Method and system for changing planting environment according to grape planting data

Abstract

The invention relates to the technical field of planting, in particular to a method and system for changing a planting environment according to grape planting data, and the method comprises the steps: obtaining growth evaluation value data of each grape seedling, the growth evaluation value data comprising a positive growth evaluation value and a negative growth evaluation value of the grape seedling; calculating a first grape seedling growth evaluation index according to the positive growth evaluation value and the negative growth evaluation value, and calculating a second grape seedling growth evaluation index after processing for a period of time; if the second time sequence number is in an ascending order for the first time sequence number, extracting the cost input value of each grape seedling recorded in the first processing strategy, and solving the optimal first processing strategy combination by taking the minimum cost input value as an optimization target; and driving the control terminal to control the corresponding processing equipment to execute the processing control action according to the instruction set. The grape planting monitoring system has the advantages that multi-element intelligent monitoring can be performed on grape planting, and low-cost planting environment improvement is realized while high-quality growth of grape seedlings is realized.

Description

Technical Field

[0001] This invention relates to the field of planting technology, and in particular to a method and system for changing the planting environment based on grape planting data. Background Technology

[0002] Traditional grape cultivation faces various challenges, requiring attention to factors such as temperature, humidity, and pests and diseases.

[0003] During the growth of grape seedlings, multiple factors such as temperature, humidity, and pests and diseases can deteriorate. There is an urgent need for intelligent monitoring of multiple factors in grape cultivation, and to achieve high-quality growth of grape seedlings while improving them at low cost. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a method and system for changing the planting environment based on grape planting data, which can carry out multi-element intelligent monitoring of grape planting, and achieve low-cost improvement of the planting environment while realizing high-quality growth of grape seedlings.

[0005] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0006] A method for altering the growing environment based on grape growing data, including

[0007] Acquire growth assessment data for each grape seedling. The growth assessment data includes positive growth assessment values ​​and negative growth assessment values. Positive growth assessment values ​​include the number of leaves, leaf size, root and stem height, and root and stem thickness. Negative growth assessment values ​​include the area affected by pests and diseases and the rate of spread of pests and diseases.

[0008] The first grape seedling growth assessment index is calculated based on the positive and negative growth assessment values. Each grape seedling is then sorted from largest to smallest according to the first grape seedling growth assessment index and a first treatment strategy is applied. After a period of treatment, the second grape seedling growth assessment index is calculated based on the positive and negative growth assessment values. The second grape seedlings are then sorted from largest to smallest according to the second grape seedling growth index.

[0009] If the second time sorting number is sorted in ascending order relative to the first time sorting number, the cost input value of each grape seedling recorded in the first processing strategy is extracted. The product of the proportion of the negative growth evaluation value and its weight factor of the disease and pest area value and the disease and pest spread rate value of each grape seedling falling into the growth evaluation value data and the proportion of the positive growth evaluation value and its weight factor of the leaf number value, leaf size value, root and stem height value, and root and stem thickness value of each grape seedling falling into the growth evaluation value data exceeds a preset proportion threshold. The optimal combination of the first processing strategy is solved with the minimum cost input value as the optimization objective.

[0010] The control terminal is driven to control the corresponding processing equipment to perform processing control actions according to the instruction set.

[0011] As a preferred option, the specific formula for calculating the grape seedling growth assessment data is as follows: E n =(α1·X1+α2·X2+α3·X3+α4·X4)-(δ1·Y1+δ2·Y2), where, E n Let α1 be the growth assessment value data for the nth grape seedling, α2 be the coefficient of the number of leaves, α3 be the coefficient of the root and stem height, α4 be the coefficient of the root and stem thickness, δ1 be the coefficient of the area affected by pests and diseases, δ2 be the coefficient of the spread rate of pests and diseases, X1 be the number of leaves, X2 be the coefficient of the leaf size, X3 be the root and stem height, X4 be the root and stem thickness, Y1 be the area affected by pests and diseases, Y2 be the spread rate of pests and diseases, and α1+α2+α3+α4=1, δ1+δ2=1.

[0012] As a preferred option, the specific formula for calculating the cost input value is as follows: Where Q is the cost input value of the first processing strategy, and E n E represents the first measured growth assessment value of the nth grape seedling. n ′ represents the second measurement of the growth assessment value of the nth grape seedling, T represents the time when the first treatment strategy was adopted, and Q' represents the fluctuation value.

[0013] As a preferred method, the values ​​of the number of leaves, leaf size, root and stem height, and root and stem thickness of grape seedlings were normalized, and the normalization was comprehensively analyzed to obtain positive growth evaluation values.

[0014] The values ​​of pest and disease area and pest and disease spread rate were normalized, and the normalized values ​​were comprehensively analyzed to obtain the negative growth assessment value.

[0015] As a preferred method, based on several characteristics of each grape seedling, the suitable range of environmental parameters for each grape seedling is matched in a pre-stored mapping table of grape seedling characteristic combinations and suitable ranges of environmental parameters.

[0016] The suitable ranges of ultraviolet intensity and temperature for each grape seedling were extracted from the suitable range of environmental parameters. Using these suitable ranges, the production environment control requirements for each grape seedling were constructed.

[0017] Based on the environmental adjustment needs of each grape seedling, different supplemental lighting and heating equipment are used to adjust the production environment.

[0018] Preferably, the pest and disease area image is obtained. The features extracted from the pest and disease area image by the current layer encoder module are passed to the current layer reverse mechanism module and the next layer encoder module respectively. After the current layer reverse mechanism module reverses the extracted features, it further extracts features based on the attention mechanism through the current layer feature convolution kernel attention hybrid module. The next layer encoder module continues to pass the extracted features to the current layer and the next layer until the next layer Kan-mamba module extracts deep features. The deep features are sent to multiple expansion branches respectively. The features output by the branch fusion are then concatenated with the output of the previous layer feature convolution kernel attention hybrid module and used as the input of the previous layer decoder module. After the top layer decoder module, the output module outputs the pest and disease area representation segmentation map.

[0019] As a preferred option, the segmentation map representing the area affected by pests and diseases is denoised.

[0020] As a preferred method, the peak signal-to-noise ratio (PSNR) of the segmented image representing the area of ​​pests and diseases is calculated as an image quality assessment value, and a set assessment threshold is used for judgment. When the PSNR is less than the assessment threshold, wavelet thresholding is used to denoise the original image of the area of ​​pests and diseases.

[0021] As a preferred option, the formula for calculating the peak signal-to-noise ratio is as follows:

[0022] `max` represents the maximum value of the image pixels, C and K represent the length and width of the image respectively, and W, ... These represent the images before and after denoising, respectively.

[0023] A system for changing the planting environment based on grape planting data includes a data acquisition module for acquiring growth assessment data for each grape seedling. The growth assessment data includes positive growth assessment values ​​and negative growth assessment values ​​for the grape seedling. Positive growth assessment values ​​include the number of leaves, leaf size, root and stem height, and root and stem thickness of the grape seedling. Negative growth assessment values ​​include the area affected by pests and diseases and the rate of spread of pests and diseases.

[0024] The sorting module is used to calculate the first grape seedling growth evaluation index based on the positive growth evaluation value and the negative growth evaluation value, sort each grape seedling in descending order according to the first grape seedling growth evaluation index and the first processing strategy, and after a period of processing, calculate the second grape seedling growth evaluation index based on the positive growth evaluation value and the negative growth evaluation value, and sort the second grape seedling in descending order according to the second grape seedling growth evaluation index.

[0025] The calculation module is used to extract the cost input value of each grape seedling recorded in the first processing strategy if the second time sorting number is sorted in ascending order relative to the first time sorting number. The product of the proportion of the negative growth evaluation value and its weight factor of the disease and pest area value and the disease and pest spread rate value of each grape seedling falling into the growth evaluation value data and the product of the proportion of the positive growth evaluation value and its weight factor of the leaf number value, leaf size value, root and stem height value, and root and stem thickness value of each grape seedling falling into the growth evaluation value data exceeds a preset proportion threshold. The optimization objective is to minimize the cost input value and solve for the optimal combination of the first processing strategies.

[0026] A control terminal is used to control the corresponding processing device to perform processing control actions according to the instruction set.

[0027] The beneficial effects of using the present invention are as follows:

[0028] 1. Obtain growth assessment data for each grape seedling. The growth assessment data includes positive growth assessment values ​​and negative growth assessment values. Positive growth assessment values ​​include the number of leaves, leaf size, root and stem height, and root and stem thickness. Negative growth assessment values ​​include the area affected by pests and diseases and the rate of spread of pests and diseases.

[0029] The first grape seedling growth assessment index is calculated based on the positive and negative growth assessment values. Each grape seedling is then sorted from largest to smallest according to the first grape seedling growth assessment index and a first treatment strategy is applied. After a period of treatment, the second grape seedling growth assessment index is calculated based on the positive and negative growth assessment values. The second grape seedlings are then sorted from largest to smallest according to the second grape seedling growth index.

[0030] If the second time sorting number is sorted in ascending order relative to the first time sorting number, the cost input value of each grape seedling recorded in the first processing strategy is extracted. The product of the proportion of the negative growth evaluation value and its weight factor of the disease and pest area value and the disease and pest spread rate value of each grape seedling falling into the growth evaluation value data and the proportion of the positive growth evaluation value and its weight factor of the leaf number value, leaf size value, root and stem height value, and root and stem thickness value of each grape seedling falling into the growth evaluation value data exceeds a preset proportion threshold. The optimal combination of the first processing strategy is solved with the minimum cost input value as the optimization objective.

[0031] When the product of the proportion of the disease and pest area value and the disease and pest spread rate value of each grape seedling falling into the negative growth assessment value data and its weighting factor, and the product of the proportion of the leaf number value, leaf size value, root stem height value, and root stem thickness value of each grape seedling falling into the positive growth assessment value data and its weighting factor, is less than 0, it means that the negative growth of this grape seedling is greater than the positive growth and the treatment effect is poor. For cost considerations, it is recommended to remove the grape seedlings and leave enough soil nutrients to support the grape seedlings with better growth, so as to increase the yield and reduce the planting burden.

[0032] 2. The specific formula for calculating the grape seedling growth assessment value is as follows: E n =(α1·X1+α2·X2+α3·X3+α4·X4)-(δ1·Y1+δ2·Y2), where, E n Let α1 be the growth assessment value data for the nth grape seedling, α2 be the coefficient of the number of leaves, α3 be the coefficient of the root and stem height, α4 be the coefficient of the root and stem thickness, δ1 be the coefficient of the area affected by pests and diseases, δ2 be the coefficient of the spread rate of pests and diseases, X1 be the number of leaves, X2 be the coefficient of the leaf size, X3 be the root and stem height, X4 be the root and stem thickness, Y1 be the area affected by pests and diseases, Y2 be the spread rate of pests and diseases, and α1+α2+α3+α4=1, δ1+δ2=1.

[0033] For example, α1=0.4, α2=0.25, α3=0.2, α4=0.15, X1=10, X2=2, X3=12, X4=1, δ1=0.3, δ2=0.7, Y1=5, Y2=10,

[0034] Then E n =0.4*10+0.25*2+0.2*12+0.15*1-0.3*5-0.7*10=-1.45, indicating that the grape seedling is in a negative growth state. The assessment is fast and accurate, and it takes into account the growth stability of the grape seedling while monitoring it in real time, further improving the accuracy of grape seedling assessment.

[0035] 3. The formula for calculating the peak signal-to-noise ratio is as follows:

[0036] `max` represents the maximum value of the image pixels, C and K represent the length and width of the image respectively, and W, ... These represent the images before and after denoising, respectively.

[0037] If the peak signal-to-noise ratio (PSNR) is greater than or equal to the set threshold, the original image is directly input into the grape seedling instance segmentation network for further processing; if the PSNR is less than the set threshold, an improved wavelet thresholding denoising algorithm is used to preprocess the image.

[0038] Then, different pests and diseases are labeled with different sequence numbers. This pest and disease area segmentation network embeds a receptive field feature convolution kernel attention hybrid module. This module extracts pest and disease information through the convolution of receptive field features and uses KAN to assign different weights to features in different channels to achieve multi-dimensional weighting of features. In addition, a pooling layer is added before upsampling to strengthen supervised learning and improve the ability to learn features. A dense expansion module is embedded before the first decoder to enhance the extraction of global context information. In addition, a reverse mechanism module is embedded in the skip connection process of each encoder to solve the problem of gradient vanishing or saturation caused by excessive positive stacking during training. After outputting the segmentation results, the segmentation is evaluated. The final result is output after the evaluation is qualified, which can ensure the accuracy of segmentation and enable the use of different types of insecticides or pesticides for different pests and diseases to improve the insecticidal effect.

[0039] These features and advantages of the present invention will be disclosed in detail in the following specific embodiments and drawings. Attached Figure Description

[0040] The invention will be further described below with reference to the accompanying drawings:

[0041] Figure 1 This is a schematic diagram of a method for changing the planting environment using grape planting data according to Embodiment 1 of the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0043] The concepts involved in this application will first be explained with reference to the accompanying drawings. It should be noted that the following explanation of each concept is only to make the content of this application easier to understand and does not imply any limitation on the scope of protection of this application.

[0044] Example 1:

[0045] A method for altering the growing environment based on grape growing data, such as Figure 1 As shown, including

[0046] Acquire growth assessment data for each grape seedling. The growth assessment data includes positive growth assessment values ​​and negative growth assessment values. Positive growth assessment values ​​include the number of leaves, leaf size, root and stem height, and root and stem thickness. Negative growth assessment values ​​include the area affected by pests and diseases and the rate of spread of pests and diseases.

[0047] The first grape seedling growth assessment index is calculated based on the positive and negative growth assessment values. Each grape seedling is then sorted from largest to smallest according to the first grape seedling growth assessment index and a first treatment strategy is applied. After a period of treatment, the second grape seedling growth assessment index is calculated based on the positive and negative growth assessment values. The second grape seedlings are then sorted from largest to smallest according to the second grape seedling growth index.

[0048] If the second time sorting number is sorted in ascending order relative to the first time sorting number, the cost input value of each grape seedling recorded in the first processing strategy is extracted. The product of the proportion of the negative growth evaluation value and its weight factor of the disease and pest area value and the disease and pest spread rate value of each grape seedling falling into the growth evaluation value data and the proportion of the positive growth evaluation value and its weight factor of the leaf number value, leaf size value, root and stem height value, and root and stem thickness value of each grape seedling falling into the growth evaluation value data exceeds a preset proportion threshold. The optimal combination of the first processing strategy is solved with the minimum cost input value as the optimization objective.

[0049] When the product of the proportion of the disease and pest area value and the disease and pest spread rate value of each grape seedling falling into the negative growth assessment value data and its weighting factor, and the product of the proportion of the leaf number value, leaf size value, root stem height value, and root stem thickness value of each grape seedling falling into the positive growth assessment value data and its weighting factor, is less than 0, it means that the negative growth of this grape seedling is greater than the positive growth and the treatment effect is poor. For cost considerations, it is recommended to remove the grape seedlings and leave enough soil nutrients to support the grape seedlings with better growth, so as to increase the yield and reduce the planting burden.

[0050] Another approach uses positive and negative growth assessment data as input parameters to a grape seedling growth behavior prediction and analysis model. A GRU unit is used to obtain feature vectors with temporal characteristics. A Spatial-ReductionAttention mechanism unit then uses an attention mechanism to obtain weight coefficients corresponding to each feature vector with temporal characteristics. By capturing time dependencies and identifying hidden key factors from the growth assessment data, key temporal information affecting the current growth of the grape seedling can be extracted. By adjusting the weight coefficients, the dynamic extraction of corresponding key influencing factors can be achieved, accurately predicting the growth information of the target grape seedling at the next moment, thus maintaining the grape seedling in a good growth state.

[0051] The control terminal is driven to control the corresponding processing equipment to perform processing control actions according to the instruction set.

[0052] For the area and spread rate of pests and diseases, image analysis technology is used. After capturing leaf images with a high-resolution camera, the area and spread rate are calculated using image processing software. The leaf surface temperature is obtained using an infrared thermometer or thermal imager. The air humidity is obtained using a humidity sensor. The seedling height is obtained using measuring tools or automated image analysis. The seedling stem diameter is obtained using calipers or a dedicated stem measuring instrument.

[0053] The specific formula for calculating the grape seedling growth assessment data is as follows: E n =(α1·X1+α2·X2+α3·X3+α4·X4)-(δ1·Y1+δ2·Y2), where, E n Let α1 be the growth assessment value data for the nth grape seedling, α2 be the coefficient of the number of leaves, α3 be the coefficient of the root and stem height, α4 be the coefficient of the root and stem thickness, δ1 be the coefficient of the area affected by pests and diseases, δ2 be the coefficient of the spread rate of pests and diseases, X1 be the number of leaves, X2 be the coefficient of the leaf size, X3 be the root and stem height, X4 be the root and stem thickness, Y1 be the area affected by pests and diseases, Y2 be the spread rate of pests and diseases, and α1+α2+α3+α4=1, δ1+δ2=1.

[0054] For example, α1=0.4, α2=0.25, α3=0.2, α4=0.15, X1=10, X2=2, X3=12, X4=1, δ1=0.3, δ2=0.7, Y1=5, Y2=10,

[0055] Then E n =0.4*10+0.25*2+0.2*12+0.15*1-0.3*5-0.7*10=-1.45, indicating that the grape seedling is in a negative growth state. The assessment is fast and accurate, and it takes into account the growth stability of the grape seedling while monitoring it in real time, further improving the accuracy of grape seedling assessment.

[0056] The specific formula for calculating the cost input value is as follows: Where Q is the cost input value of the first processing strategy, and E n E represents the first measured growth assessment value of the nth grape seedling. n′ represents the second measured growth assessment value of the nth grape seedling, T represents the time when the first treatment strategy was adopted, and Q' represents the fluctuation value. For example, the cost of irrigating grape seedlings with a large amount of water and the estimated effect of buying pesticides to kill insects are different. The fluctuation values ​​of the two are different. In the short term, watering is more effective and less expensive, while pesticides are less effective and more expensive in the short term.

[0057] The values ​​of leaf quantity, leaf size, root and stem height, and root and stem thickness of grape seedlings were normalized, and the normalization was comprehensively analyzed to obtain positive growth assessment values.

[0058] The values ​​for pest and disease area and pest spread rate were normalized, and a comprehensive analysis of the normalized values ​​was performed to obtain a negative growth assessment value. This reduces the impact of outlier data, such as data with excessively large measurement errors, and improves the accuracy of the assessment.

[0059] Based on several characteristics of each grape seedling, the suitable range of environmental parameters for each grape seedling is matched in a pre-stored mapping table of grape seedling characteristic combinations and suitable ranges of environmental parameters.

[0060] The suitable ranges of ultraviolet intensity and temperature for each grape seedling were extracted from the suitable range of environmental parameters. Using these suitable ranges, the production environment control requirements for each grape seedling were constructed.

[0061] Based on the environmental adjustment needs of each grape seedling, different supplemental lighting and heating equipment are used to adjust the production environment.

[0062] The process involves acquiring an image of the area affected by pests and diseases. The features extracted from the image by the current layer encoder module are passed to the current layer reverse mechanism module and the next layer encoder module. The current layer reverse mechanism module reverses the extracted features and then further extracts features based on the attention mechanism through the current layer feature convolution kernel attention hybrid module. The next layer encoder module continues to pass the extracted features to the current layer and the next layer until the next layer Kan-mamba module extracts deep features. The deep features are then fed into multiple expansion branches, and the features output by the fused branches are concatenated with the output of the previous layer feature convolution kernel attention hybrid module. This concatenation is then used as the input to the previous layer decoder module. Finally, after the top layer decoder module, the output module outputs a segmentation map representing the area affected by pests and diseases.

[0063] Denoise the segmented map representing the area affected by pests and diseases.

[0064] The peak signal-to-noise ratio (PSNR) of the segmented image representing the area of ​​pests and diseases is calculated as an image quality assessment value. The image quality is judged by a set assessment threshold. When the PSNR is less than the assessment threshold, wavelet thresholding is used to denoise the original image of the area of ​​pests and diseases.

[0065] The formula for calculating the peak signal-to-noise ratio is as follows:

[0066] `max` represents the maximum value of the image pixels, C and K represent the length and width of the image respectively, and W, ... These represent the images before and after denoising, respectively.

[0067] If the peak signal-to-noise ratio (PSNR) is greater than or equal to the set threshold, the original image is directly input into the grape seedling instance segmentation network for further processing; if the PSNR is less than the set threshold, an improved wavelet thresholding denoising algorithm is used to preprocess the image.

[0068] Then, different pests and diseases are labeled with different sequence numbers. This pest and disease area segmentation network embeds a receptive field feature convolution kernel attention hybrid module. This module extracts pest and disease information through the convolution of receptive field features and uses KAN to assign different weights to features in different channels to achieve multi-dimensional weighting of features. In addition, a pooling layer is added before upsampling to strengthen supervised learning and improve the ability to learn features. A dense expansion module is embedded before the first decoder to enhance the extraction of global context information. In addition, a reverse mechanism module is embedded in the skip connection process of each encoder to solve the problem of gradient vanishing or saturation caused by excessive positive stacking during training. After outputting the segmentation results, the segmentation is evaluated. The final result is output after the evaluation is qualified, which can ensure the accuracy of segmentation and enable the use of different types of insecticides or pesticides for different pests and diseases to improve the insecticidal effect.

[0069] A system for changing the planting environment based on grape planting data includes a data acquisition module for acquiring growth assessment data for each grape seedling. The growth assessment data includes positive growth assessment values ​​and negative growth assessment values ​​for the grape seedling. Positive growth assessment values ​​include the number of leaves, leaf size, root and stem height, and root and stem thickness of the grape seedling. Negative growth assessment values ​​include the area affected by pests and diseases and the rate of spread of pests and diseases.

[0070] The sorting module is used to calculate the first grape seedling growth evaluation index based on the positive growth evaluation value and the negative growth evaluation value, sort each grape seedling in descending order according to the first grape seedling growth evaluation index and the first processing strategy, and after a period of processing, calculate the second grape seedling growth evaluation index based on the positive growth evaluation value and the negative growth evaluation value, and sort the second grape seedling in descending order according to the second grape seedling growth evaluation index.

[0071] The calculation module is used to extract the cost input value of each grape seedling recorded in the first processing strategy if the second time sorting number is sorted in ascending order relative to the first time sorting number. The product of the proportion of the negative growth evaluation value and its weight factor of the disease and pest area value and the disease and pest spread rate value of each grape seedling falling into the growth evaluation value data and the product of the proportion of the positive growth evaluation value and its weight factor of the leaf number value, leaf size value, root and stem height value, and root and stem thickness value of each grape seedling falling into the growth evaluation value data exceeds a preset proportion threshold. The optimization objective is to minimize the cost input value and solve for the optimal combination of the first processing strategies.

[0072] A control terminal is used to control the corresponding processing device to perform processing control actions according to the instruction set.

[0073] It should be noted that, for the sake of simplicity, the foregoing embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to this application.

[0074] The embodiments of this application have been described in detail above. Specific examples have been used in the illustration. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

[0075] This application is described with reference to flowchart illustrations and / or block diagrams of methods, hardware products, and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0076] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1a process or multiple processes and / or boxes Figure 1 The functions specified in one or more boxes. Memory may include: flash drives, read-only memory (ROM), random access memory (RAM), hard disks or optical disks, etc.

[0077] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce a good effect.

[0078] Those skilled in the art will understand that all or part of the steps in the various methods of any of the above method embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0079] It is understood that any product that is controlled or configured to perform the processing method of the flowchart described in the embodiments of this application, such as the apparatus and computer program product of the above flowchart, falls within the scope of the related products described in this application.

[0080] Obviously, those skilled in the art can make various modifications and variations to the device provided in this application without departing from the spirit and scope of this application. Therefore, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application also intends to include these modifications and variations.

Claims

1. A method for altering the growing environment based on grape growing data, characterized in that, include Acquire growth assessment data for each grape seedling. The growth assessment data includes positive growth assessment values ​​and negative growth assessment values ​​for the grape seedling. The positive growth assessment values ​​include the number of leaves, leaf size, root and stem height, and root and stem thickness. The negative growth assessment values ​​include the area affected by pests and diseases and the rate of spread of pests and diseases. The first grape seedling growth assessment index is calculated based on the positive and negative growth assessment values. Each grape seedling is then sorted from largest to smallest according to the first grape seedling growth assessment index and a first treatment strategy is applied. After a period of treatment, the second grape seedling growth assessment index is calculated based on the positive and negative growth assessment values. The second grape seedling growth index is then sorted from largest to smallest according to the second time period. If the second time sorting number is sorted in ascending order relative to the first time sorting number, the cost input value of each grape seedling recorded in the first processing strategy is extracted. The product of the proportion of the negative growth evaluation value and its weight factor of the disease and pest area value and the disease and pest spread rate value of each grape seedling falling into the growth evaluation value data and the product of the proportion of the positive growth evaluation value and its weight factor of the leaf number value, leaf size value, root and stem height value, and root and stem thickness value of each grape seedling falling into the growth evaluation value data exceeds a preset proportion threshold. The optimal combination of the first processing strategy is solved with the minimum cost input value as the optimization objective. The control terminal is driven to control the corresponding processing equipment to perform processing control actions according to the instruction set.

2. The method for changing the planting environment based on grape planting data as described in claim 1, characterized in that, The specific formula for calculating the grape seedling growth assessment data is as follows: E n =(α1·X1+α2·X2+α3·X3+α4·X4)-(δ1·Y1+δ2·Y2), where, E n Let α1 be the growth assessment value data for the nth grape seedling, α2 be the coefficient of the number of leaves, α3 be the coefficient of the root and stem height, α4 be the coefficient of the root and stem thickness, δ1 be the coefficient of the area affected by pests and diseases, δ2 be the coefficient of the spread rate of pests and diseases, X1 be the number of leaves, X2 be the coefficient of the leaf size, X3 be the root and stem height, X4 be the root and stem thickness, Y1 be the area affected by pests and diseases, Y2 be the spread rate of pests and diseases, and α1+α2+α3+α4=1, δ1+δ2=1.

3. The method for changing the planting environment based on grape planting data as described in claim 2, characterized in that, The specific formula for calculating the cost input value is as follows: Where Q is the cost input value of the first processing strategy, and E n E represents the first measured growth assessment value of the nth grape seedling. n ′ represents the second measurement of the growth assessment value of the nth grape seedling, T represents the time when the first treatment strategy was adopted, and Q' represents the fluctuation value.

4. The method for changing the planting environment based on grape planting data as described in claim 1, characterized in that, The values ​​of leaf quantity, leaf size, root and stem height, and root and stem thickness of the grape seedlings were normalized, and the normalization was comprehensively analyzed to obtain positive growth evaluation values. The values ​​of the area affected by pests and diseases and the rate of spread of pests and diseases were normalized, and a comprehensive analysis of the normalization was performed to obtain a negative growth assessment value.

5. The method for changing the planting environment based on grape planting data as described in claim 1, characterized in that, Based on several characteristics of each grape seedling, the suitable range of environmental parameters for each grape seedling is matched in a pre-stored mapping table of grape seedling characteristic combinations and suitable ranges of environmental parameters. The suitable ranges of ultraviolet intensity and temperature for each grape seedling are extracted from the set of suitable environmental parameters. Using the suitable ranges of ultraviolet intensity and temperature, a pair of production environment control requirements for each grape seedling is constructed. Based on the environmental adjustment needs of each grape seedling, different supplemental lighting and heating equipment are used to adjust the production environment.

6. The method for changing the planting environment based on grape planting data as described in claim 1, characterized in that, The process involves acquiring an image of the area affected by pests and diseases. The features extracted from the image by the current layer encoder module are passed to the current layer reverse mechanism module and the next layer encoder module. The current layer reverse mechanism module reverses the extracted features and then further extracts features based on the attention mechanism through the current layer feature convolution kernel attention hybrid module. The next layer encoder module continues to pass the extracted features to the current layer and the next layer until the next layer Kan-mamba module extracts deep features. The deep features are then fed into multiple expansion branches, and the features output by the fused branches are concatenated with the output of the previous layer feature convolution kernel attention hybrid module. This concatenation is then used as the input to the previous layer decoder module. Finally, after the top layer decoder module, the output module outputs a segmentation map representing the area affected by pests and diseases.

7. The method for changing the planting environment based on grape planting data as described in claim 6, characterized in that, The segmentation map representing the area of ​​pests and diseases is denoised.

8. The method for changing the planting environment based on grape planting data as described in claim 7, characterized in that, The peak signal-to-noise ratio (PSNR) of the segmented image representing the area of ​​pests and diseases is calculated as an image quality assessment value. The image quality is judged by a set assessment threshold. When the PSNR is less than the assessment threshold, wavelet thresholding is used to denoise the original image of the area of ​​pests and diseases.

9. The method for changing the planting environment based on grape planting data as described in claim 8, characterized in that, The formula for calculating the peak signal-to-noise ratio is as follows: `max` represents the maximum value of the image pixels, C and K represent the length and width of the image respectively, and W, ... These represent the images before and after denoising, respectively.

10. A system for altering the growing environment based on grape growing data, characterized in that, It includes a data acquisition module for acquiring growth assessment data for each grape seedling. The growth assessment data includes positive growth assessment values ​​and negative growth assessment values ​​for the grape seedling. The positive growth assessment values ​​include the number of leaves, leaf size, root and stem height, and root and stem thickness of the grape seedling. The negative growth assessment values ​​include the area affected by pests and diseases and the rate of spread of pests and diseases. The sorting module is used to calculate a first grape seedling growth evaluation index based on positive and negative growth evaluation values, sort each grape seedling in descending order of the first grape seedling growth evaluation index and implement a first processing strategy, and after a period of processing, calculate a second grape seedling growth evaluation index based on positive and negative growth evaluation values, and sort the grape seedlings in descending order of the second grape seedling growth evaluation index. The calculation module is used to extract the cost input value of each grape seedling recorded in the first processing strategy if the second time sorting number is sorted in ascending order relative to the first time sorting number. The optimal combination of the first processing strategy is determined by the constraint that the product of the proportion of the pest and disease area value and the pest and disease spread rate value of each grape seedling falling into the negative growth evaluation value data and its weight factor and the product of the proportion of the leaf number value, leaf size value, root stem height value, and root stem thickness value of each grape seedling falling into the positive growth evaluation value data and its weight factor exceeds a preset proportion threshold. The optimization objective is to minimize the cost input value. A control terminal is used to control the corresponding processing device to perform processing control actions according to the instruction set.

Images