Method and device for predicting plant diseases and insect pests in forsythia suspensa planting period and medium

Abstract

The invention provides a pest and disease damage prediction method and device in the forsythia suspensa planting period and a medium, and relates to the technical field of pest and disease damage prediction in the forsythia suspensa planting period, and the method comprises the steps: determining a plurality of target environment influence factors corresponding to QA; constructing an environmental influence factor feature vector XL1 corresponding to the diseased forsythia suspensa planting area and an environmental influence factor feature vector XL2 corresponding to the forsythia suspensa planting area to be predicted; obtaining a first similarity eta1 between the XL1 and the XL2; obtaining an environmental influence factor sensitivity list alpha corresponding to the forsythia suspensa variety planted in the diseased forsythia suspensa planting area and an environmental influence factor sensitivity list beta corresponding to the forsythia suspensa variety planted in the to-be-predicted forsythia suspensa planting area; determining a first similarity eta1 between the XL1 and the XL2; if eta < 1 > is greater than or equal to gamma < 1 >, determining that the forsythia suspensa in the forsythia suspensa planting area to be predicted can have diseases and insect pests with the disease and insect pest type of QA; according to the invention, the precision and reliability of fructus forsythiae pest and disease prediction can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of disease and insect pest prediction during the planting period of Forsythia suspensa, and in particular to a disease and insect pest prediction method, equipment and medium during the planting period of Forsythia suspensa. Background Art

[0002] In the process of Forsythia cultivation, accurate prediction of pests and diseases is crucial to ensuring yield. Existing pest and disease prediction methods are usually based on the analysis of a single environmental factor or a unified variety characteristic, and do not fully consider the differences in sensitivity of different Forsythia varieties to environmental factors, resulting in deviations between the prediction results and the actual situation. For example, when dealing with the prediction of pests and diseases in different planting areas, traditional technologies often ignore the variety differences between the diseased area and the area to be predicted, and use the same environmental factor weights to construct feature vectors, which cannot accurately reflect the response differences between different varieties under the same environmental conditions; at the same time, the existing scheme lacks a dynamic weight association mechanism for variety sensitivity and environmental factor characteristic values, making it difficult to accurately quantify the degree of influence of environmental factors when the varieties are different, resulting in distortion of the similarity calculation results, which in turn affects the accuracy and reliability of pest and disease prediction. Therefore, how to combine the differences in the sensitivity of Forsythia varieties to environmental factors, construct a more adaptable feature vector weight system, and improve the accuracy of pest and disease prediction in different variety planting areas has become a technical problem that needs to be solved urgently in this field. Summary of the Invention

[0003] In view of the above technical problems, the technical solution adopted by the present invention is: According to a first aspect of the present application, a method for predicting pests and diseases during the planting period of Forsythia suspensa is provided, the method comprising the following steps: S100, based on the QA of the types of diseases and insect pests of Forsythia suspensa in the diseased Forsythia suspensa planting area, determine several target environmental influencing factors corresponding to the QA.

[0004] S200, obtaining the average target environmental impact factor value corresponding to each target environmental impact factor in the diseased Forsythia suspensa planting area and the Forsythia suspensa planting area to be predicted within a preset historical time period, so as to construct the environmental impact factor characteristic vector XL1 corresponding to the diseased Forsythia suspensa planting area and the environmental impact factor characteristic vector XL2 corresponding to the Forsythia suspensa planting area to be predicted.

[0005] S300: If the Forsythia suspensa variety planted in the diseased Forsythia suspensa planting area and the Forsythia suspensa planting area to be predicted is the same, a first similarity η1 between XL1 and XL2 is obtained.

[0006] S400: If the Forsythia suspensa varieties planted in the diseased Forsythia suspensa planting area and the Forsythia suspensa planting area to be predicted are different, obtain a sensitivity list α of environmental influencing factors corresponding to the Forsythia suspensa varieties planted in the diseased Forsythia suspensa planting area and a sensitivity list β of environmental influencing factors corresponding to the Forsythia suspensa varieties planted in the Forsythia suspensa planting area to be predicted.

[0007] S500 , determining the weight corresponding to each eigenvalue in XL1 and XL2 based on α and β.

[0008] S600 , determining a first similarity η1 between XL1 and XL2 according to the weight corresponding to each eigenvalue in XL1 and XL2 .

[0009] S700, if η1≥γ1, it is determined that the Forsythia suspensa in the predicted Forsythia suspensa planting area will be susceptible to pests and diseases of the QA type; otherwise, it is determined that the Forsythia suspensa in the predicted Forsythia suspensa planting area will not be susceptible to pests and diseases of the QA type; γ1 is a preset first similarity threshold.

[0010] According to another aspect of the present application, a non-transitory computer-readable storage medium is also provided, in which at least one instruction or at least one program is stored. The at least one instruction or at least one program is loaded and executed by a processor to implement the above-mentioned method for predicting pests and diseases during the Forsythia suspensa planting period.

[0011] According to another aspect of the present application, an electronic device is provided, including a processor and the above-mentioned non-transitory computer-readable storage medium.

[0012] The present invention has at least the following beneficial effects: The method for predicting pests and diseases during the planting period of Forsythia suspensa of the present invention, first, dynamically adjusts the characteristic vector weights according to the sensitivity lists α and β of environmental influencing factors of different varieties, so that the weight distribution of the environmental influencing factor characteristic vector XL1 corresponding to the diseased Forsythia suspensa planting area and the environmental influencing factor characteristic vector XL2 corresponding to the Forsythia suspensa planting area to be predicted can accurately reflect the interaction between the Forsythia suspensa variety and the environmental factors, avoiding the traditional unified weight that ignores the variety specificity; secondly, through the sensitivity-driven weight determination mechanism, the quantitative characterization of the response differences of different varieties under the same environmental conditions is realized, and the problem of characteristic vector characterization distortion caused by variety differences is solved; in addition, by combining the weight to calculate the characteristic vector similarity, the environmental matching degree between the area to be predicted and the diseased area can be more accurately measured, thereby improving the accuracy and reliability of pest and disease prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0014] Figure 1 This is a flow chart of a method for predicting pests and diseases during the Forsythia suspensa planting period provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0015] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0016] It should be noted that, based on this disclosure, those skilled in the art will appreciate that an aspect described herein can be implemented independently of any other aspect, and that two or more of these aspects can be combined in various ways. For example, any number of the aspects described herein can be used to implement an apparatus and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement such an apparatus and / or practice such a method.

[0017] The following will refer to Figure 1 The flowchart of the method for predicting pests and diseases during the planting period of Forsythia suspensa is shown, which introduces a method for predicting pests and diseases during the planting period of Forsythia suspensa.

[0018] The method for predicting diseases and insect pests during the planting period of Forsythia suspensa may comprise the following steps: S100, based on the QA of the types of diseases and insect pests of Forsythia suspensa in the diseased Forsythia suspensa planting area, determine several target environmental influencing factors corresponding to the QA.

[0019] Furthermore, target environmental factors include: temperature, humidity, rainfall, soil pH, altitude, daylight hours, and slope.

[0020] In this embodiment, there are several Forsythia suspensa planting areas, each of which is distributed in a different geographical area, and any two Forsythia suspensa planting areas are far apart; when Forsythia suspensa in any Forsythia suspensa planting area suffers from diseases and pests, the types of diseases and pests that occur can be obtained, such as fungal diseases, bacterial diseases, insect pests, etc.; different types of diseases and pests correspond to several target environmental influencing factors; for example, fungal diseases (such as Forsythia suspensa leaf spot) are usually prone to break out in high humidity (relative humidity > 80%) and warm (20-28°C) environments, and the corresponding target environmental influencing factors are temperature and humidity; aphid pests often reproduce faster under high temperature and drought conditions (temperature > 25°C, rainfall < 50mm / month), and the corresponding target environmental influencing factors are temperature and rainfall; by analyzing historical data during the Forsythia suspensa production process, a mapping relationship between each type of disease and pest and the corresponding target environmental influencing factor can be obtained.

[0021] For example, historical pest and disease data (such as onset time and severity) can be collected from forsythia cultivation areas, while simultaneously recording environmental data (such as temperature, humidity, and rainfall) for the corresponding time period. Correlation analysis (such as the Pearson correlation coefficient) can be used to calculate the correlation between environmental factors and pest and disease occurrence, screening factors with correlation coefficients greater than 0.5 as candidates. Machine learning methods (such as random forests and XGBoost) can be used to assess the characteristic importance of each environmental factor and identify target influencing factors. For example, it was found that daylight duration has a higher impact on forsythia rust than soil pH.

[0022] S200, obtaining the average target environmental impact factor value corresponding to each target environmental impact factor in the diseased Forsythia suspensa planting area and the Forsythia suspensa planting area to be predicted within a preset historical time period, so as to construct the environmental impact factor characteristic vector XL1 corresponding to the diseased Forsythia suspensa planting area and the environmental impact factor characteristic vector XL2 corresponding to the Forsythia suspensa planting area to be predicted.

[0023] In this embodiment, the average target environmental influencing factor values, such as temperature and humidity, corresponding to each target environmental influencing factor in the diseased area and the area to be predicted over a historical period, such as the past six months, can be obtained and then normalized to obtain feature vectors XL1 and XL2. It should be noted that those skilled in the art can use existing normalization methods to normalize each average target environmental influencing factor value as needed, and this will not be elaborated upon here.

[0024] Through this step, environmental characteristics are quantified to provide a data basis for similarity calculation, solving the problem of lack of structured representation of environmental data in traditional methods.

[0025] S300: If the Forsythia suspensa variety planted in the diseased Forsythia suspensa planting area and the Forsythia suspensa planting area to be predicted is the same, a first similarity η1 between XL1 and XL2 is obtained.

[0026] In this embodiment, it can be understood that Forsythia suspensa is divided into several varieties, and different Forsythia suspensa varieties are affected to different degrees by the same environmental factors. Therefore, for the case where the Forsythia suspensa varieties planted in the diseased Forsythia suspensa planting area and the Forsythia suspensa planting area to be predicted are the same, the first similarity η1 between XL1 and XL2 can be directly obtained.

[0027] S400: If the Forsythia suspensa varieties planted in the diseased Forsythia suspensa planting area and the Forsythia suspensa planting area to be predicted are different, obtain a sensitivity list α of environmental influencing factors corresponding to the Forsythia suspensa varieties planted in the diseased Forsythia suspensa planting area and a sensitivity list β of environmental influencing factors corresponding to the Forsythia suspensa varieties planted in the Forsythia suspensa planting area to be predicted.

[0028] In this embodiment, it can be understood that different Forsythia suspensa varieties have different sensitivities to the same environmental factor. Therefore, if the Forsythia suspensa varieties planted in the diseased Forsythia suspensa planting area and the Forsythia suspensa planting area to be predicted are different, the sensitivity lists α and β of the two varieties to various factors are obtained. For example, α=(0.4, 0.6) indicates that the variety in the diseased area is 0.4 sensitive to temperature and 0.6 sensitive to humidity.

[0029] Sensitivity can be calculated using a sensitivity index (SI). Specifically, the raw data can be standardized, such as using a Z-score. Then, based on a model such as a random forest or neural network, the contribution of each factor to the response indicator is calculated and converted into a dimensionless sensitivity index between 0 and 1, thereby obtaining the sensitivity. It should be noted that those skilled in the art can use existing sensitivity calculation methods to obtain α and β according to actual needs, and this will not be elaborated here.

[0030] This step can distinguish variety specificity, avoid prediction bias caused by uniform weights, and solve the core problem of existing technologies ignoring variety sensitivity differences.

[0031] S500 , determining the weight corresponding to each eigenvalue in XL1 and XL2 based on α and β.

[0032] In this embodiment, feature weights are calculated based on α and β, and then the first similarity η1 between XL1 and XL2 is calculated based on the weights, such as the weighted Euclidean distance, so that the dynamic weights reflect the differences in the responses of varieties to the environment, making the similarity calculation more realistic and improving the prediction accuracy.

[0033] Furthermore, step S500 may include the following steps: S510, obtain α=(α1, α2,…,α i ,…,α n ) and β=(β1, β2,…,β i ,…,β n ), i=1, 2,...,n; where, α i is the sensitivity of the Forsythia suspensa variety planted in the diseased Forsythia suspensa planting area to the i-th target environmental factor, β i is the sensitivity of the Forsythia suspensa variety planted in the Forsythia suspensa planting area to the i-th target environmental influencing factor, n is the number of target environmental influencing factors; SUM (α) = 1, SUM (β) = 1; SUM () is the summation function.

[0034] In this embodiment, the sensitivity data can be obtained using the method in S400, or through laboratory testing, such as disease resistance experiments under different environments, or training with historical planting data, such as feature importance of a machine learning model.

[0035] Normalization ensures that the sensitivity of different factors is comparable, avoids weight bias due to dimensional differences, and converts the differences in variety responses to the environment into calculable vectors, providing a quantitative basis for subsequent weight adjustments.

[0036] S520: Obtain a second similarity η2 between α and β.

[0037] In this embodiment, the Euclidean distance can be used to calculate the similarity η2 between α and β; η2∈[0,1], and a higher value indicates that the sensitivity distributions of the two varieties are more similar.

[0038] η2 can be used to intuitively reflect the differences in responses between varieties to environmental factors and provide a basis for the selection of weighting strategies. When η2 is close to 1, it indicates that the varieties have similar sensitivities and historical weights can be used. When η2 is close to 0, the weights need to be adjusted to accommodate variety differences.

[0039] S530, if η2≥γ2, then determine that the weight of the characteristic value corresponding to the main target environmental influencing factor in XL1 and XL2 is the first preset weight ω1, and the weight of the characteristic value corresponding to the secondary target environmental influencing factor is the second preset weight ω2; wherein, ω1>ω2, ω1+ω2=1; γ2 is the preset second similarity threshold.

[0040] If η2 ≥ γ2, such as γ2 = 0.8, it can be determined that the sensitivities of the two varieties are similar enough, and the preset weights ω1 and ω2 are directly used.

[0041] Furthermore, the value range of ω1 is 0.7 to 0.9.

[0042] The main factor weight ω1∈[0.7,0.9] and the secondary factor weight ω2=1-ω1 ensure that key environmental factors dominate the prediction results.

[0043] In this embodiment, the same variety of Forsythia suspensa is affected by many environmental factors. However, the degree of influence of each environmental factor on the growth of Forsythia suspensa is different, with some factors having a greater impact and some factors having a smaller impact. For example, temperature and humidity are usually the main factors, and soil pH is a secondary factor. The main target environmental factors and secondary target environmental factors can be determined through analysis of variance (ANOVA) or feature importance ranking.

[0044] Furthermore, we can build multiple decision trees and use Gini impurity or the reduction in information gain to evaluate feature importance. The feature importance of all trees is averaged, and features with higher importance contribute more to model predictions.

[0045] For example, a random forest model is constructed with the occurrence of forsythia diseases and insect pests as the target variable and environmental factors such as temperature, humidity, soil nutrients, etc. as feature variables.

[0046] Calculate the average value of the reduction in Gini impurity caused by each feature when splitting the node as the feature importance indicator.

[0047] Sorted by importance, the top 30%-50% of features can be considered as the main influencing factors.

[0048] Through the above steps, a balance between efficiency and accuracy can be achieved. When the differences between varieties are small, reusing preset weights can reduce computing overhead, while using historical experience to ensure prediction accuracy. It can also improve model stability, avoid frequent weight adjustments due to minor differences, and enhance the consistency of prediction results.

[0049] Furthermore, after step S530, the method may further include the following steps: S540: If η2<γ2, obtain the difference between α and β, d=1-η2 / γ2.

[0050] When the second similarity η2 between the environmental factor sensitivity lists α and β of two Forsythia suspensa varieties is less than the second similarity threshold γ2, it indicates that their sensitivities to the environmental factor differ significantly. The difference d is calculated using the formula d = 1 - η2 / γ2, where η2 / γ2 represents the ratio of the current similarity to the threshold, and 1 - η2 / γ2 quantifies the degree of difference. For example, if η2 = 0.5 and γ2 = 0.8, then d = 1 - 0.5 / 0.8 = 0.375, which means the difference is 37.5%.

[0051] This step provides a quantitative basis for subsequent weight adjustments, directly linking weight changes to differences in varietal sensitivity and avoiding subjective judgment. Standardized difference calculations ensure comparability across scenarios, improving model adaptability.

[0052] S541, according to d, adjust ω1=ω1×(1-k×d); where k is a preset adjustment coefficient; 0<k≤1; proceed to S542.

[0053] Based on the degree of difference d, the preset weights ω1 for the primary environmental factors are dynamically adjusted. In the formula, k is the adjustment coefficient (0 < k ≤ 1), which controls the magnitude of the adjustment. As d increases, meaning the difference in sensitivity between varieties grows, the value of (1 - k × d) decreases, and ω1 is compressed more. For example, if ω1 initially equals 0.8, k = 0.5, and d = 0.5, then after adjustment, ω1 equals 0.8 × (1 - 0.5 × 0.5) = 0.6.

[0054] This step can dynamically adapt to variety differences. When the sensitivity of varieties to environmental factors differ significantly, the weight of the main factors can be reduced to avoid prediction bias caused by one-size-fits-all weights. It can also improve the flexibility of the model. By adjusting the k value, the weight adjustment range can be flexibly controlled according to actual planting scenarios, such as variety characteristics and regional environment, to enhance prediction accuracy.

[0055] S542, if ω1≤ω2, set ω1=ω2+ε; where ε is a preset adjustment parameter, 0<ε<0.1.

[0056] If the primary factor weight ω1 is less than or equal to the secondary factor weight ω2 after adjustment, ω1 is forcibly set to ω2 + ε, where ε is a small positive number less than 0.1. For example, if ω1 = 0.4 and ω2 = 0.5 after adjustment, set ω1 = 0.5 + 0.05 = 0.55. Assuming ε = 0.05, ensure that ω1 > ω2.

[0057] This step can maintain the rationality of the weight logic, ensuring that the weight of the main environmental factors is always higher than that of the secondary factors, in line with the basic logic that the main factors have a greater impact on pests and diseases, and avoid the reversal of model parameters; it can also prevent prediction failure. If the weights are reversed, the model may misjudge the secondary factors as key influencing factors. This step ensures the correctness of the prediction logic through the threshold protection mechanism.

[0058] When different varieties have large differences in sensitivity to environmental factors, the model can more accurately reflect the relationship between variety characteristics, environmental factors, and pests and diseases by dynamically adjusting weights; robustness is improved through the triple mechanism of difference calculation, dynamic weight adjustment, and threshold protection to avoid prediction bias caused by variety differences, which is especially suitable for early warning of pests and diseases when multiple varieties are mixed planted or introduced across regions; interpretability is enhanced, and the weight adjustment process is based on quantitative indicators (d, k, ε), so that changes in model parameters have clear physical meanings, which is convenient for agricultural technicians to understand and optimize.

[0059] Furthermore, k can be determined by the following steps: S51, obtaining the average target environmental impact factor value corresponding to each main target environmental impact factor in the diseased Forsythia suspensa planting area and the Forsythia suspensa planting area to be predicted within a preset historical time period, so as to obtain an average target environmental impact factor value group list G=(G1, G2, ..., G p ,…,G q ), p=1, 2, …, q; G p is the average target environmental impact factor value group corresponding to the main target environmental impact factors, q is the number of main target impact factors; G p =(G p，1 , G p，2 );G p，1is the average target environmental impact factor value corresponding to the pth main target environmental impact factor in the diseased Forsythia suspensa planting area during the preset historical period, G p，2 It is the average target environmental impact factor value corresponding to the pth main target environmental impact factor in the predicted Forsythia suspensa planting area within the preset historical time period.

[0060] In this embodiment, the end time of the historical time period can be the current dynamic time point, and the duration can be 6 months. The average value of historical data eliminates short-term fluctuations and extracts the long-term characteristics of environmental factors, ensuring the stability and representativeness of the data. The structured data format facilitates subsequent comparative analysis and provides a quantitative basis for determining environmental differences.

[0061] S52, if G p，1 / H p >θ p And G p，2 / H p >θ p , then the pth main target environmental impact factor is determined as the designated factor; among them, H p is the historical average target environmental impact factor value corresponding to the pth main target environmental impact factor, θ p is the preset weight threshold corresponding to the pth main target environmental influencing factor.

[0062] For each major target environmental influencing factor, calculate its average value in the diseased area and the area to be predicted and its historical average value H p The ratio of θ p It is an empirical value and can be set according to the characteristics of the factors; for example, θ p is 0.8 or 1.2.

[0063] By using ratios to determine whether environmental factors deviate significantly from historical norms, we can screen out specific factors that have a more prominent impact on pests and diseases. We can identify abnormal environmental factors in a targeted manner to avoid misjudgments caused by fluctuations in common factors and enhance the model's sensitivity to key influencing factors.

[0064] S53 , if NUM1 / q>σ, increase k; wherein NUM1 is the number of specified factors, and σ is a preset ratio threshold.

[0065] Calculate the number of specified factors NUM1 and find its ratio NUM1 / q to the total number of main factors q; if the ratio exceeds a preset ratio threshold σ, such as σ = 0.5, increase the adjustment coefficient k.

[0066] When a large number of environmental factors, such as temperature and humidity, are abnormal at the same time and deviate significantly from historical levels, increasing k can strengthen the weight adjustment amplitude: if k increases, the adjustment force of ω1=ω1×(1-k×d) in step S541 will be stronger, so that the weight of the main factor will shift more quickly to the secondary factor; it can also dynamically adapt to the degree of environmental difference. The more abnormal environmental factors there are, the more sensitive the model is to insufficient similarity, avoiding prediction deviations due to drastic environmental changes and improving the adaptability and accuracy of pest and disease prediction.

[0067] By comparing historical data with real-time data, the degree of abnormality of environmental factors is quantified, so that k is deeply bound to the actual environmental differences; adaptive weight optimization, when the environmental differences are significant, that is, there are many specified factors, increasing k can accelerate weight redistribution, ensuring that the prediction model can more flexibly adapt to the environmental characteristics of different planting areas, and ultimately improve the accuracy and reliability of pest and disease prediction.

[0068] S600 , determining a first similarity η1 between XL1 and XL2 according to the weight corresponding to each eigenvalue in XL1 and XL2 .

[0069] Furthermore, step S600 may include the following steps: S610, obtain XL1=(XA1, XA2, ..., XA p ,…,XA q , XB1, XB2, …, XB j ,…,XB m ), p = 1, 2, ..., q; j = 1, 2, ..., m; where XA p is the characteristic value corresponding to the pth main target influencing factor in the diseased Forsythia suspensa planting area, q is the number of main target influencing factors; XB j is the characteristic value corresponding to the jth secondary target influencing factor in the diseased Forsythia suspensa planting area, m is the number of secondary target influencing factors; q+m=n.

[0070] By separating the main target influencing factors from the secondary target influencing factors, the weight distribution is more in line with the core logic of pest and disease prediction, because the main factors have a greater impact on the disease; the weight strategy is adapted to provide a clear data structure for subsequent weighted calculations, ensuring that the weights ω1 and ω2 can accurately act on the corresponding factors.

[0071] S620, obtain XL2=(XC1, XC2, ..., XC p ,…,XC q , XD1, XD2, …, XD j ,…,XD m ); Among them, XC p is the characteristic value corresponding to the pth main target influencing factor of the Forsythia suspensa planting area to be predicted; XD jis the eigenvalue corresponding to the jth secondary target influencing factor of the Forsythia suspensa planting area to be predicted.

[0072] This step ensures that the dimensions and factor classifications of XL1 and XL2 strictly correspond, avoiding calculation errors caused by data misalignment; the unified feature vector structure provides a standardized basis for comparison of environmental data from different planting areas.

[0073] S630, according to ω1 and ω2, determine η1=(ω1×∑ q p=1 (XA p -XC p ) 2 +ω2×∑ m j=1 (XB j -XD j ) 2 ) 1 / 2 .

[0074] In this embodiment, the smaller the η1 value is, the more similar XL1 and XL2 are, and the more likely the same type of pests and diseases are to occur in the predicted area.

[0075] The logic of the main factors dominating the similarity calculation is realized through ω1 and ω2. For example, temperature differences will contribute more to η1 than soil pH differences. Abstract environmental similarities are converted into comparable numerical values ​​to provide an accurate basis for S700's disease and insect pest judgment. The low weight of secondary factors can weaken the impact of non-critical environmental fluctuations and enhance the model's sensitivity to core pathogenic factors.

[0076] In the above steps, the weighting mechanism of high weight for main factors and low weight for secondary factors is used to fit the dominant characteristics of key environmental factors for the occurrence of pests and diseases, and the prediction accuracy is greatly improved compared with the traditional Euclidean distance. In conjunction with the weight adjustment process of S500, when the sensitivity of varieties differs greatly, that is, η2<γ2, the dynamically adjusted ω1 will change the calculation center of gravity of the weighted distance to ensure that the similarity results can reflect the variety specificity.

[0077] S700, if η1≥γ1, it is determined that the Forsythia suspensa in the predicted Forsythia suspensa planting area will be susceptible to pests and diseases of the QA type; otherwise, it is determined that the Forsythia suspensa in the predicted Forsythia suspensa planting area will not be susceptible to pests and diseases of the QA type; γ1 is a preset first similarity threshold.

[0078] Compare the calculated environmental feature vector similarity η1 with γ1. If η1 ≥ γ1, it means that the environmental characteristics of the predicted area and the diseased area (combined with the variety sensitivity weight) are similar enough, and it is determined that the predicted area will have QA type pests and diseases; if η1 < γ1, it means that the environmental difference is large, and it is determined that the predicted area will not have such pests and diseases.

[0079] γ1 can be calibrated with historical data. For example, by counting the probability of actual disease occurrence when η1 ≥ γ1, the γ1 value that maximizes the prediction accuracy can be selected, such as by determining the optimal threshold through the ROC curve.

[0080] The method for predicting pests and diseases during the Forsythia suspensa planting period of this embodiment, first, dynamically adjusts the feature vector weights according to the sensitivity lists α and β of environmental influencing factors of different varieties, so that the weight distribution of the environmental influencing factor feature vector XL1 corresponding to the diseased Forsythia suspensa planting area and the environmental influencing factor feature vector XL2 corresponding to the Forsythia suspensa planting area to be predicted can accurately reflect the interaction between the Forsythia suspensa variety and the environmental factors, avoiding the traditional unified weight that ignores the variety specificity; secondly, through the sensitivity-driven weight determination mechanism, the quantitative characterization of the response differences of different varieties under the same environmental conditions is realized, and the problem of feature vector characterization distortion caused by variety differences is solved; in addition, the characteristic vector similarity calculated in combination with the weight can more accurately measure the environmental matching degree between the area to be predicted and the diseased area, thereby improving the accuracy and reliability of pest and disease prediction.

[0081] Furthermore, although the steps of the method of the present disclosure are described in a particular order in the accompanying drawings, this does not require or imply that the steps must be performed in this particular order, or that all steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

[0082] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to implementing a method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0083] The program product may utilize any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0084] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0085] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0086] The program code for performing the operations of the present application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0087] An embodiment of the present invention further provides an electronic device including a processor and the aforementioned non-transitory computer-readable storage medium.

[0088] The electronic device is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0089] The electronic device is implemented as a general-purpose computing device. Components of the electronic device may include, but are not limited to, the aforementioned at least one processor, the aforementioned at least one memory, and a bus connecting different system components (including the memory and the processor).

[0090] The memory stores program codes, which can be executed by the processor, so that the processor performs the steps in various embodiments described in this specification.

[0091] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0092] The memory may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0093] The bus may represent one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0094] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter. The network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0095] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0096] An embodiment of the present invention further provides a computer program product comprising program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the method according to various exemplary embodiments of the present invention described above in this specification.

[0097] Although some specific embodiments of the present invention have been described in detail by way of examples, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present invention. It should also be understood by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention.

Claims

1. A method for predicting pests and diseases during the planting period of Forsythia suspensa, characterized in that: The method comprises the following steps: S100, based on the QA of the types of diseases and insect pests of Forsythia suspensa in the diseased Forsythia suspensa planting area, determine several target environmental influencing factors corresponding to the QA; S200, obtaining the average target environmental impact factor value corresponding to each target environmental impact factor in the diseased Forsythia suspensa planting area and the Forsythia suspensa planting area to be predicted within a preset historical time period, so as to construct an environmental impact factor feature vector XL1 corresponding to the diseased Forsythia suspensa planting area and an environmental impact factor feature vector XL2 corresponding to the Forsythia suspensa planting area to be predicted; S300, if the Forsythia suspensa variety planted in the diseased Forsythia suspensa planting area and the Forsythia suspensa planting area to be predicted are the same, obtaining a first similarity η1 between XL1 and XL2; S400, if the Forsythia suspensa varieties planted in the diseased Forsythia suspensa planting area and the Forsythia suspensa planting area to be predicted are different, obtaining a sensitivity list α of environmental influencing factors corresponding to the Forsythia suspensa varieties planted in the diseased Forsythia suspensa planting area and a sensitivity list β of environmental influencing factors corresponding to the Forsythia suspensa varieties planted in the Forsythia suspensa planting area to be predicted; S500, determining the weight corresponding to each eigenvalue in XL1 and XL2 based on α and β; S600, determining a first similarity η1 between XL1 and XL2 according to the weight corresponding to each eigenvalue in XL1 and XL2; S700, if η1≥γ1, it is determined that the Forsythia suspensa in the predicted Forsythia suspensa planting area will be susceptible to pests and diseases of the QA type; otherwise, it is determined that the Forsythia suspensa in the predicted Forsythia suspensa planting area will not be susceptible to pests and diseases of the QA type; γ1 is a preset first similarity threshold.

2. The method for predicting pests and diseases during the planting period of Forsythia suspensa according to claim 1, characterized in that: Step S500 includes the following steps: S510, obtain α=(α1, α2,…,α i ,…,α n ) and β=(β1, β2,…,β i ,…,β n ), i=1, 2,...,n; where, α i is the sensitivity of the Forsythia suspensa variety planted in the diseased Forsythia suspensa planting area to the i-th target environmental factor, β i is the sensitivity of the Forsythia suspensa variety planted in the Forsythia suspensa planting area to the i-th target environmental influencing factor, n is the number of target environmental influencing factors; SUM (α) = 1, SUM (β) = 1; SUM () is the summation function; S520, obtaining a second similarity η2 between α and β; S530, if η2≥γ2, then determine that the weight of the characteristic value corresponding to the main target environmental influencing factor in XL1 and XL2 is the first preset weight ω1, and the weight of the characteristic value corresponding to the secondary target environmental influencing factor is the second preset weight ω2; wherein, ω1>ω2, ω1+ω2=1; γ2 is the preset second similarity threshold.

3. The method for predicting pests and diseases during the planting period of Forsythia suspensa according to claim 2, characterized in that: After step S530, the method further includes the following steps: S540, if η2<γ2, obtain the difference between α and β d=1-η2 / γ2; S541, according to d, adjust ω1 = ω1 × (1-k × d); where k is a preset adjustment coefficient; 0 < k ≤ 1; proceed to S542; S542, if ω1≤ω2, set ω1=ω2+ε; where ε is a preset adjustment parameter, 0<ε<0.

1.

4. The method for predicting pests and diseases during the planting period of Forsythia suspensa according to claim 3, characterized in that: k is determined by the following steps: S51, obtaining the average target environmental impact factor value corresponding to each main target environmental impact factor in the diseased Forsythia suspensa planting area and the Forsythia suspensa planting area to be predicted within a preset historical time period, so as to obtain an average target environmental impact factor value group list G=(G1, G2, ..., G p ,…,G q ), p=1, 2,…, q; G p is the average target environmental impact factor value group corresponding to the main target environmental impact factors, q is the number of main target impact factors; G p =(G p，1 , G p，2 );G p，1 is the average target environmental impact factor value corresponding to the pth main target environmental impact factor in the diseased Forsythia suspensa planting area during the preset historical period, G p，2 is the average target environmental impact factor value corresponding to the pth main target environmental impact factor in the predicted Forsythia suspensa planting area within the preset historical time period; S52, if G p，1 / H p >θ p And G p，2 / H p >θ p , then the pth main target environmental impact factor is determined as the designated factor; among them, H p is the historical average target environmental impact factor value corresponding to the pth main target environmental impact factor, θ p is the preset weight threshold corresponding to the pth main target environmental impact factor; S53 , if NUM1 / q>σ, increase k; wherein NUM1 is the number of specified factors, and σ is a preset ratio threshold.

5. The method for predicting pests and diseases during the planting period of Forsythia suspensa according to claim 3, characterized in that: Step S600 includes the following steps: S610, obtain XL1=(XA1, XA2, ..., XA p ,…,XA q , XB1, XB2, …, XB j ,…,XB m ), p = 1, 2, ..., q; j = 1, 2, ..., m; where XA p is the characteristic value corresponding to the pth main target influencing factor in the diseased Forsythia suspensa planting area, q is the number of main target influencing factors; XB j is the characteristic value corresponding to the jth secondary target influencing factor in the diseased forsythia planting area, m is the number of secondary target influencing factors; q+m=n; S620, obtain XL2=(XC1, XC2, ..., XC p ,…,XC q , XD1, XD2, …, XD j ,…,XD m ); Among them, XC p is the characteristic value corresponding to the pth main target influencing factor of the Forsythia suspensa planting area to be predicted; XD j is the eigenvalue corresponding to the jth secondary target influencing factor of the Forsythia suspensa planting area to be predicted; S630, according to ω1 and ω2, determine η1=(ω1×∑ q p=1 (XA p -XC p ) 2 +ω2×∑ m j=1 (XB j -XD j ) 2 ) 1 / 2 .

6. The method for predicting pests and diseases during the planting period of Forsythia suspensa according to claim 2, characterized in that: The value range of ω1 is 0.7 to 0.

9.

7. The method for predicting pests and diseases during the planting period of Forsythia suspensa according to claim 1, characterized in that: Target environmental factors include: temperature, humidity, rainfall, soil pH, altitude, daylight hours, and slope.

8. A non-transitory computer-readable storage medium, wherein at least one instruction or at least one program is stored in the storage medium, characterized in that: The at least one instruction or the at least one program segment is loaded and executed by a processor to implement the method for predicting pests and diseases during the planting period of Forsythia suspensa according to any one of claims 1 to 7.

9. An electronic device, characterized in that: The device comprises a processor and the non-transitory computer-readable storage medium of claim 8.

Images