Intelligent laboratory management method for agricultural data processing

Abstract

The invention relates to the technical field of agricultural data processing, in particular to an intelligent laboratory management method for agricultural data processing. The method comprises the following steps: acquiring crop growth indexes; performing comparative learning based on the disease image of the target crop and the crop disease image of the appearance growth index to generate an appearance growth analysis result of the crop; and the information management system based on the agricultural data intelligent laboratory obtains basic data of the target crop, analyzes the basic data of the target crop based on the non-appearance growth index, and generates a non-appearance growth analysis result of the crop. The growth condition of the crops is comprehensively known through the appearance growth analysis result of the crops and the non-appearance growth analysis result of the crops, the agricultural data processing efficiency can be improved, and the crop growth monitoring efficiency is further improved.

Description

Technical Field

[0001] The invention relates to the technical field of agricultural data processing, and in particular to an intelligent laboratory management method for agricultural data processing. Background Art

[0002] With the rapid development of agricultural science and technology, agricultural production is increasingly dependent on data. Traditional agricultural management methods have problems such as incomplete data collection, low processing efficiency, and insufficient decision support, which seriously restrict the improvement of agricultural production efficiency and the optimization of agricultural product quality. In order to meet these challenges, agricultural data processing technology came into being and gradually became an important support for the development of modern agriculture.

[0003] Existing agricultural data processing technology has shortcomings: Incomplete data collection: Data collection in traditional agricultural laboratories mainly relies on manual records, which has problems such as data omissions and large errors, making it difficult to provide comprehensive and accurate data support for subsequent data processing and analysis.

[0004] Low data processing efficiency: Most existing agricultural data processing systems use a single algorithm or model, which makes it difficult to cope with complex and changeable agricultural data, resulting in low data processing efficiency and inability to meet the real-time and accuracy requirements of agricultural production.

[0005] Insufficient decision support: Due to the limitation of data processing capacity, the existing agricultural laboratory management methods are obviously insufficient in providing decision support and are unable to provide accurate and effective management suggestions for agricultural production.

[0006] Low system integration: The data sharing and system integration between different agricultural laboratories are low, resulting in serious data silos, making it difficult to achieve comprehensive integration and efficient use of agricultural data.

[0007] Therefore, an intelligent laboratory management method for agricultural data processing is urgently needed to solve the above problems. Summary of the invention

[0008] The purpose of the present invention is to provide an intelligent laboratory management method for agricultural data processing: to solve the technical problem of low efficiency of agricultural data processing in existing solutions for agricultural data processing because data collection in traditional agricultural laboratories mainly relies on manual records.

[0009] The purpose of the present invention can be achieved through the following technical solutions: An intelligent laboratory management method for agricultural data processing, applied to an information management system of an agricultural data intelligent laboratory, the method comprising: Acquire crop growth indicators, where the crop growth indicators include appearance growth indicators and non-appearance growth indicators; The information management system based on the agricultural data intelligent laboratory obtains the image of the target crop, inputs the image of the target crop into the fitness image enhancement model, outputs the enhanced image of the target crop, and inputs the enhanced image of the target crop into the image segmentation model, outputs the disease image of the target crop, and performs comparative learning based on the disease image of the target crop and the disease image of the crop with the appearance growth index, and generates the appearance growth analysis result of the crop; The information management system based on the agricultural data intelligent laboratory obtains the basic data of the target crops, wherein the basic data of the target crops include the soil element content data and the drug data corresponding to the crops, and analyzes the basic data of the target crops based on the non-appearance growth indicators to generate the non-appearance growth analysis results of the crops; The crop appearance growth analysis results and the crop non-appearance growth analysis results are used to generate a crop growth report, which is sent to the agricultural data intelligent laboratory management data center.

[0010] Furthermore, the image of the target crop is input into the fitness image enhancement model, and the enhanced image of the target crop is outputted, which includes the following processes: The intensity values ​​of edge image pixels are extracted from the image of the target crop through the Sobel edge operator, and the intensity values ​​are accumulated to obtain the sum of the intensity values ​​of the edge image pixels. ; Count the number of pixels in the edge image whose intensity values ​​are higher than the preset intensity threshold, and record this number as the number of edge pixels ; Calculate the entropy value of the enhanced image : ; in, Indicates the edge image pixel The probability of occurrence of an intensity value; The image of the target crop is divided into image blocks, based on The image blocks are used to calculate the compactness of the enhanced image. : ; ; in, Represents an image block At each pixel The sum of the contrasts at represents the convolution operator, , are two Gaussian function filters, and the size of the Gaussian kernel of the two Gaussian function filters , The calculation is as follows: ; ; in, represents the Gaussian function filter parameters, It means taking the maximum value of M and N, where M represents the number of rows of the target crop image, N represents the number of columns of the target crop image, and V represents the frequency at which the passband of the bottom pass filter reaches its peak; based on , , and Calculate the fitness value of image enhancement : ; Based on image enhancement fitness value Determine the image enhancement effect of the target crop: determine the image enhancement fitness value Whether it exceeds a preset fitness value threshold, if so, the enhanced image of the target crop is output, if not, the enhanced image of the target crop is not output.

[0011] Furthermore, the fitness image enhancement model includes at least one of a histogram equalization image enhancement model, a nonlinear stretching image enhancement model, a logarithmic transformation image enhancement model and a power method transformation image enhancement model.

[0012] Furthermore, the enhanced target crop image is input into the image segmentation model, and the target crop disease image is output, which specifically includes the following process: Step 1: record the pixels in the enhanced target crop image as data points, randomly select K data points as initial cluster centers, and then The initial cluster centers are used to obtain the optimal cluster centers; Step 2: Calculate the membership: Based on the optimal cluster center, calculate the Euclidean distance value from each data point to each cluster center, and use the Euclidean distance value to update the membership of each data point to each cluster; Step 3: Update the existing cluster center according to the new membership value; Step 4: Repeat steps 2 and 3 until the cluster center does not change or exceeds the predetermined number of iterations; Step 5: Output the neighborhood range image corresponding to the cluster center. The area image corresponding to the cluster center is the disease image of the target crop, wherein the neighborhood range image is the image of the target crop within the preset range corresponding to the cluster center.

[0013] Furthermore, based on the objective function The specific process of obtaining the optimal cluster center for the initial cluster center is as follows: ; in, is the number of initial cluster centers, The number of pixels in the enhanced image of the target crop, represents the membership of pixel i to the kth initial cluster center, Represents the Euclidean distance from pixel i to the kth initial cluster center.

[0014] Furthermore, comparative learning is performed based on the disease images of the target crops and the disease images of the crops with appearance growth indicators to generate the appearance growth analysis results of the crops, which specifically includes the following processes: Comparative learning is performed on the disease images of target crops based on the crop disease images of appearance growth indicators to obtain the representation learned by the node; Retrieve the representation of the appearance anomaly indicator and compare and parse it with the representation learned by the node: Determine whether the comparison node shows abnormal color indicators. If so, the target crop has abnormal color indicators. Determine whether the comparison node shows abnormal indicators of Huanglongbing. If so, the target crop has abnormal Huanglongbing. Determine whether the representation of the comparison node shows abnormal shape change indicators. If so, the target crop has abnormal shape change. The abnormalities existing in the target crops are recorded as the results of the appearance growth analysis of the crops.

[0015] Furthermore, the basic data of the target crops are analyzed based on the non-appearance growth indicators to generate the non-appearance growth analysis results of the crops, which specifically includes the following processes: Based on the basic data of the target crops, the soil element content data corresponding to the crops are obtained; based on the soil element content data, the number of soil nutrient element types and the total content of soil nutrient element types are obtained; based on the non-appearance growth indicators, the number of soil nutrient element types that the target crops should have and the total content of soil nutrient element types that the target crops should have are obtained; the ratio YS of the number of soil nutrient element types to the number of soil nutrient element types that the target crops should have is calculated; the ratio YSH of the total content of soil nutrient element types to the total content of soil nutrient element types that the target crops should have is calculated; Based on the basic data of the target crop, obtain the drug data, obtain the number of drug types used to irrigate the crop based on the drug data, obtain the number of drug types that should be irrigated on the crop based on the non-appearance growth index, and calculate the ratio YJ of the number of drug types irrigated on the crop to the number of drug types that should be irrigated on the crop; Substituting YS, YSH and YJ into the non-appearance growth index calculation formula, the non-appearance growth index LMS is obtained. The calculation formula is as follows: ; in, is a non-zero constant, , are weights, is 0.6, is 0.4; The non-appearance growth index LMS is recorded as the non-appearance growth analysis result of the crop.

[0016] Compared with the existing solutions, the present invention achieves the following beneficial effects: The present invention obtains crop growth indicators; an information management system based on an agricultural data intelligent laboratory obtains an image of a target crop, inputs the image of the target crop into a fitness image enhancement model, outputs an enhanced image of the target crop, and inputs the enhanced image of the target crop into an image segmentation model, outputs a disease image of the target crop, and compares and studies the disease image of the target crop and the crop disease image of the appearance growth indicator to generate an appearance growth analysis result of the crop; an information management system based on an agricultural data intelligent laboratory obtains basic data of the target crop, wherein the basic data of the target crop includes land element content data and drug data corresponding to the crop, analyzes the basic data of the target crop based on the non-appearance growth indicator, and generates a non-appearance growth analysis result of the crop. By comprehensively understanding the growth of the crop through the appearance growth analysis results of the crop and the non-appearance growth analysis results of the crop, the efficiency of agricultural data processing can be improved, and the monitoring efficiency of crop growth can be further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 is a workflow diagram of an intelligent laboratory management method for agricultural data processing according to an embodiment of the present invention; Figure 2This is a workflow diagram of another intelligent laboratory management method for agricultural data processing according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, well-known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0021] This embodiment provides an intelligent laboratory management method for agricultural data processing, which is applied to the information management system of an agricultural data intelligent laboratory. The system can obtain images of target crops in a specific area based on image sensors, and can obtain basic data of the target crops based on sensors. The sensors may include land composition detection sensors and drug detection sensors.

[0022] Figure 1 is a workflow diagram of an intelligent laboratory management method for agricultural data processing according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps: Step S101: Acquire crop growth indicators, wherein the crop growth indicators include appearance growth indicators and non-appearance growth indicators; Step S102: acquiring an image of a target crop based on the information management system of the agricultural data intelligent laboratory, inputting the image of the target crop into a fitness image enhancement model, and outputting an enhanced image of the target crop; Step S103: inputting the enhanced image of the target crop into the image segmentation model, and outputting the disease image of the target crop; Step S104: performing comparative learning based on the disease image of the target crop and the crop disease image of the appearance growth index to generate the appearance growth analysis result of the crop; Step S105: acquiring basic data of target crops based on the information management system of the agricultural data intelligent laboratory, wherein the basic data of the target crops include soil element content data and drug data corresponding to the crops, analyzing the basic data of the target crops based on non-appearance growth indicators, and generating non-appearance growth analysis results of the crops; Step S106: Generate a crop growth report based on the crop appearance growth analysis results and the crop non-appearance growth analysis results, and send it to the agricultural data intelligent laboratory management data center.

[0023] In summary, the present invention obtains crop growth indicators; the information management system based on the agricultural data intelligent laboratory obtains the image of the target crop, and inputs the image of the target crop into the fitness image enhancement model, outputs the enhanced image of the target crop, and inputs the enhanced image of the target crop into the image segmentation model, outputs the disease image of the target crop, and compares and studies the disease image of the target crop and the crop disease image of the appearance growth index to generate the appearance growth analysis result of the crop; the information management system based on the agricultural data intelligent laboratory obtains the basic data of the target crop, wherein the basic data of the target crop includes the land element content data and the drug data corresponding to the crop, and analyzes the basic data of the target crop based on the non-appearance growth index to generate the non-appearance growth analysis result of the crop. Through the appearance growth analysis results of the crop and the non-appearance growth analysis results of the crop to fully understand the growth of the crop, the efficiency of agricultural data processing can be improved, and the monitoring efficiency of crop growth can be further improved.

[0024] In some embodiments, inputting the image of the target crop into the fitness image enhancement model and outputting the enhanced image of the target crop includes the following process: The intensity values ​​of edge image pixels are extracted from the image of the target crop through the Sobel edge operator, and the intensity values ​​are accumulated to obtain the sum of the intensity values ​​of the edge image pixels. ; Count the number of pixels in the edge image whose intensity values ​​are higher than the preset intensity threshold, and record this number as the number of edge pixels ; Calculate the entropy value of the enhanced image : ; in, Indicates the edge image pixel The probability of occurrence of an intensity value; The image of the target crop is divided into image blocks, based on The image blocks are used to calculate the compactness of the enhanced image. : ; ; in, Represents an image block At each pixel The sum of the contrasts at represents the convolution operator, , are two Gaussian function filters, and the size of the Gaussian kernel of the two Gaussian function filters , The calculation is as follows: ; ; in, represents the Gaussian function filter parameters, It means taking the maximum value of M and N, where M represents the number of rows of the target crop image, N represents the number of columns of the target crop image, and V represents the frequency at which the passband of the bottom pass filter reaches its peak; based on , , and Calculate the fitness value of image enhancement : ; Based on image enhancement fitness value Determine the image enhancement effect of the target crop: determine the image enhancement fitness value Whether it exceeds a preset fitness value threshold, if so, the enhanced image of the target crop is output, if not, the enhanced image of the target crop is not output.

[0025] It is worth noting that the steps of Sobel operator edge extraction usually include: Grayscale: Convert a color image to a grayscale image, because the Sobel operator is usually applied to grayscale images, which is easier to handle and faster to calculate.

[0026] Calculate gradient: Apply Sobel operators in the horizontal and vertical directions to the grayscale image. The Sobel operator uses a 3×3 convolution kernel to perform convolution operations on the image to obtain gradient images in the horizontal direction and gradient images in the vertical direction respectively.

[0027] Merge gradient images: Merge the horizontal and vertical gradient images into a gradient magnitude image. The merging method is usually to calculate the gradient magnitude of each pixel, that is, the square root of the sum of the squares of the horizontal and vertical gradients.

[0028] Threshold processing: Perform threshold processing on the gradient magnitude image, and regard the pixels with gradient magnitude greater than a certain threshold as edge pixels, and the rest as non-edge pixels. This step can help remove noise and segment the edge area.

[0029] After obtaining the edge image, to calculate the sum of the intensities of the edge pixels, you can follow the steps below: Traverse the edge image: traverse each pixel in the edge image.

[0030] Determine edge pixels: Determine whether the current pixel is an edge pixel based on the result of threshold processing.

[0031] Accumulate edge pixel intensities: If it is an edge pixel, add its intensity value to the sum.

[0032] It is worth noting that the fitness image enhancement model includes at least one of the following image enhancement models: a histogram equalization image enhancement model, a nonlinear stretching image enhancement model, a logarithmic transformation image enhancement model, and a power method transformation image enhancement model.

[0033] In some embodiments, the enhanced target crop image is input into the image segmentation model, and the target crop disease image is output, which specifically includes the following process: Step 1: record the pixels in the enhanced target crop image as data points, randomly select K data points as initial cluster centers, and then The initial cluster centers are used to obtain the optimal cluster centers; Step 2: Calculate the membership: Based on the optimal cluster center, calculate the Euclidean distance value from each data point to each cluster center, and use the Euclidean distance value to update the membership of each data point to each cluster; Step 3: Update the existing cluster center according to the new membership value; Step 4: Repeat steps 2 and 3 until the cluster center does not change or exceeds the predetermined number of iterations; Step 5: Output the neighborhood range image corresponding to the cluster center. The area image corresponding to the cluster center is the disease image of the target crop, wherein the neighborhood range image is the image of the target crop within the preset range corresponding to the cluster center.

[0034] Furthermore, based on the objective function The specific process of obtaining the optimal cluster center for the initial cluster center is as follows: ; in, is the number of initial cluster centers, The number of pixels in the enhanced image of the target crop, represents the membership of pixel i to the kth initial cluster center, Represents the Euclidean distance from pixel i to the kth initial cluster center.

[0035] In some embodiments, the comparative learning based on the disease image of the target crop and the crop disease image of the appearance growth index to generate the appearance growth analysis result of the crop specifically includes the following process: Comparative learning is performed on the disease images of target crops based on the crop disease images of appearance growth indicators to obtain the representation learned by the node; Retrieve the representation of the appearance anomaly indicator and compare and parse it with the representation learned by the node: Determine whether the comparison node shows abnormal color indicators. If so, the target crop has abnormal color indicators. Determine whether the comparison node shows abnormal indicators of Huanglongbing. If so, the target crop has abnormal Huanglongbing. Determine whether the representation of the comparison node shows abnormal shape change indicators. If so, the target crop has abnormal shape change. The abnormalities existing in the target crops are recorded as the results of the appearance growth analysis of the crops.

[0036] In some embodiments, analyzing the basic data of the target crop based on the non-appearance growth index to generate the non-appearance growth analysis result of the crop specifically includes the following process: Step S201: based on the basic data of the target crop, obtaining the soil element content data corresponding to the crop, obtaining the number of soil nutrient element types and the total content of the soil nutrient element types based on the soil element content data, and obtaining the number of soil nutrient element types and the total content of the soil nutrient element types that the target crop should have based on the non-appearance growth index; Step S202: Calculate the ratio YS of the number of soil nutrient element types to the number of soil nutrient element types that the target crop should have, and calculate the ratio YSH of the total content of soil nutrient element types to the total content of soil nutrient element types that the target crop should have; Step S203: obtaining drug data based on the basic data of the target crop, obtaining the number of drug types used for irrigating the crop based on the drug data, obtaining the number of drug types that should be irrigated with the crop based on the non-appearance growth index, and calculating the ratio YJ of the number of drug types used for irrigating the crop to the number of drug types that should be irrigated with the crop; Step S204: Substitute YS, YSH and YJ into the non-appearance growth index calculation formula to obtain the non-appearance growth index LMS, which is as follows: ; in, is a non-zero constant, , are weights, is 0.6, is 0.4; The non-appearance growth index LMS is recorded as the non-appearance growth analysis result of the crop.

[0037] Further, it is determined whether the non-appearance growth index LMS exceeds a preset non-appearance growth index threshold. If so, it is determined that the crop meets the non-appearance growth index requirement. If not, it is determined that the crop does not meet the non-appearance growth index requirement.

[0038] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0039] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0040] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0041] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only for some logical functions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0042] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0043] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent laboratory management method for agricultural data processing, characterized in that: An information management system applied to an agricultural data intelligence laboratory, the method comprising: Acquire crop growth indicators, where the crop growth indicators include appearance growth indicators and non-appearance growth indicators; The information management system based on the agricultural data intelligent laboratory obtains the image of the target crop, inputs the image of the target crop into the fitness image enhancement model, outputs the enhanced image of the target crop, and inputs the enhanced image of the target crop into the image segmentation model, outputs the disease image of the target crop, and performs comparative learning based on the disease image of the target crop and the disease image of the crop with the appearance growth index, and generates the appearance growth analysis result of the crop; The information management system based on the agricultural data intelligent laboratory obtains the basic data of the target crops, wherein the basic data of the target crops include the soil element content data and the drug data corresponding to the crops, and analyzes the basic data of the target crops based on the non-appearance growth indicators to generate the non-appearance growth analysis results of the crops; The crop appearance growth analysis results and the crop non-appearance growth analysis results are used to generate a crop growth report, which is sent to the agricultural data intelligent laboratory management data center.

2. The intelligent laboratory management method for agricultural data processing according to claim 1, characterized in that: Inputting the target crop image into the fitness image enhancement model and outputting the enhanced target crop image includes the following processes: The intensity values ​​of edge image pixels are extracted from the image of the target crop through the Sobel edge operator, and the intensity values ​​are accumulated to obtain the sum of the intensity values ​​of the edge image pixels. ; Count the number of pixels in the edge image whose intensity values ​​are higher than the preset intensity threshold, and record this number as the number of edge pixels ; Calculate the entropy value of the enhanced image : ； in, Indicates the edge image pixel The probability of occurrence of an intensity value; The image of the target crop is divided into image blocks, based on The image blocks are used to calculate the compactness of the enhanced image. : ； ； in, Represents an image block At each pixel The sum of the contrasts at represents the convolution operator, , are two Gaussian function filters, and the size of the Gaussian kernel of the two Gaussian function filters , The calculation is as follows: ； ； in, represents the Gaussian function filter parameters, It means taking the maximum value of M and N, where M represents the number of rows of the target crop image, N represents the number of columns of the target crop image, and V represents the frequency at which the passband of the bottom pass filter reaches its peak; based on , , and Calculate the fitness value of image enhancement : ； Based on image enhancement fitness value Determine the image enhancement effect of the target crop: determine the image enhancement fitness value Whether it exceeds a preset fitness value threshold, if so, the enhanced image of the target crop is output, if not, the enhanced image of the target crop is not output.

3. The intelligent laboratory management method for agricultural data processing according to claim 2 is characterized in that: The fitness image enhancement model includes at least one of a histogram equalization image enhancement model, a nonlinear stretching image enhancement model, a logarithmic transformation image enhancement model and a power method transformation image enhancement model.

4. The intelligent laboratory management method for agricultural data processing according to claim 1, characterized in that: Inputting the enhanced target crop image into the image segmentation model and outputting the target crop disease image specifically includes the following processes: Step 1: record the pixels in the enhanced target crop image as data points, randomly select K data points as initial cluster centers, and then The initial cluster centers are used to obtain the optimal cluster centers; Step 2: Calculate the membership: Based on the optimal cluster center, calculate the Euclidean distance value from each data point to each cluster center, and use the Euclidean distance value to update the membership of each data point to each cluster; Step 3: Update the existing cluster center according to the new membership value; Step 4: Repeat steps 2 and 3 until the cluster center does not change or exceeds the predetermined number of iterations; Step 5: Output the neighborhood range image corresponding to the cluster center. The area image corresponding to the cluster center is the disease image of the target crop, wherein the neighborhood range image is the image of the target crop within the preset range corresponding to the cluster center.

5. The intelligent laboratory management method for agricultural data processing according to claim 4 is characterized in that: Based on the objective function The specific process of obtaining the optimal cluster center for the initial cluster center is as follows: ； in, is the number of initial cluster centers, is the number of pixels in the enhanced image of the target crop, represents the membership of pixel i to the kth initial cluster center, Represents the Euclidean distance from pixel i to the kth initial cluster center.

6. The intelligent laboratory management method for agricultural data processing according to claim 1, characterized in that: Based on the comparative learning of the target crop disease images and the crop disease images of the appearance growth index, the generation of crop appearance growth analysis results specifically includes the following processes: Comparative learning is performed on the disease images of target crops based on the crop disease images of appearance growth indicators to obtain the representation learned by the node; Retrieve the representation of the appearance anomaly indicator and compare and parse it with the representation learned by the node: Determine whether the comparison node shows abnormal color indicators. If so, the target crop has abnormal color indicators. Determine whether the comparison node shows abnormal indicators of Huanglongbing. If so, the target crop has abnormal Huanglongbing. Determine whether the representation of the comparison node shows abnormal shape change indicators. If so, the target crop has abnormal shape change. The abnormalities existing in the target crops are recorded as the results of the appearance growth analysis of the crops.

7. The intelligent laboratory management method for agricultural data processing according to claim 1, characterized in that: The basic data of target crops are analyzed based on non-appearance growth indicators to generate non-appearance growth analysis results of crops, which specifically includes the following processes: Based on the basic data of the target crops, the soil element content data corresponding to the crops are obtained; based on the soil element content data, the number of soil nutrient element types and the total content of soil nutrient element types are obtained; based on the non-appearance growth indicators, the number of soil nutrient element types that the target crops should have and the total content of soil nutrient element types that the target crops should have are obtained; the ratio YS of the number of soil nutrient element types to the number of soil nutrient element types that the target crops should have is calculated; the ratio YSH of the total content of soil nutrient element types to the total content of soil nutrient element types that the target crops should have is calculated; Based on the basic data of the target crop, obtain the drug data, obtain the number of drug types used to irrigate the crop based on the drug data, obtain the number of drug types that should be irrigated on the crop based on the non-appearance growth index, and calculate the ratio YJ of the number of drug types irrigated on the crop to the number of drug types that should be irrigated on the crop; Substituting YS, YSH and YJ into the non-appearance growth index calculation formula, the non-appearance growth index LMS is obtained. The calculation formula is as follows: ； in, is a non-zero constant, , are weights, is 0.6, is 0.4; The non-appearance growth index LMS is recorded as the non-appearance growth analysis result of the crop.

Images