomaly spectrum database refers to an expert knowledge base containing plant anomaly cases over the years.

[0050] Historical abnormal cases refer to typical plant abnormal events and their development processes recorded in the past.

[0051] The evolution process data refers to the complete historical record of the anomaly from its occurrence to its development, and the local climate environment refers to the real-time microclimate conditions such as temperature and humidity in the monitoring area.

[0052] The probability of spread refers to the predicted value of the possibility of abnormal spread based on multi-factor analysis; the warning level refers to the different levels of warnings divided according to the degree of risk.

[0053] A risk distribution map refers to a spatial visualization chart that directly displays the risk level of each area.

[0054] In an embodiment of the present application, the spatial distribution density index of the potential risk area (such as the number of abnormal patches per unit area) is first calculated, and similarity matching is performed with historical diffusion cases of similar diseases (such as rust and mildew) in the plant abnormal spectrum database. Then, based on the matching results, the diffusion probability of the potential risk area under the local climate environment is corrected, and local climate parameters (such as temperature, humidity, and wind speed) are introduced to construct a Bayesian network model to correct the limitations of simple spatial density assessment and predict the diffusion probability of abnormal areas under different environmental conditions. Finally, the three risk areas of high, medium, and low are divided according to the probability value, and a risk distribution map containing multiple warning levels is generated, and the intervention effect reference data of similar historical cases are simultaneously annotated in the map.

[0055] For the above case, the system retrieved the historical records of similar cases and found that the diffusion pattern of the current abnormal area is similar to that of a pollution incident in the past. Combining weather forecasts and soil condition data, a professional model simulation shows that if no timely intervention is made, the abnormal area will expand rapidly. The model divides the surrounding areas into different risk levels based on environmental factors. In the final thermal warning map, the core area is shown as the highest risk, and a gradual risk buffer zone is formed around it.

[0056] 105. According to the risk distribution map, output treatment suggestion plans matching each warning level.

[0057] In this step, the risk distribution map refers to a visualization chart of regional distribution marked with different risk levels.

[0058] The warning level refers to the severity level divided according to the risk prediction results.

[0059] Treatment recommendations refer to differentiated maintenance measures formulated for different risk levels, including prevention and control methods, operation schedules and resource allocation recommendations.

[0060] In the embodiment of the present application, the warning level division of each area is first determined based on the risk distribution map. Then, the matching historical disposal plan is retrieved from the expert knowledge base as a reference benchmark. Then, the plan is optimized and adjusted in combination with factors such as the current plant phenological period, weather conditions, and maintenance resources. Finally, a treatment recommendation plan matching each warning level is generated, including specific operating specifications, implementation time windows, and expected effects.

[0061] For the highest risk areas, the system pushes a multi-level response plan: immediately launch drones to precisely spray specific solutions for treatment; transplant specific plants to the core pollution area in a short period of time; and implement enhanced monitoring of surrounding risk areas. At the same time, according to the characteristics of the current growth stage of the plants, the plan specifically notes the most appropriate way of applying the pesticide to reduce damage. All disposal instructions are transmitted to the on-site smart devices in real time, and the system will continue to monitor the treatment effect to ensure that the disposal measures are effective.

[0062] In summary, steps 101 to 105 achieve all-weather, all-round monitoring of the health status of garden plants, establish a scientific and accurate health diagnosis system, greatly improve the accuracy and timeliness of abnormal identification, and provide forward-looking decision-making support for disease prevention and control; the final hierarchical warning and precise maintenance plan realizes the transformation of garden management from passive response to active prevention. The promotion and application of this system will significantly improve the intelligent level of urban garden management, effectively protect precious garden plant resources, and provide solid technical support for creating a sustainable ecological urban environment.

[0063] In order to improve the risk classification and early warning of garden plants based on artificial intelligence, an intelligent analysis system based on the plant abnormal spectrum database was developed. By building a database containing a variety of plant abnormal spectrum characteristics, the system realizes multi-band fine analysis of reflectance spectrum data, provides an objective and accurate scientific basis for garden plant health diagnosis, and significantly improves the accuracy and reliability of plant abnormality detection.

[0064] In some embodiments, the chlorophyll content data in the reflectance spectrum data is analyzed based on the spectral change characteristic curves and reflection intensity threshold data corresponding to different plant types under abnormal growth conditions through the pre-constructed plant abnormal spectrum database in step 102 to generate abnormal growth characteristic data, including: 201. For each plant type, pre-build a plant abnormal spectrum database including spectral change characteristic curves and reflection intensity threshold data in multiple continuous band intervals of the plant type under abnormal growth conditions; In step 201, plant types refer to various types of garden plant varieties strictly divided according to the plant taxonomy system, including but not limited to ginkgo and sycamore for trees, roses and azaleas for shrubs, and tulips and lilies for herbs; abnormal growth states refer to various pathological and physiological abnormalities that occur in plants during their growth, including fungal diseases, bacterial infections, insect pests, nutrient deficiency, water stress, light insufficiency and other abnormal growth conditions; spectral change characteristic curve refers to the characteristic change trajectory of the reflectance spectrum of a plant under a specific abnormal state, which has diagnostic significance and changes with wavelength. This change trajectory can intuitively reflect the changes in the physiological state of the plant; reflection intensity threshold data refers to the normal value range of reflectance in each band calculated by collecting a large number of healthy samples and using statistical methods, including the upper and lower limits of reflectance. These threshold data have plant species specificity and seasonal variation characteristics.

[0065] In the embodiment of the present application, firstly, for each plant type, the spectral change characteristic curves in multiple continuous band intervals under abnormal growth conditions are obtained through experimental observation, including but not limited to typical abnormal modes such as chlorophyll degradation and water loss. Then, statistical analysis is performed on each band interval to determine the upper and lower limits of the reflection intensity threshold data, and a standardized plant abnormal spectrum database is established. Finally, the spectral characteristic curves of different plant types under different abnormal growth conditions are associated with the reflection intensity threshold data and stored to form a benchmark data set for real-time comparison.

[0066] 202. Divide the reflectance spectrum data into a plurality of sub-band data segments according to the band interval division rule of the spectrum change characteristic curve in the plant abnormal spectrum database; In step 202, the reflectance spectrum data refers to the continuous reflectance data of the plant canopy collected by professional-grade hyperspectral imaging equipment, which has high spectral resolution and high spatial resolution; the band interval division rule refers to the optimal spectral segmentation scheme determined by experts based on the spectral response characteristics and abnormal diagnosis requirements of different plant varieties; the sub-band data segment refers to the reflectance data set within a specific wavelength range obtained by accurately segmenting the original hyperspectral data using digital signal processing methods according to the established division rules, and each sub-band corresponds to a specific physiological indicator diagnostic function.

[0067] In the embodiment of the present application, the band interval division rules of the spectral change characteristic curve pre-stored in the plant abnormal spectrum database are first accurately read. The rules not only clearly stipulate the starting and ending wavelengths of each characteristic band, but also include the overlapping settings and boundary processing methods of each band interval. Then, according to the division rules, the high-resolution reflection spectrum data collected in real time is accurately divided into multiple sub-band data segments that are completely consistent with the database structure, ensuring that the wavelength range of each sub-band data segment strictly corresponds to the definition in the database. Finally, each sub-band data segment is professionally normalized, and standardized radiation correction and atmospheric correction algorithms are used to eliminate the influence of factors such as ambient lighting conditions and observation angles, ensuring that its reflection intensity data can be directly and accurately compared with the threshold data in the database.

[0068] 203. Determine whether the fluctuation direction of the reflection intensity sequence of each sub-band data segment is consistent with the preset direction of the spectral change characteristic curve, and compare whether the mean value of the reflection intensity data of each sub-band data segment exceeds the upper limit or lower limit of the reflection intensity threshold data, so as to mark it as a primary deviation segment or a secondary deviation segment; In step 203, the reflection intensity sequence refers to a continuous reflectance value sequence arranged in wavelength order within a specific sub-band data segment, and this sequence reflects the subtle change characteristics of the reflectance within the band; the preset direction refers to the typical trend direction of the reflectance change of the band under a specific abnormal state recorded in the database, including multiple modes such as monotonically increasing, monotonically decreasing, increasing first and then decreasing; the first-level deviation segment refers to an abnormal data segment that meets two conditions at the same time: one is that the fluctuation direction of the reflection intensity sequence is completely consistent with the preset direction, and the other is that the reflectance mean significantly exceeds the threshold range; the second-level deviation segment refers to an abnormal data segment whose fluctuation direction of the reflection intensity sequence is inconsistent with the preset direction but the reflectance mean exceeds the threshold range.

[0069] In the embodiment of the present application, firstly, a time series analysis method is used to perform a detailed trend analysis on the reflection intensity sequence of each sub-band data segment, and a sliding window algorithm and regression analysis are used to determine whether its fluctuation direction is completely consistent with the preset direction of the spectral change characteristic curve of the corresponding band in the plant abnormal spectrum database. Then, a statistical calculation method is used to accurately calculate the mean of the reflection intensity data of each sub-band data segment, and a strict comparison is made with the upper and lower limits of the reflection intensity threshold data stored in the database. Finally, accurate marking is performed according to the comparison results: when the fluctuation direction of the reflection intensity sequence is completely consistent with the preset direction and the mean exceeds the threshold range, it is marked as a first-level deviation segment; when only the mean exceeds the threshold range but the fluctuation direction is inconsistent, it is marked as a second-level deviation segment. This hierarchical marking method can more accurately reflect the degree and characteristics of abnormal plant growth.

[0070] 204. Extract at least two specific sub-band data segments associated with the chlorophyll content data in the reflectance spectrum data from the plant abnormal spectrum database, and determine whether the reflection intensity difference between the at least two specific sub-band data segments exceeds the reflection intensity threshold data, so as to mark them as chlorophyll abnormal segments; In step 204, the chlorophyll content data refers to the core physiological indicator data reflecting the photosynthesis capacity and health status of plants obtained by inversion through professional spectral analysis methods; the specific sub-band data segment refers to a characteristic wavelength interval combination that has been scientifically verified to have a strong correlation with the chlorophyll content, usually including the chlorophyll absorption peak band and the reflection peak band; the reflection intensity difference refers to the difference between the reflectivity means of two characteristic sub-band data segments, and this difference value can effectively reflect the relative content change of chlorophyll.

[0071] In the embodiment of the present application, firstly, the specific sub-band data segment information closely related to the chlorophyll content data is accurately extracted from the plant abnormal spectrum database. These bands are usually located in the red light region (such as 670-680nm) and near-infrared region (such as 700-750nm) that are most sensitive to chlorophyll changes. Then, the corresponding specific sub-band data segment is accurately located in the real-time collected hyperspectral reflectance spectrum data, and the difference in reflection intensity between them is calculated using a differential algorithm. Finally, the difference is strictly compared with the reflection intensity threshold data. When the difference exceeds the preset threshold range, the band combination is marked as a chlorophyll abnormal segment. This marking method can effectively identify potential abnormalities in the photosynthesis system, including early abnormal symptoms such as reduced chlorophyll content and decreased photosynthetic efficiency.

[0072] 205. Generate growth anomaly characteristic data including band deviation type and intensity information according to the quantity ratio of the first-level deviation segments, the second-level deviation segments and the chlorophyll anomaly segments.

[0073] In step 205, the quantity ratio refers to the percentage of the number of each type of abnormal marked sub-bands to the total number of analyzed sub-bands, and this indicator reflects the extent of the abnormality; the band deviation types include three basic types: primary deviation, secondary deviation and chlorophyll abnormality, and each type can be further divided into three levels: mild, moderate and severe according to the deviation amplitude; the intensity information refers to the quantitative value of the specific degree to which each abnormal sub-band exceeds the normal threshold range, usually expressed as a multiple of the standard deviation or a percentage.

[0074] In the embodiment of the present application, a statistical algorithm is first used to accurately count the number of segments marked as first-level deviation segments, second-level deviation segments, and chlorophyll abnormality segments in all sub-band data segments. Then, the proportion of each type of abnormal segment in the total sub-band data segment is determined by a weighted calculation method, and the importance of different band intervals to plant health diagnosis is considered. Finally, based on the proportion results and the band distribution characteristics of the abnormal segment, comprehensive growth abnormality feature data containing detailed band deviation types (such as water abnormality, chlorophyll abnormality, nutrient deficiency, etc.) and precise intensity information (such as mild abnormality, moderate abnormality, severe abnormality) is generated. This data not only contains quantitative indicators of the degree of abnormality, but also provides diagnostic information on the type of abnormality, providing a scientific basis and decision-making support for subsequent plant health assessment and precision agricultural management.

[0075] Here is a specific example: In a monitoring project for key protected plant areas in a botanical garden, the system first calls a pre-built database of rare plant abnormal spectra, which contains the spectral feature data of the plant variety under 12 typical abnormal conditions. The reflectance spectrum data collected by the hyperspectral imager is accurately segmented according to the fine band division scheme of the plant variety (a total of 18 characteristic bands). In-depth analysis found that the reflection intensity sequence of the 650-680nm band showed a typical leaf disease change trend (correlation coefficient 0.92) and the mean was 2.3 standard deviations lower than the normal threshold, and the system marked it as a severe first-level deviation segment. Further analysis showed that the reflectance difference between the 680nm and 720nm characteristic bands reached 0.15, exceeding the normal range by 35%, and was confirmed as a severe chlorophyll abnormality segment. The final statistical results showed that 35% of the analyzed bands had first-degree deviations (of which 20% were severe), and 25% of the bands showed abnormal chlorophyll characteristics (of which 15% were severe). The system generated a detailed characteristic report containing the diagnostic conclusion of "severe photosynthesis disorder, immediate foliar nutrient supplementation and fungal control are recommended."

[0076] In summary, through steps 201 to 205, accurate identification of specific abnormalities of different plant varieties is achieved; the reliability of chlorophyll abnormality detection is significantly improved by adopting multi-band collaborative analysis and hierarchical labeling methods; by quantitatively evaluating the degree of abnormality and type distribution characteristics, a scientific decision-making basis is provided for the health diagnosis and precise maintenance of garden plants, which solves the technical difficulties existing in traditional monitoring methods as a whole and greatly improves the intelligence level of garden plant health monitoring.

[0077] In order to solve the problem that existing plant health monitoring methods are difficult to accurately identify abnormal chlorophyll changes and cannot distinguish temporary fluctuations from substantial lesions, a chlorophyll anomaly detection system based on multi-band collaborative analysis has been developed. The system achieves accurate comparison and analysis of reflectance spectrum data by predetermining the chlorophyll characteristic band combination, provides a reliable basis for chlorophyll status assessment for plant health diagnosis, and significantly improves the accuracy of photosynthesis anomaly detection. In some embodiments, step 204 extracts at least two specific sub-band data segments associated with the chlorophyll content data in the reflectance spectrum data from the plant abnormal spectrum database, and determines whether the reflection intensity difference between the at least two specific sub-band data segments exceeds the reflection intensity threshold data to mark them as chlorophyll abnormal segments, including: 301. Preset a first sub-band interval and a second sub-band interval associated with the chlorophyll content data in the reflectance spectrum data in the plant abnormal spectrum database; In step 301, the plant abnormal spectrum database refers to a standardized spectral feature database containing various types of garden plants at different growth stages and different health conditions established through long-term observations; the chlorophyll content data refers to the core physiological parameters reflecting the efficiency of plant photosynthesis obtained through a professional spectral inversion algorithm; the first sub-band interval refers to the wavelength range where the chlorophyll absorption characteristics are most significant, usually in the red light band; the second sub-band interval refers to the near-infrared band range where the chlorophyll reflectance characteristics are most obvious; the reflectance spectrum data refers to a spectral data set collected by a hyperspectral imaging system containing continuous reflectance information of the plant canopy in the visible light to near-infrared band.

[0078] In an embodiment of the present application, first, two first sub-band intervals and second sub-band intervals associated with the chlorophyll content data in the reflectance spectrum data are pre-set in the plant abnormal spectrum database. These two sub-band intervals are characteristic bands specially selected to have a strong correlation with the chlorophyll content data, and their selection basis includes: the first sub-band interval is located in a band range with obvious chlorophyll absorption characteristics, and the second sub-band interval is located in a band range that is sensitive to changes in the internal structure of the leaves. In the database construction stage, a large amount of experimental data is used to verify the correlation coefficients between these two sub-band intervals and changes in chlorophyll content to ensure their reliability as diagnostic indicators of chlorophyll content. At the same time, corresponding parameter settings of the first sub-band interval and the second sub-band interval are established for different plant types, and stored in the plant abnormal spectrum database.

[0079] 302. Extract corresponding two specific sub-band data segments from the plurality of sub-band data segments according to the first sub-band interval and the second sub-band interval; In step 302, the multiple sub-band data segments refer to characteristic wavelength range data sets formed after finely dividing the original hyperspectral data according to the physiological and biochemical characteristics of plants, and each sub-band corresponds to a specific diagnostic value of plant physiological functions; the specific sub-band data segment refers to a key characteristic band data set directly related to chlorophyll diagnosis that is screened out from all sub-bands through professional spectral analysis technology, and these band combinations have clear plant physiological significance and stable diagnostic performance.

[0080] In an embodiment of the present application, first, accurate extraction is performed from the multiple sub-band data segments after the band division processing according to the wavelength range parameters of the first sub-band interval and the second sub-band interval pre-set in step 301. The extraction process adopts a strict wavelength matching algorithm to ensure that the wavelength range of the two specific sub-band data segments extracted is completely consistent with the definition in the plant abnormal spectrum database. For the reflectance spectrum data obtained in each monitoring cycle, the system will perform this extraction process to ensure the temporal continuity of the data. During the extraction process, the data quality will be triple-checked: wavelength range check, signal-to-noise ratio check and continuity check to ensure that the two specific sub-band data segments extracted meet the quality requirements of subsequent analysis.

[0081] 303. Calculate the reflection intensity difference between the two specific sub-band data segments, and determine whether the positive and negative signs of the reflection intensity difference are consistent with the sign direction in the reflection intensity threshold data range; In step 303, the reflection intensity difference refers to the quantitative difference between the reflectance means of two characteristic sub-bands after standardization; the reflection intensity threshold data range refers to the normal fluctuation range of chlorophyll-related band differences established through long-term monitoring of healthy plants; the sign direction refers to the specific physiological meaning represented by the positive and negative difference values, such as negative values ​​usually indicate enhanced chlorophyll absorption characteristics.

[0082] In the embodiment of the present application, the reflection intensity difference of the two specific sub-band data segments extracted in step 302 is first calculated. The calculation process adopts a standardized algorithm: first calculate the reflection intensity mean of all sampling points in the first sub-band interval and the second sub-band interval, and then calculate the difference between the two. Then, the positive and negative signs of the reflection intensity difference are compared with the reflection intensity threshold data range stored in the plant abnormal spectrum database. The standard sign direction of the difference under different growth states is pre-set in the database as a basis for judgment. The system will perform strict sign direction consistency judgment, which is a key step in identifying chlorophyll anomalies. The influence of measurement errors will be considered in the judgment process, and a reasonable fault tolerance range will be set.

[0083] 304. If the positive and negative signs of the reflection intensity difference are consistent with the preset sign direction, and the reflection intensity difference exceeds the upper limit or lower limit of the reflection intensity threshold data, the two specific sub-band data segments are marked as chlorophyll anomaly segments.

[0084] In step 304, the preset symbol direction refers to the typical variation pattern of chlorophyll abnormality summarized by plant pathologists based on a large number of clinical observations; the upper and lower limits refer to the dynamic threshold boundaries set in consideration of seasonal variation factors; and the chlorophyll abnormality segment refers to the spectral data segment that has been confirmed through multiple verifications to have significant chlorophyll metabolism abnormalities.

[0085] In an embodiment of the present application, first, based on the judgment result of step 303, when the positive and negative signs of the reflection intensity difference are consistent with the preset sign direction in the reflection intensity threshold data range, the threshold comparison stage is entered. The system will strictly compare the absolute value of the reflection intensity difference with the upper and lower limits of the reflection intensity threshold data stored in the plant abnormal spectrum database. A dynamic threshold mechanism is used for comparison, taking into account influencing factors such as plant type and growth stage. When the reflection intensity difference exceeds the upper threshold, it is marked as an abnormal increase in chlorophyll content; when it exceeds the lower threshold, it is marked as an abnormal decrease in chlorophyll content. The system will mark two specific sub-band data segments that meet the conditions as chlorophyll abnormality segments and record the abnormality level. The marking process implements a double verification mechanism to ensure the accuracy of the marking results.

[0086] Here is a specific example: In an ecological monitoring project in a forest park, the system conducted a health assessment of the protected southern yew. First, based on the unique spectral characteristics of the tree species, the optimal band division scheme (a total of 22 sub-bands) was called from the database. Then the hyperspectral data collected by the drone was processed to accurately extract the chlorophyll a characteristic absorption band and the near-infrared reflectance platform band. Analysis found that the reflectivity differences of some plants in the monitored area in these two bands were significantly abnormal, which was highly consistent with the magnesium deficiency symptoms found in recent soil tests. The system automatically marked these abnormal areas and generated a detailed diagnostic report, suggesting precise maintenance through a combination of foliar spraying and soil improvement. After the management staff implemented maintenance according to the suggestion, the review data one month later showed that the chlorophyll index had improved significantly.

[0087] In summary, steps 301 to 304 achieve accurate assessment of the photosynthesis status of plants by scientifically selecting chlorophyll characteristic band combinations; the use of difference analysis and double verification mechanisms significantly improves the reliability of chlorophyll anomaly detection; and by establishing a complete labeling and diagnosis process, an objective chlorophyll status assessment basis is provided for plant health management, which effectively solves the shortcomings of traditional methods in identifying chlorophyll anomalies and provides important technical support for the precise maintenance of garden plants.

[0088] In order to solve the problem that traditional plant health monitoring methods are difficult to accurately identify early abnormalities and cannot effectively distinguish local abnormalities from systemic risks, a plant health risk assessment system based on spatiotemporal feature analysis has been developed. The early warning capability and management efficiency of plant health monitoring have been significantly improved. In some embodiments, the artificial intelligence algorithm described in step 103 identifies abnormal areas in the plant canopy according to the continuous change characteristics of the growth abnormality feature data, and verifies the surrounding areas corresponding to the abnormal areas to screen out potential risk areas, including: 401. Calculate the continuous change characteristics of three consecutive time points and the degree of deviation between the current characteristic value and the normal reference value according to the time series of the abnormal growth characteristic data using an artificial intelligence algorithm; In step 401, abnormal growth characteristic data refers to a structured data set obtained through hyperspectral analysis that includes multidimensional physiological indicators such as plant chlorophyll content, water status, and nutrient levels; time series refers to a set of plant growth monitoring data collected continuously at fixed time intervals; continuous change characteristics refer to the change trends and fluctuation characteristics of plant physiological indicators within three consecutive monitoring cycles; normal reference values ​​refer to the dynamic benchmark value range established through long-term observation of healthy plants, taking into account seasonal changes and growth stages; the degree of deviation refers to the significance level of the difference between the current observation value and the normal reference range quantified by statistical analysis methods.

[0089] In the embodiment of the present application, the abnormal growth characteristic data is first arranged according to a time series, and an artificial intelligence algorithm is used to analyze the continuous change characteristics of three consecutive time points. Specifically, it includes: calculating the change rate of the proportion of the deviation segment of each band at each time point, the intensity fluctuation value of the abnormal chlorophyll segment, and the evolution trend of the reflection intensity difference. Then, the characteristic value of the current time point is compared with the normal reference value stored in the plant abnormal spectrum database, and the degree of deviation of the current characteristic value is quantitatively calculated. This process strictly maintains the structural consistency with the abnormal growth characteristic data generated in step 205 to ensure the unified input data standard of the time series analysis. Finally, the analysis results including the continuously changing characteristic parameters and the degree of deviation score are output.

[0090] 402. Marking points whose continuous change characteristics exceed a first threshold and whose deviation degree exceeds a second threshold as abnormal points, and performing spatial clustering on the abnormal points to form abnormal areas in the plant canopy; In step 402, the continuous change feature exceeding the first threshold means that the change trend of the plant physiological index reaches the preset significance level, indicating that there is a risk of continued deterioration; the degree of deviation exceeds the second threshold means that the current observation value exceeds the normal reference range to the extent that it reaches the warning standard; the abnormal point refers to the spatial location coordinates confirmed by dual condition verification to have health problems; spatial clustering refers to aggregating adjacent abnormal points in spatial distribution into continuous abnormal areas with clear boundaries based on density and distance algorithms.

[0091] In the embodiment of the present application, the first threshold is first set to determine the significance of the continuous change feature, and the second threshold is set to determine the severity of the deviation. The system scans all monitoring points, and when the continuous change feature of a certain point exceeds the first threshold and the degree of deviation exceeds the second threshold, the point is marked as an abnormal point. Then a spatial clustering algorithm is used to perform aggregation analysis on all abnormal points, and the marking rules of the first-level deviation segment and the second-level deviation segment in step 203 are kept consistent during the clustering process. For each abnormal area formed, its spatial range, the number of abnormal points and the average degree of deviation are recorded, and these parameters are directly derived from the calculation results of step 401.

[0092] 403. Expand the abnormal area by a preset distance to form an annular verification zone, and count the proportion of abnormal points in the annular verification zone. When the proportion exceeds the verification threshold, it is determined to be a valid abnormal area. In step 403, the annular verification zone refers to a circular buffer zone formed by taking the boundary of the abnormal area as a reference and expanding outward in consideration of the law of plant disease transmission; the proportion of abnormal points refers to the proportion of the number of points determined to be abnormal within the verification zone to the total number of points in the area; the verification threshold refers to the critical value for abnormal spread determination based on historical data analysis; the effective abnormal area refers to the range of the abnormal area that has been verified to have a risk of spread through the surrounding environment.

[0093] In the embodiment of the present application, first, the boundary of the abnormal area determined in step 402 is used as a reference, and a preset distance is expanded outward to form an annular verification zone. The preset distance is set according to the characteristics of the plant canopy, and is usually 1.2 times the average radius of the abnormal area. Then, the abnormal characteristics of all points within the verification zone are counted, and the proportion of the number of points marked as abnormal points is calculated. When the proportion exceeds the preset verification threshold, the original abnormal area is determined to be a valid abnormal area. The abnormal point marking standard in step 402 is strictly adopted during the judgment process to ensure the consistency of the verification logic.

[0094] 404. Calculate a risk index according to the anomaly intensity of the core area of ​​the effective anomaly area, the anomaly diffusion degree of the verification zone, and the deterioration trend in the time series, and screen out areas where the risk index exceeds the warning value as potential risk areas.

[0095] In step 404, the abnormal intensity of the core area refers to the quantitative value of the health risk level inside the abnormal area obtained by fusion calculation of multiple indicators; the abnormal diffusion degree of the verification zone refers to the spatial gradient characteristics of the spread of abnormal characteristics to the surrounding areas; the deterioration trend refers to the accelerated development trend of abnormal characteristics in the time dimension; the risk index is a comprehensive risk assessment value obtained by weighted fusion calculation of multi-dimensional indicators; the warning value is the risk warning trigger threshold dynamically adjusted according to the characteristics of the plant variety and the growth stage.

[0096] In the embodiment of the present application, firstly, based on the effective abnormal area confirmed in step 403, three core indicators are calculated: the abnormal intensity of the core area (taken from the deviation degree data of step 401); the abnormal diffusion degree of the verification zone (calculated according to the verification result of step 403); the deterioration trend in the time series (from the continuous change characteristic analysis of step 401). Then, the comprehensive risk index is calculated according to the preset formula, and the weight coefficient in the formula matches the historical cases in the plant abnormal spectrum database. Finally, the area with a risk index exceeding the warning value is screened out as a potential risk area. The warning value is dynamically adjusted according to the plant variety and growth stage to ensure the accuracy of the early warning.

[0097] Here is a specific example: In the monitoring of the subtropical plant area of ​​a large botanical garden, the system found yellowing leaves in the banyan community through three consecutive weeks of monitoring. Analysis shows that the reflectivity of the 680nm band continues to rise, and the moisture index has a clear downward trend (step 401). Spatial analysis identified two abnormal clusters, among which the abnormality in the east of the main scenic area was the most significant (step 402). Peripheral verification of the area found that 25% of the plants within 50 meters to the northwest had early symptoms (step 403). Comprehensively evaluating the high intensity of the core abnormality in the area, the fast diffusion speed, and the high temperature and high humidity season, the system determined it to be a high-risk area (step 404). The garden immediately took isolation and prevention measures based on the early warning information, and a re-examination two weeks later showed that the disease was effectively controlled.

[0098] In summary, steps 401 to 404 achieve early and accurate identification and risk assessment of plant health anomalies by building a spatiotemporal multidimensional feature analysis system; the technical route of combining spatial clustering with surrounding environment verification significantly improves the accuracy and reliability of risk area detection; and a dynamic risk assessment model is established to provide a scientific basis for garden maintenance decision-making. This method effectively solves the problems of traditional monitoring methods in early identification of anomalies, risk assessment accuracy, and warning timeliness, provides key technical support for the digital transformation of plant health management, and has important application value for improving garden maintenance and protecting plant resources.

[0099] In order to solve the problem that it is difficult to accurately predict the abnormal diffusion trend and lack of historical experience reference in existing plant health monitoring, a risk prediction system based on historical case matching has been developed. It provides an objective and reliable reference basis for risk prediction, significantly improves the accuracy and scientificity of the abnormal diffusion trend prediction, and provides important support for accurate decision-making in garden maintenance. In some embodiments, the spatial distribution density of the potential risk area described in step 104 is matched with the evolution process data corresponding to the historical abnormal cases stored in the plant abnormal spectrum database to obtain a matching result, including: 501. Extracting evolution process data corresponding to each historical abnormal case from the plant abnormal spectrum database, the evolution process data including initial abnormal density distribution, density change trend of each evolution stage and corresponding environmental parameter change curve; In step 501, the plant abnormal spectrum database refers to a professional database system that contains complete records of various plant abnormal events through long-term monitoring accumulation; historical abnormal cases refer to typical plant health abnormal events that have been verified and fully recorded by experts, including diseases, insect pests, physiological disorders and other types; evolution process data refers to a complete spatiotemporal record data set of abnormal events from the initial occurrence to the final resolution; initial abnormal density distribution refers to the spatial distribution density and morphological characteristics when the abnormality is first detected; density change trend refers to the area expansion speed and spatial distribution change law of the abnormal area in the subsequent development process; environmental parameter change curve refers to the microenvironment monitoring data recorded synchronously with the abnormal development process, including continuous change indicators such as temperature, humidity, light intensity, and soil parameters.

[0100] In an embodiment of the present application, the evolution process data corresponding to each historical abnormal case is first extracted from the plant abnormal spectrum database. The specific extraction content includes the abnormal density distribution map of the initial stage of each case, which contains the spatial density value and distribution characteristics of the abnormal point. At the same time, the density change trend data of each time node in the evolution process of the case are extracted. These data record the expansion rate of the abnormal area and the core density fluctuation. The environmental parameter change curve corresponding to the case is also extracted, including the time series record of parameters such as temperature, humidity and light. During the extraction process, the data field is strictly kept consistent with the original storage structure of the database to ensure the integrity and accuracy of the evolution process data. All extracted data are converted into a unified space-time coordinate system to establish a standardized data foundation for subsequent comparison and analysis.

[0101] 502. Perform a multi-dimensional comparison between the density distribution map of the potential risk area and the evolution process data of each historical case to determine an initial matching coefficient, and mark the historical case whose initial matching coefficient exceeds a preset reference value as a candidate case; perform phased matching between the risk area characteristics of the candidate case and the evolution process data corresponding to the historical case to calculate the evolution matching degree of the candidate case; In step 502, the potential risk area refers to a set of abnormal areas with diffusion risks confirmed through previous analysis; the density distribution map refers to a rasterized thematic map reflecting the distribution density of abnormal points generated by a spatial interpolation algorithm; the multi-dimensional comparison refers to a comprehensive similarity assessment from multiple independent dimensions such as spatial morphological characteristics, time evolution laws, and environmental response characteristics; the evolution matching degree refers to the overall similarity between the current risk status and historical cases quantified by a mathematical model, which is a standardized score value between 0 and 1.

[0102] In an embodiment of the present application, first, the evolution process data corresponding to each historical abnormal case is extracted from the plant abnormal spectrum database. These data include the initial abnormal density distribution, the density change trend of each evolution stage, and the corresponding environmental parameter change curve. The density distribution map of the currently identified potential risk area is compared with the evolution process data in the historical case. This step involves data comparison in multiple dimensions, such as density distribution pattern, density change rate and direction, and changes in environmental parameters (such as temperature, humidity, etc.). Based on the results of the above multi-dimensional comparison, an initial matching coefficient is calculated for each historical case. This coefficient reflects the similarity or matching degree between the current potential risk area and the historical case in each dimension. A preset benchmark value is set, and those historical cases whose initial matching coefficients exceed this benchmark value are marked as candidate cases. This means that only when the similarity between a historical case and the current potential risk area is high enough will it be further considered.

[0103] Secondly, for each candidate case, its risk area characteristics are analyzed in depth and matched in detail with the data of the historical case at different evolution stages. This includes evaluating the risk diffusion pattern in different periods, changes in the affected scope, and other relevant factors. According to the different development stages of the historical case, it is compared with the current potential risk area stage by stage. The purpose of this is to better understand the possible development trajectory of the potential risk area and its potential impact scale. Based on the results of the above stage matching, an evolution matching degree is calculated for each candidate case. This metric comprehensively considers the similarities and differences in the development of risk areas over time, and provides a basis for predicting future development trends.

[0104] Through these two steps, historical data can be effectively used to predict and evaluate the risk level of current garden plants, thus providing a scientific basis for taking timely and effective early warning and management measures. This method not only improves the accuracy of risk management, but also provides support for the rational allocation of resources.

[0105] 503. Taking the evolution matching degree of the candidate case as the matching result.

[0106] In step 503, candidate cases refer to a collection of historical abnormal cases with reference value obtained through preliminary screening and similarity calculation; the evolutionary matching degree refers to the comprehensive similarity score obtained through standardization and weighted calculation; the matching result refers to the professional report finally output by the system containing the best matching case and its detailed similarity analysis.

[0107] In the embodiment of the present application, the evolution matching degrees of each historical case calculated in step 502 are first sorted, and the cases whose matching degrees exceed the preset threshold are screened as candidate cases. The preset threshold is set by default, and then the candidate cases are verified twice to check the matching of the key turning points in the evolution process data with the current potential risk areas. Verify whether the phase difference of the environmental parameter change curve is within the allowable range. Finally, the candidate cases that have passed the verification and their evolution matching degrees are output as the formal matching results. The result maintains the field correspondence with the plant abnormal spectrum database, contains the complete case number, matching score and key matching feature description, and provides a reliable basis for subsequent early warning analysis.

[0108] Here is a specific example: In a pine forest health monitoring project in a scenic spot, the system detected abnormal yellowing of needles in many pine trees. Through historical case matching analysis, the system first screened out 15 qualified pine tree abnormal cases from the database (step 501). After detailed comparison, it was found that the current abnormal distribution was highly consistent with the initial characteristics of pine wilt disease five years ago, with the spatial distribution morphological similarity reaching a "very high" level, the environmental response characteristic similarity being "high", and the comprehensive matching ranking first (step 502). The system automatically generated an early warning report, indicating that the disease may spread to neighboring areas within the next month under similar meteorological conditions. Based on the prediction, the scenic area management department deployed prevention and control measures in advance, including setting up isolation belts and targeted drug treatment, and successfully controlled the disease in the initial occurrence area (step 503).

[0109] In summary, steps 501 to 503 achieve scientific prediction and risk assessment of abnormal development of plant health by establishing a complete historical case matching mechanism; adopt a multi-dimensional, multi-indicator comprehensive similarity evaluation system to significantly improve the accuracy and reliability of the prediction results; and provide an intuitive and reliable reference for garden maintenance decisions through intelligent matching result analysis and visualization. This technology effectively solves the problem of insufficient experience and strong subjectivity of traditional monitoring methods in predicting abnormal development trends, realizes the transformation from passive response to active prevention, greatly improves the scientific level of plant health management and risk prevention and control capabilities, and has important application value for protecting rare plant resources and maintaining ecological security.

[0110] In order to solve the problem that it is difficult to accurately identify the type of abnormality and quantify the severity of abnormalities in existing plant health monitoring, a plant abnormality grading and marking system based on multi-dimensional spectral analysis has been developed. Differentiated identification standards are provided for different types of abnormalities, which significantly improves the accuracy and operability of plant health status assessment and provides a scientific basis for precise maintenance decisions. In some embodiments, the step 203 determines whether the fluctuation direction of the reflection intensity sequence of each sub-band data segment is consistent with the preset direction of the spectral change characteristic curve, and compares whether the mean of the reflection intensity data of each sub-band data segment exceeds the upper or lower limit of the reflection intensity threshold data to mark it as a first-level deviation segment or a second-level deviation segment, including: 601. Obtain reflection intensity sequences of the plurality of sub-band data segments within corresponding band intervals, extract changes of adjacent data points in the reflection intensity sequence, and calculate a distribution ratio of positive and negative signs of the changes; In step 601, the sub-band data segment refers to a characteristic wavelength interval data set formed after the original hyperspectral data is scientifically divided according to the physiological characteristics of the plant, and each sub-band corresponds to a specific physiological diagnostic function; the band interval refers to a continuous wavelength range segment divided in the visible light to near-infrared spectrum, and its width is determined according to the spectral response characteristics of the plant variety; the reflection intensity sequence refers to a series of continuous reflectance measurement values ​​arranged in wavelength order within a specific sub-band interval; the change refers to the difference in reflectance values ​​of adjacent wavelength points in the reflection intensity sequence, reflecting the local change characteristics of the spectral curve; the positive and negative sign distribution ratio refers to the ratio of the number of positive and negative reflectance changes in the specific sub-band interval to the total change, which is used to quantify the overall change trend of the spectral curve.

[0111] In an embodiment of the present application, firstly, a reflection intensity sequence of the plurality of sub-band data segments in the corresponding band interval is obtained, and the sequence contains continuous reflection intensity data points arranged in order of wavelength. Adjacent data point differential calculation is performed on each sub-band data segment, and the change in reflection intensity between every two adjacent data points is extracted. Then, the distribution of positive and negative signs of all changes is counted, and the quantitative ratio of positive changes to negative changes is calculated. The ratio calculation process adopts a sliding window method, and the window size is dynamically adjusted according to the length of the band interval to ensure the representativeness of the statistical results. Finally, the positive and negative sign distribution ratio value of each sub-band data segment is output as the basic data for directional consistency judgment.

[0112] 602. Compare the positive and negative sign distribution ratio with the preset allowable direction range in the spectral change characteristic curve, and determine that the directions are inconsistent when the positive and negative sign distribution ratio exceeds the allowable direction range, otherwise determine that the directions are consistent; In step 602, the allowable direction range refers to the reasonable fluctuation range of the reflectance change trend of a specific plant variety under a specific abnormal state recorded in the plant abnormal spectrum database, and this range is obtained through statistical analysis of a large amount of experimental data; directional inconsistency refers to the existence of statistically significant differences between the change trend of the measured reflection intensity sequence and the typical abnormal characteristic pattern recorded in the database; directional consistency refers to the change trend of the measured reflection intensity sequence being consistent with one or more typical abnormal characteristic patterns in the database and within the allowable error range.

[0113] In an embodiment of the present application, the preset allowable direction range parameter in the spectral change characteristic curve is first read from the plant abnormal spectrum database. The parameter defines the normal direction distribution interval of the reflection intensity change under a healthy state. Then, the positive and negative sign distribution ratio calculated in step 601 is strictly compared with the allowable direction range. The comparison process adopts an interval judgment method. When the measured ratio value completely falls outside the allowable direction range, it is judged as inconsistent in direction; when the ratio value falls entirely or partially within the allowable direction range, it is judged as consistent in direction. The system will record the direction consistency judgment results of each sub-band data segment and mark the specific wavelength position that exceeds the allowable range.

[0114] 603. Calculate the reflection intensity averages of the plurality of sub-band data segments, and obtain the upper limit and lower limit of the corresponding band interval in the reflection intensity threshold data; In step 603, the mean reflection intensity refers to the arithmetic mean of the reflectance of all valid wavelength points in the sub-band data segment, representing the overall reflectance level of the band; the upper limit refers to the higher boundary value of the normal distribution range of the reflectance of a specific band established through long-term monitoring of healthy plants; the lower limit refers to the lower boundary value of the normal distribution range of the reflectance of a specific band.

[0115] In an embodiment of the present application, the reflection intensity sequences of the multiple sub-band data segments are firstly averaged, and a weighted average algorithm is used, in which a higher weight is given to the reflection intensity at the center of the band interval. Then, the reflection intensity threshold data is accurately retrieved from the plant abnormal spectrum database to obtain the upper and lower limits of the corresponding band interval. The threshold data is dynamically adjusted according to the plant variety, growth stage and environmental conditions to ensure the applicability of the threshold setting. The system compares the relationship between the reflection intensity mean of each sub-band data segment and the corresponding threshold interval, and records the specific band position and excess amplitude that exceed the threshold.

[0116] 604. When the fluctuation direction is consistent with the preset direction and the mean value exceeds the upper limit or the lower limit, it is marked as a first-level deviation segment; when the fluctuation direction is inconsistent with the preset direction and the mean value exceeds the upper limit or the lower limit, it is marked as a second-level deviation segment.

[0117] In step 604, the first-level deviation segment refers to a significant anomaly that satisfies the following two conditions at the same time: the fluctuation direction of the reflection intensity sequence is consistent with a typical abnormal characteristic pattern in the database; the mean reflection intensity significantly exceeds the normal threshold range; the second-level deviation segment refers to a potential anomaly that satisfies the following conditions: the mean reflection intensity exceeds the normal threshold range, but the fluctuation direction is inconsistent with the typical abnormal characteristic pattern.

[0118] In the embodiment of the present application, the direction consistency determination result of step 602 and the threshold comparison result of step 603 are first integrated to perform a hierarchical marking operation. When a sub-band data segment satisfies two conditions at the same time: the fluctuation direction is consistent with the preset direction and the mean reflection intensity exceeds the upper limit or lower limit, the sub-band data segment is marked as a first-level deviation segment. When the fluctuation direction is inconsistent with the preset direction but the mean reflection intensity still exceeds the threshold, it is marked as a second-level deviation segment. The marking process adopts a double verification mechanism, and the boundary conditions will be reviewed with reference to the analysis results of adjacent bands. Finally, a complete report containing the deviation marks of all sub-band data segments is generated, in which the first-level deviation segments and the second-level deviation segments are distinguished by different identifiers to provide standardized input for subsequent comprehensive analysis.

[0119] Here is a specific example: In an ecological monitoring project in a forest park, the system conducted a health assessment of red pine forests in key protected areas. When analyzing the spectral data of red pine in a certain area, the system first detected a significant upward trend in the reflection intensity sequence in the 690-710nm band (step 601). After comparison with the database, the change direction was highly consistent with the initial characteristics of pine needle rust (step 602). The mean reflection intensity of this band was significantly higher than the normal upper limit of healthy red pine in this season (step 603). The system marked it as a first-level deviation segment and diagnosed it as "early infection of pine needle rust" (step 604). Based on the diagnosis results, the management staff implemented preventive spraying of low-concentration agents, which effectively controlled the development of the disease. The review data two weeks later showed that the spectral characteristics of red pine in the area had returned to the normal range.

[0120] In summary, steps 601 to 603 achieve accurate identification and classification evaluation of plant health anomalies by establishing a scientific and complete spectral anomaly classification and labeling system; the technical route of combining directional feature analysis with threshold deviation detection significantly improves the accuracy and reliability of abnormal diagnosis; and by establishing standardized abnormal classification standards, a scientific basis is provided for differentiated and precise plant health management. This method effectively solves the technical bottlenecks of traditional monitoring methods in early abnormal identification, type differentiation, and degree evaluation, greatly improves the intelligent level and decision-making support capabilities of plant health monitoring, and provides important technical support for the digital transformation of garden maintenance and the scientific protection of plant resources.

[0121] In order to solve the problem that existing plant health risk warning methods are difficult to accurately predict abnormal diffusion trends and cannot dynamically adjust warning levels, a risk warning grading system based on multi-factor coupling analysis has been developed. The risk level distribution of different regions is intuitively presented, which provides decision support for precise prevention and control, and significantly improves the accuracy and timeliness of garden plant health risk warnings. In some embodiments, the diffusion probability of the potential risk area under the local climate environment is corrected based on the matching results in step 105 to generate a risk distribution map containing multiple warning levels, including: 701. Based on the matching result, the diffusion probability of the potential risk area under the local climate environment is corrected, and according to the comparison relationship between the corrected diffusion probability and the preset risk threshold, three warning levels of high, medium and low are divided, and a risk distribution map corresponding to the warning level is generated.

[0122] In step 701, the matching result refers to the comparison conclusion between the current potential risk area and the historical abnormal cases obtained through multi-dimensional similarity evaluation, including core indicators such as spatial distribution morphology similarity and evolution speed matching; the local climate environment specifically refers to the microclimate data set collected in real time in the monitoring area, including key environmental parameters such as temperature, relative humidity, rainfall, wind speed, etc. that directly affect the spread of plant diseases; the diffusion probability is a quantitative value of the possibility of expansion of the abnormal area calculated based on historical statistical models and real-time environmental data; the risk threshold is the warning level classification standard determined through expert argumentation and historical data analysis, including three key critical values ​​of high risk threshold, medium risk threshold and low risk threshold; the risk distribution map is a spatial visualization chart generated by geographic information system technology, which uses red, yellow and blue color gradients to identify high, medium and low warning areas respectively, and supports multi-scale display and interactive query functions.

[0123] In the embodiment of the present application, the confidence of the matching results is first evaluated, and historical cases with high confidence are selected as the main reference. Then, a diffusion probability correction model including environmental factors such as temperature and humidity is established, and the influence weight of each factor is quantified through multivariate regression analysis. Then, according to the current real-time environmental monitoring data, the environmental correction coefficient is calculated to adjust the basic diffusion probability. The corrected diffusion probability is then compared with the preset risk threshold, and the final warning level is determined by a fuzzy comprehensive evaluation method. Finally, spatial interpolation technology is used to generate a continuous risk distribution map, and different risk areas are highlighted through visual rendering. The entire analysis process uses a sliding time window technology to achieve dynamic updating of risk warnings.

[0124] Here is a specific example: In the lotus disease monitoring in a wetland park, the system found that the current abnormal regional distribution matched the "lotus leaf brown spot disease" in the historical case library by 85%. Combined with the current high temperature and high humidity environment (temperature 32°C, humidity 85%), the system corrected the basic diffusion probability. According to the preset threshold (high risk > 70%, medium risk 40-70%, low risk < 40%), the area is marked as a high-risk area. The generated risk distribution map clearly shows: the core area is a red warning, the surrounding 50-meter buffer zone is a yellow warning, and the outer area is a blue warning. Based on the warning map, the management personnel implemented graded prevention and control, focusing on high-risk areas. A review one week later showed that the spread of the disease was effectively curbed.

[0125] In summary, step 701 achieves scientific quantitative assessment of plant health risks by establishing a dynamic probability correction model; adopts a three-level early warning mechanism to significantly improve the rationality and operability of risk classification; and provides an intuitive decision-making basis for precise prevention and control through spatial visualization. This technology effectively solves the shortcomings of traditional methods in terms of risk prediction accuracy, early warning timeliness, and prevention and control targeting, realizes the transformation from passive response to active prevention, and provides key technical support for the digital transformation of garden plant health management.

[0126] Figure 2 A schematic diagram of a risk classification and early warning system for garden plants based on artificial intelligence is provided for the present application embodiment. Figure 2 As shown, the system includes: The acquisition module 21 is used to collect images of the target plant coverage area through a drone cluster deployed in the garden area to obtain reflectance spectrum data of the plant canopy; A generating module 22 is used to analyze the chlorophyll content data in the reflectance spectrum data based on the spectral change characteristic curves and reflectance intensity threshold data corresponding to different plant types under abnormal growth conditions through a pre-constructed plant abnormal spectrum database to generate abnormal growth characteristic data; A screening module 23, for identifying abnormal areas in the plant canopy according to the continuous change characteristics of the abnormal growth characteristic data based on an artificial intelligence algorithm, and verifying the surrounding areas corresponding to the abnormal areas to screen out potential risk areas; The correction module 24 is further used to match the spatial distribution density of the potential risk area with the evolution process data corresponding to the historical abnormal cases stored in the plant abnormal spectrum database, and to correct the diffusion probability of the potential risk area under the local climate environment based on the matching result to generate a risk distribution map containing multiple warning levels; The output module 25 is used to output treatment suggestion plans matching each warning level according to the risk distribution map.

[0127] Figure 2 The artificial intelligence-based garden plant risk classification early warning system can be implemented Figure 1 The implementation principle and technical effect of the artificial intelligence-based risk classification and early warning method for garden plants described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the artificial intelligence-based risk classification and early warning system for garden plants in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0128] In one possible design, Figure 2 The artificial intelligence-based risk classification and early warning system for garden plants of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0129] The processing component 32 is used for the above Figure 1 The embodiment provides an artificial intelligence-based risk classification and early warning method for garden plants.

[0130] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0131] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0132] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0133] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0134] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0135] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0136] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The illustrated embodiment is an artificial intelligence-based risk classification and early warning method for garden plants.

[0137] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0138] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0139] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0140] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A risk classification and early warning method for garden plants based on artificial intelligence, characterized in that: include: By deploying a drone cluster in the garden area, images of the target plant coverage area are collected to obtain the reflectance spectrum data of the plant canopy; Through the pre-constructed plant abnormal spectrum database, based on the spectral change characteristic curves and reflection intensity threshold data corresponding to different plant types under abnormal growth conditions, the chlorophyll content data in the reflection spectrum data is analyzed to generate growth abnormality characteristic data; Based on the artificial intelligence algorithm, according to the continuous change characteristics of the abnormal growth characteristic data, the abnormal area in the plant canopy is identified, and the surrounding area corresponding to the abnormal area is verified to screen out the potential risk area; Matching the spatial distribution density of the potential risk area with the evolution process data corresponding to the historical abnormal cases stored in the plant abnormal spectrum database, and correcting the diffusion probability of the potential risk area under the local climate environment based on the matching result to generate a risk distribution map containing multiple warning levels; According to the risk distribution map, a processing suggestion plan matching each warning level is output.

2. The method according to claim 1, characterized in that Through the pre-constructed plant abnormal spectrum database, based on the spectral change characteristic curves and reflection intensity threshold data corresponding to different plant types under abnormal growth conditions, the chlorophyll content data in the reflection spectrum data is analyzed to generate growth abnormality characteristic data, including: For each plant type, a plant abnormal spectrum database is pre-built, which includes spectrum change characteristic curves and reflection intensity threshold data in multiple continuous band intervals of the plant type under abnormal growth conditions; The reflectance spectrum data is divided into a plurality of sub-band data segments according to the band interval division rule of the spectrum change characteristic curve in the plant abnormal spectrum database; Determine whether the fluctuation direction of the reflection intensity sequence of each sub-band data segment is consistent with the preset direction of the spectral change characteristic curve, and compare whether the mean value of the reflection intensity data of each sub-band data segment exceeds the upper limit or lower limit of the reflection intensity threshold data, so as to mark it as a primary deviation segment or a secondary deviation segment; Extracting at least two specific sub-band data segments associated with the chlorophyll content data in the reflectance spectrum data from the plant abnormal spectrum database, and determining whether the reflection intensity difference between the at least two specific sub-band data segments exceeds the reflection intensity threshold data, so as to mark them as chlorophyll abnormal segments; According to the proportion of the first-level deviation segments, the second-level deviation segments and the chlorophyll abnormality segments, growth abnormality characteristic data including band deviation type and intensity information are generated.

3. The method according to claim 2, characterized in that Extracting at least two specific sub-band data segments associated with the chlorophyll content data in the reflectance spectrum data from the plant abnormal spectrum database, and determining whether the reflection intensity difference between the at least two specific sub-band data segments exceeds the reflection intensity threshold data to mark them as chlorophyll abnormal segments, including: Presetting a first sub-band interval and a second sub-band interval associated with the chlorophyll content data in the reflectance spectrum data in the plant abnormal spectrum database; Extracting two corresponding specific sub-band data segments from the plurality of sub-band data segments according to the first sub-band interval and the second sub-band interval; Calculating the reflection intensity difference between the two specific sub-band data segments, and determining whether the positive and negative signs of the reflection intensity difference are consistent with the sign direction in the reflection intensity threshold data range; If the positive and negative signs of the reflection intensity difference are consistent with the preset sign direction, and the reflection intensity difference exceeds the upper limit or lower limit of the reflection intensity threshold data, the two specific sub-band data segments are marked as chlorophyll anomaly segments.

4. The method according to claim 1, characterized in that: Based on the artificial intelligence algorithm, according to the continuous change characteristics of the abnormal growth characteristic data, the abnormal area in the plant canopy is identified, and the surrounding area corresponding to the abnormal area is verified to screen out potential risk areas, including: Calculate the continuous change characteristics of three consecutive time points and the degree of deviation between the current characteristic value and the normal reference value according to the time series of the abnormal growth characteristic data using an artificial intelligence algorithm; Marking points whose continuous change characteristics exceed a first threshold and whose deviation degree exceeds a second threshold as abnormal points, and performing spatial clustering on the abnormal points to form abnormal areas in the plant canopy; An annular verification zone is formed by expanding the abnormal area by a preset distance, and the number of abnormal points in the annular verification zone is counted. When the ratio exceeds the verification threshold, it is determined to be a valid abnormal area; The risk index is calculated based on the anomaly intensity of the core area of ​​the effective anomaly area, the anomaly diffusion degree of the verification zone and the deterioration trend in the time series, and the area where the risk index exceeds the warning value is screened out as a potential risk area.

5. The method according to claim 1, characterized in that The spatial distribution density of the potential risk area is matched with the evolution process data corresponding to the historical abnormal cases stored in the plant abnormal spectrum database to obtain a matching result, including: Extracting evolution process data corresponding to each historical abnormal case from the plant abnormal spectrum database, the evolution process data including initial abnormal density distribution, density change trend of each evolution stage and corresponding environmental parameter change curve; Perform multi-dimensional comparison between the density distribution map of the potential risk area and the evolution process data of each historical case to determine the initial matching coefficient, and mark the historical cases whose initial matching coefficient exceeds the preset benchmark value as candidate cases; perform phased matching between the risk area characteristics of the candidate cases and the evolution process data corresponding to the historical cases, and calculate the evolution matching degree of the candidate cases; The evolution matching degree of the candidate case is taken as the matching result.

6. The method according to claim 2, characterized in that Determine whether the fluctuation direction of the reflection intensity sequence of each sub-band data segment is consistent with the preset direction of the spectral change characteristic curve, and compare whether the mean value of the reflection intensity data of each sub-band data segment exceeds the upper limit or lower limit of the reflection intensity threshold data to mark it as a primary deviation segment or a secondary deviation segment, including: Acquire the reflection intensity sequences of the plurality of sub-band data segments within the corresponding band interval, extract the variation of adjacent data points in the reflection intensity sequence, and calculate the distribution ratio of the positive and negative signs of the variation; Comparing the positive and negative sign distribution ratio with the preset allowable direction range in the spectral change characteristic curve, and determining that the directions are inconsistent when the positive and negative sign distribution ratio exceeds the allowable direction range, otherwise determining that the directions are consistent; Calculate the reflection intensity averages of the plurality of sub-band data segments, and obtain the upper limit and lower limit of the corresponding band interval in the reflection intensity threshold data; When the fluctuation direction is consistent with the preset direction and the mean exceeds the upper limit or lower limit, it is marked as a first-level deviation segment. When the fluctuation direction is inconsistent with the preset direction and the mean exceeds the upper limit or lower limit, it is marked as a second-level deviation segment.

7. The method according to claim 1, characterized in that The diffusion probability of the potential risk area under the local climate environment is corrected based on the matching result to generate a risk distribution map containing multiple warning levels, including: Based on the matching results, the diffusion probability of the potential risk area under the local climate environment is corrected. According to the comparison relationship between the corrected diffusion probability and the preset risk threshold, three warning levels of high, medium and low are divided, and a risk distribution map corresponding to the warning level is generated.

8. An artificial intelligence-based risk classification and early warning system for garden plants, characterized in that: include: An acquisition module is used to collect images of the target plant coverage area through a drone cluster deployed in the garden area to obtain reflectance spectrum data of the plant canopy; A generation module is used to analyze the chlorophyll content data in the reflectance spectrum data based on the spectral change characteristic curves and reflection intensity threshold data corresponding to different plant types under abnormal growth conditions through a pre-constructed plant abnormal spectrum database to generate abnormal growth characteristic data; A screening module, for identifying abnormal areas in the plant canopy based on the continuous change characteristics of the abnormal growth characteristic data based on an artificial intelligence algorithm, and verifying the surrounding areas corresponding to the abnormal areas to screen out potential risk areas; A correction module matches the spatial distribution density of the potential risk area with the evolution process data corresponding to the historical abnormal cases stored in the plant abnormal spectrum database, and corrects the diffusion probability of the potential risk area under the local climate environment based on the matching result to generate a risk distribution map containing multiple warning levels; The output module is used to output processing suggestions matching each warning level according to the risk distribution map.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an artificial intelligence-based garden plant risk grading and early warning method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, an artificial intelligence-based garden plant risk grading and early warning method as described in any one of claims 1 to 7 is implemented.

Images