A method and system for integrated assessment and control of diseases and pests in passion fruit cultivation.

Abstract

This invention discloses a method and system for comprehensive assessment and control of diseases and pests in passion fruit cultivation. The method includes: dividing a target area into n different sub-regions; acquiring plant image information, environmental characteristic information, climate characteristic information, regional meteorological information, and information on the number of captured pests in each sub-region; preprocessing the acquired information; identifying the acquired information to obtain identification results; classifying and merging the sub-regions using a clustering algorithm to obtain m merged sub-regions; calculating the degree of disease or pest infestation in each merged sub-region to obtain disease and pest infestation degree information; conducting a comprehensive assessment of diseases and pests in each merged sub-region to obtain assessment results; and formulating candidate control schemes based on the assessment results, identification results, and regional meteorological information, and selecting the optimal control scheme. This method effectively improves the accuracy and effectiveness of disease and pest control.

Description

Technical Field

[0001] This invention relates to the field of integrated pest management and control, and in particular to a method and system for integrated pest management and control in passion fruit cultivation. Background Technology

[0002] With advancements in agricultural planting techniques, passion fruit has gradually become a popular fruit, frequently purchased by many families due to its high nutritional value and delicious taste. However, passion fruit cultivation is inevitably affected by pests and diseases, which can hinder plant growth and ultimately impact yield.

[0003] In existing technologies, when plant diseases and pests are found to appear in the cultivation area, a single control measure is directly used to deal with them. This often leads to incomplete control or excessive use of pesticides and other adverse consequences. Therefore, how to effectively and accurately control diseases and pests that occur during cultivation is a key issue. Summary of the Invention

[0004] This invention overcomes the shortcomings of the prior art and proposes a method and system for comprehensive assessment and control of diseases and pests in the passion fruit cultivation process. Its main purpose is to accurately control diseases and pests while improving the control effect.

[0005] To achieve the above objectives, the first aspect of this invention provides a method for integrated assessment and control of pests and diseases in passion fruit cultivation, comprising:

[0006] The target area is divided into n different sub-regions. Plant image information, environmental feature information, climate feature information, regional meteorological information, and regional pest capture quantity information are obtained for each sub-region. The obtained information is then preprocessed.

[0007] The plant image information and environmental feature information of each sub-region are obtained and processed to identify n identification result information;

[0008] Clustering algorithm is used to classify and merge all sub-regions to obtain m merged sub-regions. The degree of disease or pest infestation in each merged sub-region is calculated to obtain the disease and pest infestation information of each merged sub-region.

[0009] A comprehensive assessment of pests and diseases in each merged sub-region is conducted using information on disease severity, pest severity, identification results, climate characteristics, and environmental characteristics to obtain assessment results.

[0010] Candidate prevention and control plans are developed by evaluating and identifying the results and regional meteorological information, and the optimal prevention and control plan is selected.

[0011] In this scheme, dividing the target area into n different sub-regions and preprocessing the acquired information specifically involves:

[0012] Divide the target area into n different sub-regions and assign each sub-region a unique label number;

[0013] Acquire plant image information, environmental feature information, regional meteorological information, climate feature information, and regional pest capture quantity information for each sub-region;

[0014] The environmental characteristics information includes: ambient temperature and humidity, soil temperature and humidity, and soil pH value;

[0015] The acquired information is preprocessed by screening, filtering, and noise reduction.

[0016] In this scheme, the process of identifying and processing the plant image information and environmental feature information of each sub-region to obtain n identification result information is as follows:

[0017] A recognition model is built based on YOLOv5, and the recognition model is subjected to deep learning and training to obtain a recognition model that meets the expectations.

[0018] The plant image information and environmental feature information of each sub-region are imported into the recognition model to obtain n recognition result information;

[0019] The identification results include: disease type information, pest type information, and environmental suitability information.

[0020] In this scheme, a clustering algorithm is used to classify and merge all sub-regions, resulting in m merged sub-regions. The severity of disease or pest infestation in each merged sub-region is calculated to obtain the disease and pest infestation severity information for each merged sub-region. Specifically:

[0021] The disease and pest types in each sub-region are obtained by identifying the results. A clustering algorithm is used to classify each sub-region, and sub-regions of the same category are merged to obtain merged sub-regions.

[0022] Each sub-region is divided into four categories: A, B, C, and D. Category A is the region with diseases, Category B is the region with pests, Category C is the region with both diseases and pests, and Category D is the region without diseases or pests.

[0023] By analyzing the area of ​​lesions on plants in each merged region and the number of pests captured per unit time, information on the severity of pests and diseases in each merged region can be obtained.

[0024] In this scheme, the process of obtaining pest and disease severity information for each merged sub-region by using information on the area of ​​lesions on plants in each merged sub-region and the number of pests captured per unit time also includes:

[0025] The plant image information of each merged sub-region is processed into grayscale to obtain grayscale plant image information;

[0026] The grayscale plant images are classified using the K-means clustering algorithm to obtain classified grayscale plant images, and then the classified grayscale plant images are denoised.

[0027] Extract the contour information of the plant and plant lesions, calculate the pixel area S1 of the plant in the classified grayscale plant image information and define it as the total area of ​​the plant in the region, and calculate the pixel area S2 of the plant lesions in the classified grayscale plant image information and define it as the area of ​​the plant lesions in the region.

[0028] The disease severity information for each merged sub-region is calculated by using the total area of ​​plants in the region and the area of ​​disease spots on plants in the region.

[0029] The specific formula for calculating the severity of the disease is as follows:

[0030]

[0031] In the formula, D i The disease severity, total plant area in region S1, and lesion area in region S2 are all considered.

[0032] In this scheme, the process of obtaining pest and disease severity information for each merged sub-region by using information on the area of ​​lesions on plants in each merged sub-region and the number of pests captured per unit time also includes:

[0033] The number of pests captured per unit time is calculated by the regional pest capture information, which is used to determine the degree of pest infestation.

[0034] The threshold for judging the degree of pest infestation is set based on the number of pests captured per unit time. The calculated number of pests captured per unit time is compared with the threshold for judging the degree of pest infestation to obtain the degree of pest infestation in each merged sub-region.

[0035] The specific formula for calculating the number of pests captured per unit time is as follows:

[0036]

[0037] In the formula, C p The number of pests captured per unit time, Q p T represents the number of pests captured in the area, and T represents the total time spent capturing pests in the area.

[0038] In this plan, the comprehensive assessment of pests and diseases in each merged sub-region to obtain assessment results specifically includes:

[0039] Obtain information on disease severity, pest severity, identification results, climate characteristics, and environmental characteristics for each merged sub-region;

[0040] A comprehensive assessment model for pests and diseases is constructed, and the comprehensive assessment model for pests and diseases is subjected to deep learning and training to obtain a comprehensive assessment model for pests and diseases that meets the expectations.

[0041] By importing information on disease severity, pest severity, identification results, climate characteristics, and environmental characteristics into the integrated pest management model, assessment results are obtained.

[0042] In this plan, the process of formulating candidate prevention and control plans based on evaluation results, identification results, and regional meteorological information, and selecting the optimal prevention and control plan, specifically includes:

[0043] Pest and disease control examples are obtained based on big data retrieval, forming a control example dataset;

[0044] Candidate prevention and control plans will be developed by combining assessment results, identification results, and regional meteorological information with prevention and control case datasets.

[0045] Extract the duration of control efficacy of candidate control programs and use it as the control weight of the candidate control programs. Sort the candidate control programs to obtain a control efficacy duration ranking table.

[0046] Based on the assessment results, disease severity, and pest severity information of each merged sub-region, combined with the control efficacy duration ranking table, the optimal control plan is selected.

[0047] A second aspect of the present invention also provides a system for comprehensive assessment and control of diseases and pests in passion fruit cultivation. The system includes a memory and a processor. The memory includes a program for comprehensive assessment and control of diseases and pests in passion fruit cultivation. When the processor executes the program for comprehensive assessment and control of diseases and pests in passion fruit cultivation, it performs the following steps:

[0048] The target area is divided into n different sub-regions. Plant image information, environmental feature information, climate feature information, regional meteorological information, and regional pest capture quantity information are obtained for each sub-region. The obtained information is then preprocessed.

[0049] The plant image information and environmental feature information of each sub-region are obtained and processed to identify n identification result information;

[0050] Clustering algorithm is used to classify and merge all sub-regions to obtain m merged sub-regions. The degree of disease or pest infestation in each merged sub-region is calculated to obtain the disease and pest infestation information of each merged sub-region.

[0051] A comprehensive assessment of pests and diseases in each sub-region is conducted using information on disease severity, pest severity, environmental characteristics, climate characteristics, and regional meteorological information to obtain the assessment results.

[0052] Candidate prevention and control plans are developed by evaluating and identifying the results and regional meteorological information, and the optimal prevention and control plan is selected.

[0053] In this plan, the process of formulating candidate prevention and control plans based on evaluation results, identification results, and regional meteorological information, and then selecting the optimal prevention and control plan, specifically involves:

[0054] Pest and disease control examples are obtained based on big data retrieval, forming a control example dataset;

[0055] Candidate prevention and control plans will be developed by combining assessment results, identification results, and regional meteorological information with prevention and control case datasets.

[0056] Extract the duration of control efficacy of candidate control programs and use it as the control weight of the candidate control programs. Sort the candidate control programs to obtain a control efficacy duration ranking table.

[0057] Based on the assessment results, disease severity, and pest severity information of each merged sub-region, combined with the control efficacy duration ranking table, the optimal control plan is selected.

[0058] This invention discloses a method and system for comprehensive assessment and control of diseases and pests in passion fruit cultivation. The method includes: dividing a target area into n different sub-regions; acquiring plant image information, environmental characteristic information, climate characteristic information, regional meteorological information, and information on the number of captured pests in each sub-region; preprocessing the acquired information; identifying the acquired information to obtain identification results; classifying and merging the sub-regions using a clustering algorithm to obtain m merged sub-regions; calculating the degree of disease or pest infestation in each merged sub-region to obtain disease and pest infestation degree information; conducting a comprehensive assessment of diseases and pests in each merged sub-region to obtain assessment results; and formulating candidate control schemes based on the assessment results, identification results, and regional meteorological information, and selecting the optimal control scheme. This method effectively improves the accuracy and effectiveness of disease and pest control. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments or examples of the present invention, the drawings used in the embodiments or examples will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained according to these drawings without creative effort.

[0060] Figure 1 This is a flowchart of a method for integrated assessment and control of diseases and pests in passion fruit cultivation, provided by an embodiment of the present invention.

[0061] Figure 2 A data processing flowchart of a pest and disease integrated assessment and control method provided in an embodiment of the present invention;

[0062] Figure 3 This is a block diagram of a comprehensive assessment and control system for diseases and pests in the passion fruit cultivation process, provided in an embodiment of the present invention.

[0063] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0064] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0065] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0066] Figure 1 This is a flowchart of a method for integrated assessment and control of diseases and pests in passion fruit cultivation, provided by an embodiment of the present invention.

[0067] like Figure 1 As shown, this invention provides a flowchart of a method for integrated assessment and control of pests and diseases in passion fruit cultivation, including:

[0068] S102, the target area is divided into n different sub-regions, and plant image information, environmental feature information, climate feature information, regional meteorological information, and regional pest capture quantity information of each sub-region are obtained respectively. The obtained information is preprocessed.

[0069] Divide the target area into n different sub-regions and assign each sub-region a unique label number;

[0070] Acquire plant image information, environmental feature information, regional meteorological information, climate feature information, and regional pest capture quantity information for each sub-region;

[0071] The environmental characteristics information includes: ambient temperature and humidity, soil temperature and humidity, and soil pH value;

[0072] The acquired information is preprocessed by screening, filtering, and noise reduction.

[0073] S104, the plant image information and environmental feature information of each sub-region are processed for identification to obtain n identification result information;

[0074] A recognition model is built based on YOLOv5, and the recognition model is subjected to deep learning and training to obtain a recognition model that meets the expectations.

[0075] The plant image information and environmental feature information of each sub-region are imported into the recognition model to obtain n recognition result information;

[0076] The identification results include: disease type information, pest type information, and environmental suitability information.

[0077] S106, use clustering algorithm to classify and merge all sub-regions to obtain m merged sub-regions, calculate the degree of disease or pest infestation in each merged sub-region, and obtain the degree of disease and pest infestation information of each merged sub-region;

[0078] The disease and pest types in each sub-region are obtained by identifying the results. A clustering algorithm is used to classify each sub-region, and sub-regions of the same category are merged to obtain merged sub-regions.

[0079] Each sub-region is divided into four categories: A, B, C, and D. Category A is the region with diseases, Category B is the region with pests, Category C is the region with both diseases and pests, and Category D is the region without diseases or pests.

[0080] By analyzing the area of ​​lesions on plants in each merged region and the number of pests captured per unit time, information on the severity of pests and diseases in each merged region can be obtained.

[0081] Furthermore, the process of obtaining disease and pest severity information for each merged sub-region by using the regional plant lesion area information and the number of pests captured per unit time for each merged sub-region includes: performing grayscale processing on the plant image information of each merged sub-region to obtain grayscale plant image information; classifying the grayscale plant image information using the K-means clustering algorithm to obtain classified grayscale plant image information; performing noise reduction processing on the classified grayscale plant image information; extracting the contour information of the plant and plant lesions; calculating the pixel area S1 of the plant in the classified grayscale plant image information and defining it as the total area of ​​the regional plants; calculating the pixel area S2 of the plant lesions in the classified grayscale plant image information and defining it as the area of ​​the regional plant lesions; and calculating the disease severity information for each merged sub-region using the total area of ​​the regional plants and the area of ​​the regional plant lesions.

[0082] The specific formula for calculating the severity of the disease is as follows:

[0083]

[0084] In the formula, D i The disease severity, total plant area in region S1, and lesion area in region S2 are all considered.

[0085] Furthermore, the process of obtaining pest and disease severity information and insect pest severity information for each merged sub-region by using the regional plant lesion area information and the number of pests captured per unit time information for each merged sub-region also includes: calculating the number of pests captured per unit time information based on the regional pest capture information, which is used to determine the insect pest severity information; setting an insect pest severity judgment threshold based on the number of pests captured per unit time, and comparing the calculated number of pests captured per unit time with the insect pest severity judgment threshold to obtain the insect pest severity for each merged sub-region.

[0086] The specific formula for calculating the number of pests captured per unit time is as follows:

[0087]

[0088] In the formula, C p The number of pests captured per unit time, Q p T represents the number of pests captured in the area, and T represents the total time spent capturing pests in the area.

[0089] Furthermore, regional meteorological information, environmental characteristics, and identification results of each merged sub-region are obtained; pests in each merged sub-region are trapped using sex pheromones to obtain information on the number of pests trapped in each merged sub-region; the number of pests trapped per unit time is calculated based on the number of pests trapped in each merged sub-region; the growth habits of pests in each merged sub-region are obtained based on the identification results and big data retrieval; the growth stage information of pests in each merged sub-region is obtained by combining the information on the number of pests trapped per unit time, regional meteorological information, environmental characteristics, and pest growth habits; and pest outbreak time is predicted based on the pest growth stage information, the number of pests trapped per unit time, regional meteorological information, and environmental characteristics in each merged sub-region, and control plans are formulated for each merged sub-region to accurately control pests and improve the accuracy and thoroughness of pest control.

[0090] S108: Candidate prevention and control plans are formulated by evaluating and identifying the results and regional meteorological information, and the optimal prevention and control plan is selected.

[0091] Pest and disease control examples are obtained based on big data retrieval, forming a control example dataset;

[0092] Candidate prevention and control plans will be developed by combining assessment results, identification results, and regional meteorological information with prevention and control case datasets.

[0093] Extract the duration of control efficacy of candidate control programs and use it as the control weight of the candidate control programs. Sort the candidate control programs to obtain a control efficacy duration ranking table.

[0094] Based on the assessment results, disease severity, and pest severity information of each merged sub-region, combined with the control efficacy duration ranking table, the optimal control plan is selected.

[0095] Furthermore, a merged sub-region with severe pest and disease infestation is selected, and the severity of pest and disease infestation in each sub-region within the merged sub-region is calculated. A sub-region with severe pest and disease infestation is defined as a dangerous area, and environmental characteristic information and identification result information of the dangerous area are obtained. Based on the identification result information, pest and disease pattern information of the dangerous area is obtained through big data retrieval. Environmental characteristic information and meteorological characteristic information of the sub-regions near the dangerous area are obtained, and the similarity between the environmental characteristic information of the nearby sub-regions and the environmental characteristic information of the dangerous area is calculated to obtain a similarity value. If the similarity value is greater than a preset threshold, the area is defined as a high-risk area. The meteorological characteristics, identification result information, and pest and disease pattern information of the high-risk area are combined to predict the occurrence time of pests and diseases in the high-risk area, obtaining pest and disease occurrence time information. Based on the obtained pest and disease occurrence time information, a prevention and control plan for the high-risk area is formulated.

[0096] Furthermore, plant image information of the target area is acquired, and the plant image information is processed to obtain plant growth stage information; based on the plant growth stage information and big data retrieval, the optimal suitable conditions for each stage of plant growth are obtained; based on the optimal suitable conditions information, the water requirement information for each growth stage of the plant is obtained as a threshold for judging soil moisture content; meteorological information and soil moisture content information of the target area are acquired, and the real-time soil moisture content information is compared with the judgment threshold; if the soil moisture content is greater than the judgment threshold, a warning message of excessive soil moisture content in the target area is obtained; if the soil moisture content is less than the judgment threshold, a warning message of insufficient soil moisture content in the target area is obtained, and an irrigation plan is formulated; the soil moisture content of the target area at future times is predicted by combining the meteorological information of the target area with the real-time soil moisture content information, and the predicted moisture content information is obtained; the plant growth stage information of the target area at future times is acquired, and the water requirement information of each growth stage of the plant is used to obtain the water requirement information of the plant at future times; the predicted moisture content information is compared with the water requirement information of the plant at future times, and an irrigation plan or a solution to improve the drainage efficiency of the area is adopted according to the judgment result.

[0097] It should be noted that dividing the target area into different sub-regions and conducting pest and disease identification and comprehensive assessment in each sub-region allows for a precise understanding of the pest and disease situation in the target area. Through the identification and analysis of each sub-region, it can be determined whether the pests, diseases, or both are present in each sub-region. Based on the different diseases or pests, control plans can be developed to address the pest and disease problems in each region in a targeted manner. This prevents the overuse of pesticides that pollute the environment or the excessive use of equipment that increases control costs, greatly improving the pest and disease control effect in passion fruit cultivation. At the same time, by dividing the area to determine the pest and disease situation, it is possible to better control pests and diseases in the target area.

[0098] Figure 2 A data processing flowchart of a pest and disease integrated assessment and control method provided in an embodiment of the present invention;

[0099] like Figure 2 As shown, this invention provides a data processing flowchart for a comprehensive assessment and control method for pests and diseases, including:

[0100] S202, Preprocess the various information obtained;

[0101] S204, identify and process the plant image information and environmental feature information of each sub-region to obtain the identification result information;

[0102] S206, Classify each sub-region based on the recognition results to obtain the merged sub-region;

[0103] Furthermore, the types of diseases and pests in each sub-region are obtained through the identification results. Clustering algorithms are used to classify each sub-region, and sub-regions of the same category are merged to obtain merged sub-regions. Each sub-region is divided into four categories: A, B, C, and D. Category A is the region with diseases, Category B is the region with pests, Category C is the region with both diseases and pests, and Category D is the region without diseases or pests.

[0104] S208, conduct a comprehensive assessment of pests and diseases in each merged sub-region to obtain assessment results information;

[0105] Furthermore, information on disease severity, pest severity, identification results, climate characteristics, and environmental characteristics are imported into the integrated pest assessment model to obtain assessment results.

[0106] S210, develops candidate prevention and control plans by evaluating and identifying results information and regional meteorological information;

[0107] S212. Based on the assessment results, disease severity information, and pest severity information, combined with the control efficacy duration ranking table, the optimal control plan is selected.

[0108] Furthermore, soil samples were collected from each merged sub-region after treatment using the optimal control scheme; gas chromatography was used to detect the collected soil samples to obtain pesticide residue information for each merged sub-region; the pesticide residue information was compared with a preset threshold to obtain soil environmental status information for each merged sub-region; based on data retrieval, examples of pesticide pollution treatment methods were constructed to form an example dataset; soil pollution treatment schemes were formulated based on pesticide residue information, soil environmental status information, and pesticide type information in the optimal control scheme, combined with the example dataset; environmental and meteorological characteristics of the areas treating pesticide pollution in the example dataset were extracted and compared with the environmental and meteorological characteristics of each merged region to calculate similarity values, which were used as the calculation weights for selecting the best soil pollution treatment scheme, and weighted calculations were performed on each soil pollution treatment scheme; the soil pollution treatment schemes were ranked based on the calculation results, and the best soil pollution treatment scheme for each merged sub-region was selected.

[0109] It should be noted that the target area is divided into different sub-regions, and the pest and disease situation in each sub-region is classified to obtain the classified merged sub-regions. The merged sub-regions are then comprehensively evaluated, and prevention and control plans are formulated to address the pest and disease situation in each merged sub-region. When formulating and selecting the optimal prevention and control plan, the meteorological information of each region is taken into consideration, and a prevention and control plan suitable for the current weather is adopted to prevent meteorological factors from causing incomplete pest and disease control and affecting the normal growth of passion fruit in the target area.

[0110] Figure 3This is a block diagram of a comprehensive assessment and control system for diseases and pests in the passion fruit cultivation process, provided in an embodiment of the present invention.

[0111] like Figure 3 As shown, the present invention provides a comprehensive assessment and control system 3 for diseases and pests in passion fruit cultivation. The system includes a memory 31 and a processor 32. The memory 31 contains a program for a comprehensive assessment and control method for diseases and pests in passion fruit cultivation. When the processor 32 executes the program, the following steps are implemented:

[0112] The target area is divided into n different sub-regions. Plant image information, environmental feature information, climate feature information, regional meteorological information, and regional pest capture quantity information are obtained for each sub-region. The obtained information is then preprocessed.

[0113] The plant image information and environmental feature information of each sub-region are obtained and processed to identify n identification result information;

[0114] Clustering algorithm is used to classify and merge all sub-regions to obtain m merged sub-regions. The degree of disease or pest infestation in each merged sub-region is calculated to obtain the disease and pest infestation information of each merged sub-region.

[0115] A comprehensive assessment of pests and diseases in each sub-region is conducted using information on disease severity, pest severity, environmental characteristics, climate characteristics, and regional meteorological information to obtain the assessment results.

[0116] Candidate prevention and control plans are developed by evaluating and identifying the results and regional meteorological information, and the optimal prevention and control plan is selected.

[0117] It should be noted that regionalized and subdivided target areas allow for the assessment and analysis of pests and diseases in each area, providing information on the pest and disease situation in each region. This enables targeted solutions to pest and disease problems in different areas, effectively controlling pests and diseases in each region while reducing control costs and improving control efficiency and effectiveness.

[0118] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components can be combined, or integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be electrical, mechanical, or other forms.

[0119] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0120] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0121] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0122] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0123] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for integrated assessment and control of pests and diseases in passion fruit cultivation, characterized in that, include: The target area is divided into n different sub-regions. Plant image information, environmental feature information, climate feature information, regional meteorological information, and regional pest capture quantity information are obtained for each sub-region. The obtained information is then preprocessed. The plant image information and environmental feature information of each sub-region are obtained and processed to identify n identification result information; Clustering algorithm is used to classify and merge all sub-regions to obtain m merged sub-regions. The degree of disease or pest infestation in each merged sub-region is calculated to obtain the disease and pest infestation information of each merged sub-region. A comprehensive assessment of pests and diseases in each merged sub-region is conducted using information on disease severity, pest severity, identification results, climate characteristics, and environmental characteristics to obtain assessment results. Candidate prevention and control plans are developed by evaluating and identifying the results and regional meteorological information, and the optimal prevention and control plan is selected.

2. The method for integrated assessment and control of pests and diseases in passion fruit cultivation according to claim 1, characterized in that, The process of dividing the target region into n different sub-regions and preprocessing the acquired information specifically includes: Divide the target area into n different sub-regions and assign each sub-region a unique label number; Acquire plant image information, environmental feature information, regional meteorological information, climate feature information, and regional pest capture quantity information for each sub-region; The environmental characteristics information includes: ambient temperature and humidity, soil temperature and humidity, and soil pH value; The acquired information is preprocessed by screening, filtering, and noise reduction.

3. The method for integrated assessment and control of pests and diseases in passion fruit cultivation according to claim 1, characterized in that, The process of identifying and processing the plant image information and environmental feature information of each sub-region to obtain n identification result information specifically includes: A recognition model is built based on YOLOv5, and the recognition model is subjected to deep learning and training to obtain a recognition model that meets the expectations. The plant image information and environmental feature information of each sub-region are imported into the recognition model to obtain n recognition result information; The identification results include: disease type information, pest type information, and environmental suitability information.

4. The method for integrated assessment and control of pests and diseases in passion fruit cultivation according to claim 1, characterized in that, The method employs a clustering algorithm to classify and merge all sub-regions, resulting in m merged sub-regions. The severity of disease or pest infestation is calculated for each merged sub-region, yielding disease and pest severity information for each merged sub-region. Specifically, this includes: The disease and pest types in each sub-region are obtained by identifying the results. A clustering algorithm is used to classify each sub-region, and sub-regions of the same category are merged to obtain merged sub-regions. Each sub-region is divided into four categories: A, B, C, and D. Category A is the region with diseases, Category B is the region with pests, Category C is the region with both diseases and pests, and Category D is the region without diseases or pests. By analyzing the area of ​​lesions on plants in each merged subregion and the number of pests captured per unit time, information on the severity of pests and diseases in each merged subregion can be obtained.

5. The method for integrated assessment and control of pests and diseases in passion fruit cultivation according to claim 4, characterized in that, The method of obtaining pest and disease severity information for each merged sub-region by using information on the area of ​​lesions on plants in each merged sub-region and the number of pests captured per unit time also includes: The plant image information of each merged sub-region is processed into grayscale to obtain grayscale plant image information; The grayscale plant images are classified using the K-means clustering algorithm to obtain classified grayscale plant images, and then the classified grayscale plant images are denoised. Extract the contour information of the plant and plant lesions, calculate the pixel area S1 of the plant in the classified grayscale plant image information and define it as the total area of ​​the plant in the region, and calculate the pixel area S2 of the plant lesions in the classified grayscale plant image information and define it as the area of ​​the plant lesions in the region. The disease severity information for each merged sub-region is calculated by using the total area of ​​plants in the region and the area of ​​disease spots on plants in the region. The specific formula for calculating the severity of the disease is as follows: In the formula, D i The disease severity, total plant area in region S1, and lesion area in region S2 are all considered.

6. The method for integrated assessment and control of diseases and pests in passion fruit cultivation according to claim 4, characterized in that, The method of obtaining pest and disease severity information for each merged sub-region by using information on the area of ​​lesions on plants in each merged sub-region and the number of pests captured per unit time also includes: The number of pests captured per unit time is calculated by the regional pest capture information, which is used to determine the degree of pest infestation. The threshold for judging the degree of pest infestation is set based on the number of pests captured per unit time. The calculated number of pests captured per unit time is compared with the threshold for judging the degree of pest infestation to obtain the degree of pest infestation in each merged sub-region. The specific formula for calculating the number of pests captured per unit time is as follows: In the formula, C p The number of pests captured per unit time, Q p T represents the number of pests captured in the area, and T represents the total time spent capturing pests in the area.

7. The method for integrated assessment and control of pests and diseases in passion fruit cultivation according to claim 1, characterized in that, The comprehensive assessment of pests and diseases in each merged sub-region, and the resulting assessment information, specifically include: Obtain information on disease severity, pest severity, identification results, climate characteristics, and environmental characteristics for each merged sub-region; A comprehensive assessment model for pests and diseases is constructed, and the comprehensive assessment model for pests and diseases is subjected to deep learning and training to obtain a comprehensive assessment model for pests and diseases that meets the expectations. By importing information on disease severity, pest severity, identification results, climate characteristics, and environmental characteristics into the integrated pest management model, assessment results are obtained.

8. The method for integrated assessment and control of pests and diseases in passion fruit cultivation according to claim 1, characterized in that, The process of formulating candidate prevention and control plans based on evaluation results, identification results, and regional meteorological information, and selecting the optimal prevention and control plan, specifically includes: Pest and disease control examples are obtained based on big data retrieval, forming a control example dataset; Candidate prevention and control plans will be developed by combining assessment results, identification results, and regional meteorological information with prevention and control case datasets. Extract the duration of control efficacy of candidate control programs and use it as the control weight of the candidate control programs. Sort the candidate control programs to obtain a control efficacy duration ranking table. Based on the assessment results, disease severity, and pest severity information of each merged sub-region, combined with the control efficacy duration ranking table, the optimal control plan is selected.

9. A comprehensive assessment and control system for diseases and pests in passion fruit cultivation, characterized in that, The system includes a memory and a processor. The memory contains a program for integrated assessment and control of pests and diseases in passion fruit cultivation. When the processor executes the program for integrated assessment and control of pests and diseases in passion fruit cultivation, it performs the following steps: The target area is divided into n different sub-regions. Plant image information, environmental feature information, climate feature information, regional meteorological information, and regional pest capture quantity information are obtained for each sub-region. The obtained information is then preprocessed. The plant image information and environmental feature information of each sub-region are obtained and processed to identify n identification result information; Clustering algorithm is used to classify and merge all sub-regions to obtain m merged sub-regions. The degree of disease or pest infestation in each merged sub-region is calculated to obtain the disease and pest infestation information of each merged sub-region. A comprehensive assessment of pests and diseases in each sub-region is conducted using information on disease severity, pest severity, environmental characteristics, climate characteristics, and regional meteorological information to obtain the assessment results. Candidate prevention and control plans are developed by evaluating and identifying the results and regional meteorological information, and the optimal prevention and control plan is selected.

10. The integrated pest and disease assessment and control system for passion fruit cultivation according to claim 9, characterized in that, The process of formulating candidate prevention and control plans based on evaluation results, identification results, and regional meteorological information, and selecting the optimal prevention and control plan, specifically includes: Pest and disease control examples are obtained based on big data retrieval, forming a control example dataset; Candidate prevention and control plans will be developed by combining assessment results, identification results, and regional meteorological information with prevention and control case datasets. Extract the duration of control efficacy of candidate control programs and use it as the control weight of the candidate control programs. Sort the candidate control programs to obtain a control efficacy duration ranking table. Based on the assessment results, disease severity, and pest severity information of each merged sub-region, combined with the control efficacy duration ranking table, the optimal control plan is selected.

Images