Agricultural industry chain information data monitoring, processing and analyzing method

Abstract

The invention relates to the technical field of agricultural information. The method specifically comprises the following steps: S1, crop demand analysis; s2, evaluating the influence of meteorological data; s3, a soil fertilization strategy; s4, crop yield prediction; and S5, market prediction: judging the growth stages of crops in the crop images of each sampling area of the farmland through an image processing technology, matching to obtain the specific nutrient demand corresponding to the growth stages of the crops, and evaluating the influence coefficient of meteorological data on the nutrient demand of the crops by obtaining the meteorological data of the farmland. The method comprises the following steps: generating a soil specific nutrient spatial distribution map through a spatial interpolation technology, generating a variable fertilization prescription map based on influence coefficients of meteorological data on crop nutrient demands and specific nutrient demands corresponding to crop growth stages, and constructing a time sequence model for crop ripening time and yield of each round of crops in history. And obtaining the maturation time and the yield prediction result of the current crop and judging whether early warning is performed or not, thereby improving the agricultural production efficiency and enhancing the agricultural risk management capability.

Description

Technical Field

[0001] The present invention relates to the field of agricultural information technology. Specifically, it is a method for monitoring, processing, and analyzing agricultural industrial chain information data. Background Art

[0002] With the continuous growth of the global population and the increasing requirements for food safety and quality, traditional agricultural production methods are facing huge challenges. The transformation of agriculture towards modernization, technology, and intelligence has become an inevitable trend. In this context, the monitoring and processing of agricultural industrial chain information data have become crucial. The agricultural industrial chain covers multiple links such as planting, breeding, processing, and sales. A large amount of data is generated in each link. Effective monitoring and processing of these data can achieve precise management and optimal allocation of agricultural resources, improve agricultural production efficiency and quality, enhance the risk resistance ability of agriculture, and promote the process of agricultural modernization.

[0003] In recent years, information technology has developed rapidly, and the application of technologies such as the Internet of Things, big data, and artificial intelligence in the agricultural field has gradually increased. However, at present, the monitoring and processing of agricultural industrial chain information data are still in the development stage, and there is still a large gap from the goals of comprehensiveness, efficiency, and intelligence.

[0004] For example, the existing Chinese patent with the application number 202310744208.3 discloses a digital agricultural industrial chain data processing and analysis system. This solution collects, stores, processes, and applies data from different sources in the agricultural data warehouse through the data management unit, and constructs an information system for "traceability and supervision" of agricultural product quality and safety through the industrial end, enabling users to more intuitively understand the changes and turning points of each data, which is beneficial for agricultural decision-making and command.

[0005] However, the following problems exist in the above patent: First, although this solution monitors factors such as environmental parameters and disease conditions during the crop growth process, it does not associate them with historical relevant data, and it is impossible to mine rules with the help of historical data to accurately evaluate the future crop growth status and early warning of potential risks.

[0006] Second, in the price market unit, this solution only collects, classifies, stores, and analyzes the real-time agricultural product market price data, and does not involve price prediction. In the case of large fluctuations in the agricultural product market price, it is impossible to understand the price trend in advance, and it is difficult for all parties to formulate risk response strategies in advance. Summary of the Invention

[0007] In order to overcome the shortcomings in the background art, the embodiment of the present invention provides a method for monitoring, processing, and analyzing agricultural industrial chain information data, which can effectively solve the problems involved in the above background art.

[0008] The object of the present invention can be achieved by the following technical solutions: An information data monitoring, processing and analysis method for an agricultural industrial chain, the method comprising the following steps: S1. Crop demand analysis: Obtain crop images of each sampling area of the farmland, and determine the growth stage of the crops through image processing technology, and match to obtain the specific nutrient requirements corresponding to the growth stage of the crops.

[0009] S2. Evaluation of the influence of meteorological data: Evaluate the influence coefficient of meteorological data on the nutrient requirements of crops by obtaining meteorological data of the farmland.

[0010] S3. Soil fertilization strategy: Conduct specific nutrient analysis on the sampled soil, use spatial interpolation technology to generate a spatial distribution map of specific soil nutrients, and generate a variable fertilization prescription map based on the influence coefficient of meteorological data on the nutrient requirements of crops and the specific nutrient requirements corresponding to the growth stage of the crops.

[0011] S4. Crop yield prediction: Construct a time series model for the crop maturity time and yield of each historical round of crops, obtain the maturity time and yield prediction results of the current crop, and determine whether to give an early warning.

[0012] S5. Market prediction: Generate a decision tree based on the statistical data of agricultural product prices in the market, and output the price prediction of agricultural products.

[0013] Preferably, the specific analysis method of the crop demand analysis is as follows: Obtain crop images of each sampling area of the farmland through low-altitude remote sensing by an unmanned aerial vehicle, perform grayscale processing on them, use edge detection technology to extract the edge contours of the crops in the crop images of each sampling area of the farmland, calculate the crop areas of the crop images of each sampling area of the farmland, compare them with the areas of the crop images of each sampling area of the farmland to obtain the vegetation coverage of each sampling area of the farmland, extract a set amount of crops from the farmland, obtain their images, use edge detection technology to extract the edge contours of the crops, and compare them with the crop images of each growth stage stored in the management database respectively, so as to determine the growth stage of the crops. By matching with the demand for different nutrients at each growth stage of the crops stored in the management database, the specific nutrient requirements corresponding to the growth stage of the crops are obtained. The specific nutrient refers to a specific nutrient component required for the concerned crops.

[0014] Preferably, the meteorological data includes rainfall, average temperature and air humidity.

[0015] Preferably, the specific analysis method for evaluating the influence of meteorological data is as follows: Set several monitoring periods of equal length, denoted as each monitoring period. Connect to the meteorological data platform to obtain the rainfall, average temperature, and air humidity in the farmland area during each monitoring period. Compare the meteorological data in the farmland area during each monitoring period with the set meteorological data thresholds to obtain the comprehensive scores of the meteorological data in the farmland area during each monitoring period, and accumulate them to obtain the influence coefficient of meteorological data on crop nutrient requirements.

[0016] Preferably, the specific analysis method for analyzing specific nutrients in the sampled soil is as follows: Set each sampling node in each sampling area of the farmland according to the equal-spacing principle, and collect a set amount of soil from each sampling node in each sampling area of the farmland as soil samples to obtain soil samples at each sampling node in each sampling area of the farmland. Obtain the specific nutrient content of the soil samples at each sampling node in each sampling area of the farmland through chemical analysis.

[0017] Preferably, the specific generation method of the spatial distribution map of soil specific nutrients is as follows: Take each sampling area of the farmland as each interpolation unit, select the center point of each interpolation unit as the interpolation point, respectively obtain the distances between the interpolation points in each sampling area of the farmland and each sampling node in the interpolation unit where they are located, assign weights to the interpolation points in each sampling area of the farmland and each sampling node in the interpolation unit where they are located according to the distance from near to far, and accumulate the product of the weights of each sampling node in each sampling area of the farmland and the specific nutrient content of the corresponding sampling node of the corresponding soil sample to obtain the estimated value of the specific nutrients in the soil of each sampling area of the farmland. Obtain the position coordinates of the interpolation points in each sampling area of the farmland, and combine the position coordinates of the interpolation points in each sampling area of the farmland and the estimated values of the specific nutrients of the corresponding soil to construct an interpolation surface, and visually display the generated interpolation surface in a geographic information system, that is, the spatial distribution map of soil specific nutrients.

[0018] Preferably, the specific generation method of the variable fertilization prescription map is as follows: Set a stepped nutrient range for specific nutrients, screen out the farmland areas belonging to the same nutrient range according to the spatial distribution map of soil specific nutrients, divide the farmland into each fertilization area accordingly, and number each fertilization area of the farmland from large to small according to the specific nutrient content. The number is , read the influence coefficient of meteorological data on crop nutrient requirements and the specific nutrient demand corresponding to the crop growth stage, and calculate the required fertilization amount for each fertilization area , where represents the specific nutrient demand corresponding to the crop growth stage, is the influence coefficient of meteorological data on crop nutrient requirements, is the th specific nutrient threshold of the fertilization area, The fertilizer utilization rate of the preset farmland soil is used to generate a variable fertilization prescription map according to the fertilization amount requirements of each fertilization area, and fertilize the crops in each fertilization area accordingly.

[0019] Preferably, the specific operation method for constructing the time series model is as follows: Obtain the historical growth data of each round of crops and the meteorological data within the corresponding time period, as well as the crop maturity time and yield of each round of historical crops. Select several historical time points from the historical growth data of each round of crops and the meteorological data within the corresponding time period according to the principle of equal time intervals. Denote the corresponding crop growth data and corresponding meteorological data as the planting data at each historical time point. Sort the historical time points in chronological order to generate time series data. Denote the planting data at each historical time point as , indicating the number of the th historical time point, , select items of moving average according to the analysis requirements. For the time series , calculate the moving average value . When , . When , calculate the average value of the previous items as the approximate moving average value. . When , use itself as the moving average value. Thus, the -item moving average values of each historical time point are obtained. Construct a time series model based on the -item moving average values of each historical time point, the crop maturity time and yield of each round of historical crops.

[0020] Preferably, the specific operation method for crop yield prediction is as follows: Obtain the growth data and meteorological data of the current crop at each time point, calculate the -item moving average value, input it into the time series model, and output the predicted results of the maturity time and yield of the current crop. Set a yield expectation threshold. If the predicted result of the yield of the current crop is less than the yield expectation threshold, give an early warning. If the predicted result of the yield of the current crop is greater than or equal to the yield expectation threshold, no early warning is required.

[0021] Preferably, the specific operation method of step S5 is as follows: S51. Obtain the statistical data of agricultural product prices on the website of the Ministry of Agriculture and Rural Affairs. For specific agricultural products, obtain the prices of specific agricultural products at each price time point, set a stepped price range, and when the price of a specific agricultural product fluctuates to a new price range at a certain price time point, mark that price time point. Thus, each marked time point is obtained. By taking the difference between adjacent marked time points, the duration for which each price range persists in the market is obtained, denoted as the listing duration of each price range. At the same time, obtain the listing quantity of specific agricultural products within the listing duration of each price range.

[0022] S52. Define the listing duration of each price range as feature 1, and define the listing quantity of specific agricultural products within the listing duration of each price range as feature 2, to obtain a feature 1 data set and a feature 2 data set. According to the equal-spacing principle, divide the data corresponding to feature 1 and feature 2 into several intervals respectively, and calculate the proportion of the th interval and the th interval in the corresponding feature data set. Let represent the number of the th interval of feature 1, and represent the number of the th interval of feature 2. Calculate the Gini coefficients of each interval of feature 1 and feature 2 according to the interval proportion.

[0023] S53. Compare the Gini coefficients of each interval of feature 1 and feature 2, select the feature and division point with the smallest Gini coefficient as the optimal division feature and division point for the feature 1 data set and the feature 2 data set. According to the selected optimal division feature and division point, divide the feature 1 data set and the feature 2 data set into two child nodes.

[0024] S54. For the newly generated child nodes, set that the number of data in each child node is less than the set threshold as meeting the stop condition. If the number of data in a certain child node is greater than or equal to the set threshold, repeat S52 and S53, continue to select the optimal division feature and division point on the child node for node division, recursively construct a sub-tree. If the number of data in a certain child node is less than the set threshold, mark it as a leaf node, calculate the average price of all data in this leaf node, and use the average price as the predicted value of this leaf node. Proceed in this way until all nodes meet the stop condition, and the decision tree construction is completed. Then, input the characteristics of the agricultural product to be predicted into the decision tree, and output the price prediction of the agricultural product.

[0025] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: First, the present invention generates a spatial distribution map of specific soil nutrients through spatial interpolation technology, clearly showing the spatial variation of soil nutrients in farmland. Based on the influence coefficient of meteorological data on crop nutrient requirements and the specific nutrient requirements corresponding to different crop growth stages, a variable fertilization prescription map is generated, which can perform precise fertilization according to the differences in soil nutrients in different regions of the farmland, as well as the different meteorological conditions and crop growth stages in different regions.

[0026] Second, the present invention constructs a time series model based on the crop maturity time and yield of each historical crop to obtain the prediction results of the maturity time and yield of the current crop. By comparing the prediction results with the pre-set standards, it is judged whether the current crop growth faces risks and whether a warning needs to be issued, so as to respond to potential risks and opportunities in advance and improve the stability and risk resistance of agricultural production.

[0027] Third, the present invention generates a decision tree based on the statistical data of agricultural product prices in the market and outputs the price prediction of agricultural products. In the case of large fluctuations in the market price of agricultural products, understanding the price trend in advance helps all parties formulate risk response strategies in advance. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The present invention will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to the following drawings without creative efforts.

[0029] Figure 1 It is a schematic flowchart of the method of the present invention.

[0030] Figure 2 is Figure 1 the flowchart judgment block diagram of step S4 in

[0031] Figure 3 is Figure 1 the schematic flowchart of step S5 in DETAILED DESCRIPTION OF THE EMBODIMENTS

[0032] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0033] Please refer to Figure 1As shown in the figure, the present invention provides a method for monitoring, processing and analyzing agricultural industrial chain information data, and the method includes the following steps: S1. Crop demand analysis: Obtain crop images of each sampling area of the farmland, and judge the growth stage of the crops through image processing technology, and match to obtain the specific nutrient demand corresponding to the growth stage of the crops.

[0034] The specific analysis method of the crop demand analysis is as follows: Obtain crop images of each sampling area of the farmland through low-altitude remote sensing by an unmanned aerial vehicle, perform grayscale processing on them, use edge detection technology to extract the edge contours of the crops in the crop images of each sampling area of the farmland, calculate the crop areas of the crop images of each sampling area of the farmland, compare them with the areas of the crop images of each sampling area of the farmland to obtain the vegetation coverage of each sampling area of the farmland, extract a set amount of crops from the farmland, obtain their images, use edge detection technology to extract the edge contours of the crops, and compare them with the crop images of each growth stage stored in the management database respectively, so as to judge the growth stage of the crops. By matching with the demand for different nutrients at each growth stage of the crops stored in the management database, obtain the specific nutrient demand corresponding to the growth stage of the crops; Providing nutrients according to the actual needs of the crops helps to improve the fertilizer utilization rate, reduce the agricultural production cost, and improve the quality and quality of agricultural products. The specific nutrient refers to a specific nutrient component required for the concerned crops.

[0035] It should be noted that the specific analysis method of the edge detection technology is as follows: Perform grayscale processing on the crop images of each sampling area of the farmland, calculate the grayscale change rate of the pixel points in the horizontal and vertical directions through the gradient operator to obtain the magnitude and direction of the gradient, set two grayscale value thresholds respectively, a high threshold and a low threshold, mark the pixel points with gradient values greater than the high threshold as strong edge points, mark the pixel points with gradient values between the low threshold and the high threshold as weak edge points, mark the pixel points with gradient values less than the low threshold as non-edge points, start from the strong edge points, and connect the weak edge points connected to the strong edge points through 8-neighborhood search to form a complete edge contour, and obtain the edge contours of the crops in the crop images of each sampling area of the farmland.

[0036] S2. Meteorological data impact assessment: Evaluate the impact coefficient of meteorological data on crop nutrient demand by obtaining farmland meteorological data.

[0037] The meteorological data includes rainfall, average temperature and air humidity.

[0038] The specific analysis method for the impact assessment of meteorological data is as follows: Set several monitoring periods of equal length, denoted as each monitoring period. Connect to the meteorological data platform to obtain the rainfall, average temperature, and air humidity in the farmland area during each monitoring period. Compare the meteorological data in the farmland area during each monitoring period with the set meteorological data threshold to obtain the comprehensive score of the meteorological data in the farmland area during each monitoring period, and accumulate it to obtain the impact coefficient of meteorological data on crop nutrient requirements; it can more clearly observe the changes in meteorological data at different time periods and ensure the timeliness and comprehensiveness of the data.

[0039] It should be noted that the specific analysis method for the comprehensive score of the meteorological data in the farmland area during each monitoring period is as follows: Set the meteorological data threshold, and extract the maximum and minimum values corresponding to rainfall, average temperature, and air humidity respectively. Denote the maximum and minimum values corresponding to rainfall as , denote the rainfall in the farmland area during each monitoring period as , represents the number of the th monitoring period, , through the formula obtain the rainfall score in the farmland area during each monitoring period , according to the method of analyzing the rainfall score in the farmland area during each monitoring period, obtain the average temperature score and air humidity score in the farmland area during each monitoring period , calculate the comprehensive score of the meteorological data in the farmland area during each monitoring period : , where respectively represent the preset weight factors of rainfall, average temperature, and air humidity.

[0040] It should be noted that compare the actual meteorological data with the preset threshold, and give a score between 0 and 1 according to the comparison result, where 1 represents the most ideal meteorological conditions and 0 represents the least ideal conditions.

[0041] It should be noted that in a specific embodiment, can be set to 0.5, can be set to 0.3, It can be set to 0.2. Rainfall is crucial for crop growth as it directly affects the water supply to crops. Excessive rainfall may lead to waterlogging, while insufficient rainfall may cause drought. Temperature affects the physiological activities of crops, including photosynthesis and respiration. An appropriate temperature range can promote crop growth, while too high or too low temperatures may inhibit growth or damage the crops. Therefore, the average temperature is also an important meteorological factor, but its weight may be slightly lower than that of rainfall because its impact may be more dependent on crop species and growth stages. Air humidity affects the transpiration of crops and the occurrence of pests and diseases. Appropriate humidity can reduce water evaporation, keep the soil moist, and also help control pests and diseases. However, the impact of air humidity on crop growth may not be as direct as that of rainfall and temperature. Therefore, the weight corresponding to air humidity is the lowest, and the weight corresponding to rainfall is the highest.

[0042] S3. Soil fertilization strategy: Conduct specific nutrient analysis on the sampled soil, use spatial interpolation technology to generate a spatial distribution map of specific soil nutrients, and generate a variable fertilization prescription map based on the influence coefficient of meteorological data on crop nutrient requirements and the specific nutrient requirements corresponding to the crop growth stage.

[0043] The specific analysis method for conducting specific nutrient analysis on the sampled soil is as follows: Set sampling nodes in each sampling area of the farmland according to the equal-spacing principle, collect a set amount of soil from each sampling node in each sampling area of the farmland as soil samples to obtain soil samples from each sampling node in each sampling area of the farmland, and obtain the specific nutrient content of the soil samples from each sampling node in each sampling area of the farmland through chemical analysis methods; Provide accurate soil fertility information for agricultural production, help formulate precise fertilization plans according to the soil nutrient status, and achieve fertilization according to demand.

[0044] It should be noted that the specific division method of the equal-spacing principle is as follows: If the farmland has a regular shape (such as a rectangle), it can be directly divided at equal intervals along the length and width directions of the farmland according to the set interval to form a grid-like sampling node layout; If the farmland has an irregular shape, it can be first divided into several relatively regular sub-areas, and then sampling nodes can be set for each sub-area according to the equal-spacing principle.

[0045] It should be noted that the specific analysis method of the chemical analysis method is as follows: For soil acidity and alkalinity, weigh a set amount of soil sample, put it into a beaker, add carbon dioxide-free water according to the set soil-water ratio, stir evenly to obtain a supernatant, and measure the pH value of the supernatant with a pH meter after standing.

[0046] For soil organic matter, a set amount of soil sample is weighed and placed in a hard test tube. A potassium dichromate - sulfuric acid solution with a set concentration and volume is added, and it is heated and oxidized in an oil bath to react the organic carbon in the soil with potassium dichromate. The remaining potassium dichromate is titrated with a standard ferrous sulfate solution, and the soil organic matter content is calculated based on the amount of ferrous sulfate consumed.

[0047] The specific method for generating the spatial distribution map of specific soil nutrients is as follows: Taking each sampling area of the farmland as each interpolation unit, selecting the center point of each interpolation unit as the interpolation point, respectively obtaining the distances between the interpolation points of each sampling area in the farmland and each sampling node in its corresponding interpolation unit, assigning weights to the interpolation points of each sampling area in the farmland and each sampling node in its corresponding interpolation unit in ascending order of distance, accumulating the product of the weights of each sampling node in each sampling area of the farmland and the content of the specific nutrient of the corresponding sampling node of the corresponding soil sample to obtain the estimated value of the specific nutrient of the soil in each sampling area of the farmland, obtaining the position coordinates of the interpolation points of each sampling area in the farmland, constructing an interpolation surface by combining the position coordinates of the interpolation points of each sampling area in the farmland and the estimated value of the specific nutrient of the corresponding soil, and visually displaying the generated interpolation surface in a geographic information system, namely the spatial distribution map of specific soil nutrients; making the soil nutrient estimation value more reasonable and accurate, being able to better reflect the actual situation of the soil nutrients around the interpolation point, avoiding the estimation deviation caused by simple averaging or not considering the distance factor, and improving the accuracy and reliability of nutrient estimation.

[0048] It should be noted that the specific calculation method for assigning weights to the interpolation points of each sampling area in the farmland and each sampling node in its corresponding interpolation unit in ascending order of distance is as follows: For the interpolation point , there are sampling nodes around it ( ), let the distance from sampling node to interpolation point be , and the Euclidean distance is used to calculate the weight of interpolation point .

[0049] It should be noted that the weight formula of the interpolation point is based on the idea of inverse distance weighted interpolation, that is, it is considered that the sampling nodes closer to the interpolation point have a greater influence on this interpolation point. In Euclidean space, the inverse square of the distance is widely used for weight assignment. The weight of a single sampling node reflects its relative influence on the interpolation of the interpolation point. According to the principle of inverse distance weight, the reciprocal square of the distance can be used as a preliminary indicator to measure its influence. In order to make the sum of the weights of all sampling nodes equal to 1 (ensuring the normalization of weights), each Perform normalization processing by dividing each by the sum of all sampling nodes sum. .

[0050] The specific generation method of the variable fertilization prescription map is as follows: Set a stepped nutrient range for a specific nutrient, screen out the farmland areas belonging to the same nutrient range according to the spatial distribution map of the specific nutrient in the soil, divide the farmland into each fertilization area accordingly, and number each fertilization area of the farmland from large to small according to the specific nutrient content. The number is , read the influence coefficient of meteorological data on crop nutrient demand and the specific nutrient demand corresponding to the crop growth stage, and calculate the required fertilization amount for each fertilization area , where represents the specific nutrient demand corresponding to the crop growth stage, is the influence coefficient of meteorological data on crop nutrient demand, is the specific nutrient threshold of the th fertilization area, is the preset fertilizer utilization rate of the farmland soil. Generate a variable fertilization prescription map according to the required fertilization amount of each fertilization area, and fertilize the crops in each fertilization area accordingly; it is convenient to formulate a fertilization plan and arrange fertilization operations, improving the operability and accuracy of fertilization.

[0051] It should be noted that among the required fertilization amounts of each fertilization area, represents the specific nutrient demand corresponding to the crop growth stage, which is the amount of specific nutrient required for the crop to grow to the current stage under ideal conditions. However, in actual situations, meteorological conditions will affect crop nutrient demand. Therefore, the influence coefficient of meteorological data on crop nutrient demand is introduced, represents the total amount of specific nutrient that the crop actually needs to obtain from the soil after considering the influence of meteorological factors, is the specific nutrient threshold of the th fertilization area, that is, the level that the existing specific nutrient content in the soil of this area has reached. Subtract the existing specific nutrient content in this area from the total amount of specific nutrient that the crop actually needs to obtain, and the demand is the amount of specific nutrient that the crop in this fertilization area still needs to supplement additionally, is the preset fertilizer utilization rate of the farmland soil, indicating the proportion of the fertilizer applied to the soil that can be absorbed and utilized by the crop. Because when actually fertilizing, since the fertilizer utilization rate is not 100%, it is necessary to divide the amount of nutrient that the crop still needs to supplement additionally by the fertilizer utilization rate to obtain the actual amount of fertilizer that needs to be applied to this fertilization area, that is .

[0052] A feasible simulation process involves planting a wheat field and dividing it into 3 fertilization areas ( ). Given that the nitrogen requirement of wheat during the jointing stage (growth stage) for a specific nutrient is = 15 kg / mu, and meteorological data shows that the current meteorological conditions are favorable for wheat to absorb nitrogen, with the influence coefficient of meteorological data on crop nutrient requirements = 0.2, and the preset fertilizer utilization rate of farmland soil = 0.4, the simulation results can be obtained. For specific details, refer to Table 1, which lists some representative data.

[0053] Table 1. Data and calculation results of each fertilization area collected partially

[0054] Fertilization area Specific nutrient threshold (kg / mu) Actual amount of fertilizer to be applied to the fertilization area (kg / mu) 1 5 #timg# 2 8 #timg# 3 3 #timg#

[0055] S4. Crop yield prediction: Construct a time series model for the crop maturity time and yield of each historical round of crops, obtain the maturity time and yield prediction results of the current crop, and determine whether to give an early warning.

[0056] Please refer to Figure 2 As shown, the specific operation method for constructing the time series model is as follows: Obtain the growth data of each historical round of crops and the meteorological data within the corresponding time period, as well as the crop maturity time and yield of each historical round of crops. Select several historical time points from the growth data of each historical round of crops and the meteorological data within the corresponding time period according to the principle of equal time intervals. Denote the corresponding crop growth data and corresponding meteorological data as the planting data at each historical time point. Sort the historical time points in chronological order to generate time series data. Denote the planting data at each historical time point as , represents the number of the th historical time point. , select items of moving average according to the analysis requirements. For the time series , calculate the moving average value . When , . When , calculate the average value of the first items as the approximate moving average value. When, take itself as the moving average value. Thus, the -item moving average values of each historical time point are obtained. According to the Construct a time series model using the moving average of items, the crop maturity time of each round in history, and the yield construction time; through learning and modeling of historical data, the model can capture the potential relationships between crop growth, environmental factors, and time, providing a scientific decision-making basis for agricultural production.

[0057] It should be noted that when the data volume is small, only all the existing data can be used to calculate an average value that can relatively reflect the overall trend, while when continues to increase, when calculating the moving average value each time, the number of data points counted forward from the current time point is for averaging. The purpose is to make the moving average value reflect the average level of data within a relatively stable time period, eliminate the impact of accidental fluctuations of individual data points on the overall trend, and thus more clearly show the long-term trend of the data.

[0058] The specific operation method for the crop yield prediction is as follows: Obtain the growth data and meteorological data of the current crop at each time point, calculate the item moving average value, input it into the time series model, output the maturity time and yield prediction results of the current crop, set the yield expectation threshold. If the yield prediction result of the current crop is less than the yield expectation threshold, give an early warning; if the yield prediction result of the current crop is greater than or equal to the yield expectation threshold, no early warning is required; it provides a risk early warning mechanism for agricultural production. When the yield may be lower than expected, measures can be taken in a timely manner, such as increasing fertilization and strengthening pest control, to minimize losses as much as possible. When the yield meets or exceeds the expectation, production and sales can be reasonably arranged to improve economic benefits.

[0059] S5. Market prediction: Generate a decision tree based on the statistical data of agricultural product prices in the market, and output the price prediction of agricultural products.

[0060] Please refer to Figure 3 As shown, the specific operation method of step S5 is as follows: S51. Obtain the statistical data of agricultural product prices in the market from the website of the Ministry of Agriculture and Rural Affairs. For specific agricultural products, obtain the prices of specific agricultural products at each price time point, set the stepped price range. When the price of a specific agricultural product at a certain price time point fluctuates to a new price range, mark that price time point, and thus obtain each marked time point. By taking the difference between adjacent marked time points, obtain the duration that each price range persists in the market, denoted as the market duration of each price range. At the same time, obtain the market volume of specific agricultural products within the market duration of each price range; it provides a clear time identifier for subsequent analysis of price change rules, facilitates understanding the price fluctuations of specific agricultural products at different stages, helps to grasp the market price trend, and provides important price information reference for producers, sellers, and consumers.

[0061] Define the market duration of each price range as Feature 1 and the market volume of specific agricultural products within the market duration of each price range as Feature 2, obtaining the Feature 1 data set and the Feature 2 data set. According to the equal-spacing principle, divide the data corresponding to Feature 1 and Feature 2 into several intervals respectively, and calculate the proportion of the rd, th intervals in the data set of this feature , Let represent the number of the th interval of Feature 1, and represent the number of the th interval of Feature 2. Calculate the Gini coefficients of each interval of Feature 1 and Feature 2 according to the interval proportion , ; The Gini coefficient can quantify the distribution of feature data, understand the degree of data concentration and difference. A smaller Gini coefficient indicates a more uniform data distribution, and a larger Gini coefficient indicates a more concentrated data distribution.

[0062] It should be noted that taking the Gini coefficients of each interval of Feature 1 as an example, let represent the proportion of the th interval of Feature 1 in this node, that is, divide the data of Feature 1 into intervals according to the equal-spacing principle, and the proportion of each interval in the overall is . Assuming that the proportions of all intervals are equal, that is , at this time the distribution is the most uniform. Since is a constant, according to the constant summation formula, we can get . When the distribution is completely uniform, define the Gini coefficient as 0. As the degree of uneven distribution increases, the Gini coefficient gradually increases to 1. In order to make the Gini coefficient 0 when the distribution is completely uniform, subtract from 1 to get . When all data are concentrated in one interval, for example , and the rest is , at this time the Gini coefficient

[0063] It should be noted that when calculating the The specific analysis method for the proportion of each interval in this node is as follows: Screen out the maximum and minimum values of the data of Feature 1 (the listing duration in each price range) and Feature 2 (the listing quantity of specific agricultural products during the listing duration in each price range) to obtain the data ranges of Feature 1 and Feature 2. Divide the data ranges of Feature 1 and Feature 2 into several intervals according to the equal-spacing principle. Traverse all the data of Feature 1 and Feature 2, count the number of data points in each interval, and divide the number of data points in each interval by the total number of data of this feature to obtain the proportion of each interval in this node.

[0064] S53. Compare the Gini coefficients of each interval of Feature 1 and Feature 2, and select the feature and splitting point with the smallest Gini coefficient as the optimal splitting feature and splitting point for the Feature 1 data set and the Feature 2 data set. According to the selected optimal splitting feature and splitting point, divide the Feature 1 data set and the Feature 2 data set into two child nodes; By continuously splitting the nodes, the decision tree can gradually construct a complex classification structure to accurately classify and predict the data under different feature combinations. Each child node represents a more specific data subset, which helps to analyze the relationship between data more deeply and improve the model's understanding and prediction ability of market price changes.

[0065] It should be noted that in a specific embodiment, taking the duration of the price range as the splitting feature and the optimal splitting point found is 10 days, then the samples with a price range duration less than 10 days are divided into one child node, and the samples greater than or equal to 10 days are divided into another child node.

[0066] S54. For the newly generated child nodes, set the condition that the number of data in each child node is less than the set threshold to meet the stop condition. If the number of data in a certain child node is greater than or equal to the set threshold, repeat S52 and S53, continue to select the optimal splitting feature and splitting point on the child node for node splitting, and recursively construct the subtree. If the number of data in a certain child node is less than the set threshold, mark it as a leaf node, calculate the average price of all the data in this leaf node, and use the average price as the predicted value of this leaf node. In this way, until all nodes meet the stop condition, the decision tree construction is completed. Then, input the characteristics of the agricultural products to be predicted into the decision tree to output the price prediction of the agricultural products; The predicted value of the leaf node provides a specific numerical reference for the price prediction of agricultural products. As an intuitive model structure, the decision tree can quickly and accurately output the price prediction result according to the input characteristics of agricultural products.

[0067] It should be noted that in a specific embodiment, price statistical data of apples in the past 365 days are obtained from the website of the Ministry of Agriculture and Rural Affairs. For apples, the price is recorded every day (price time point), and the stepped price range is set as: low price range (below 8 yuan per catty), medium price range (8 - 12 yuan per catty), high price range (above 12 yuan per catty).

[0068] During these 365 days, on the 30th day, the apple price rose from 7.5 yuan per catty to 8.2 yuan per catty, fluctuating into the medium price range, and the 30th day was marked; on the 120th day, the price rose from 11.8 yuan per catty to 12.5 yuan per catty, fluctuating into the high price range, and the 120th day was marked; on the 200th day, the price dropped from 13 yuan per catty to 11.5 yuan per catty, returning to the medium price range, and the 200th day was marked.

[0069] Then the listing duration in the low price range is 30 days, the listing duration in the medium price range after the first fluctuation is 120 - 30 = 90 days, the listing duration in the high price range is 200 - 120 = 80 days, and the listing duration in the medium price range after the second fluctuation is 365 - 200 = 165 days. At the same time, the apple listing volume within the listing duration in the low price range is 50 tons, the listing volume within the first medium price range listing duration is 120 tons, the listing volume within the high price range listing duration is 90 tons, and the listing volume within the second medium price range listing duration is 180 tons.

[0070] Define the listing duration of each price range (feature 1) as: [30, 90, 80, 165], and the apple listing volume within the listing duration of each price range (feature 2) as: [50, 120, 90, 180]. Obtain the feature 1 data set and the feature 2 data set. According to the equal interval principle, divide the data range [30, 165] of feature 1 into 3 intervals: [30 - 70], [71 - 110], [111 - 165], and also divide the data range [50, 180] of feature 2 into 3 intervals: [50 - 90], [91 - 130], [131 - 180].

[0071] Statistics show that the number of data points of feature 1 in the three intervals is 1, 1, and 2 respectively. Then the proportions of each interval in the feature 1 data set are , the number of data points of feature 2 in the three intervals is 1, 1, and 2 respectively, and the proportions of each interval in the feature 2 data set are , and calculate the Gini coefficients of feature 1 and feature 2 according to the formula .

[0072] Since the Gini coefficients of Feature 1 and Feature 2 are equal, Feature 1 is randomly selected as the optimal partitioning feature. Analyze the data set of Feature 1 [30, 90, 80, 165], and determine that the optimal partitioning point is 80 days. At this time, the samples in the data set of Feature 1 with a price range duration less than 80 days (i.e., the sample corresponding to 30 days) are partitioned into one child node, and the samples greater than or equal to 80 days (i.e., the samples corresponding to 90 days, 80 days, and 165 days) are partitioned into another child node. At the same time, the data set of Feature 2 [50, 120, 90, 180] is partitioned accordingly according to the partitioning method of Feature 1, that is, the samples corresponding to less than 80 days (here it is the market volume of 50 tons corresponding to the duration of 30 days) are partitioned into one child node, and the samples corresponding to greater than or equal to 80 days (i.e., the market volumes of 120 tons, 90 tons, and 180 tons corresponding to the durations of 90 days, 80 days, and 165 days) are partitioned into another child node.

[0073] Set the stop threshold for the number of data in the child node to 2. For the two newly generated child nodes: In the first child node, the number of samples in the data set of Feature 1 with a price range duration less than 80 days is 1, and the number of samples in the corresponding market volume data set of Feature 2 is also 1, which is less than the set threshold of 2. Therefore, mark this child node as a leaf node, calculate the average price of the data within this leaf node (the data combination of the apple price in the low price range within 30 days of the listing duration and the market volume of 50 tons) as 7.5 yuan per catty, and use 7.5 yuan per catty as the predicted value of this leaf node.

[0074] In the second child node, the number of samples in the data set of Feature 1 with a price range duration greater than or equal to 80 days is 3, and the number of samples in the corresponding market volume data set of Feature 2 is also 3, which is greater than the set threshold of 2. Therefore, the steps of S52 and S53 need to be repeated until the number of data in all child nodes is less than the set threshold, mark these child nodes as leaf nodes, and calculate the average price of all data within each leaf node as the predicted value.

[0075] Input the apple-related feature data to be predicted (such as the listing duration of the price range for a certain period of time, the market volume, etc.) into the constructed decision tree. According to the internal structure and rules, the decision tree quickly and accurately outputs the price prediction result of the apple.

[0076] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention, and still be covered by the protection scope of the present invention.

Claims

1. A method for monitoring, processing and analyzing agricultural industry chain information data, characterized in that: The steps include: S1. Crop demand analysis: Obtain crop images of each sampling area of ​​the farmland, determine the growth stage of the crop through image processing technology, and match the specific nutrient demand corresponding to the crop growth stage; S2. Meteorological data impact assessment: Evaluate the impact coefficient of meteorological data on crop nutrient demand by obtaining farmland meteorological data; S3. Soil fertilization strategy: Analyze the specific nutrients of the sampled soil, use spatial interpolation technology to generate a spatial distribution map of soil specific nutrients, and generate a variable fertilization prescription map based on the influence coefficient of meteorological data on crop nutrient demand and the specific nutrient demand corresponding to the crop growth stage; S4. Crop yield prediction: Build a time series model for the maturity time and yield of each crop cycle in history, obtain the maturity time and yield prediction results of the current crop, and determine whether to issue an early warning; S5. Market forecast: Generate a decision tree based on the price statistics of agricultural products in the market and output the price forecast of agricultural products.

2. The method for monitoring, processing and analyzing agricultural industry chain information data according to claim 1, characterized in that: The specific analysis method of the crop demand analysis is as follows: The crop images of each sampling area of ​​the farmland are obtained by low-altitude remote sensing using unmanned aerial vehicles, and grayscale processing is performed on them. The edge contours of the crops in the crop images of each sampling area of ​​the farmland are extracted using edge detection technology, and the crop area of ​​the crop images of each sampling area of ​​the farmland is calculated. The crop area is compared with the crop image area of ​​each sampling area of ​​the farmland to obtain the vegetation coverage of each sampling area of ​​the farmland. A set amount of crops are extracted from the farmland to obtain their images, and the edge contours of the crops are extracted using edge detection technology. The crop edge contours are compared with the crop images of each growth stage stored in the management database to determine the growth stage of the crops. By matching the requirements for different nutrients at each growth stage of the crops stored in the management database, the specific nutrient requirements corresponding to the crop growth stage are obtained. The specific nutrient refers to a specific nutrient required for the crop of concern.

3. The method for monitoring, processing and analyzing agricultural industry chain information data according to claim 1, characterized in that: The meteorological data include rainfall, average temperature and air humidity.

4. The method for monitoring, processing and analyzing agricultural industry chain information data according to claim 3, characterized in that: The specific analysis method for the meteorological data impact assessment is as follows: Set a number of monitoring periods of equal length, recorded as each monitoring period, and connect to the meteorological data platform to obtain the rainfall, average temperature and air humidity in each monitoring period in the farmland area. Compare the meteorological data of each monitoring period in the farmland area with the set meteorological data threshold to obtain the comprehensive score of the meteorological data in each monitoring period in the farmland area, and add them up to get the influence coefficient of meteorological data on crop nutrient demand.

5. The method for monitoring, processing and analyzing agricultural industry chain information data according to claim 1, characterized in that: The specific analysis method for analyzing the specific nutrients of the sampled soil is as follows: According to the principle of equal spacing, sampling nodes are set in each sampling area of ​​the farmland, and a set amount of soil is collected from each sampling node in each sampling area of ​​the farmland as soil samples to obtain soil samples at each sampling node in each sampling area of ​​the farmland. The specific nutrient content of the soil samples at each sampling node in each sampling area of ​​the farmland is obtained by chemical analysis.

6. The method for monitoring, processing and analyzing agricultural industry chain information data according to claim 5, characterized in that: The specific method for generating the soil specific nutrient spatial distribution map is as follows: Each sampling area of ​​the farmland is taken as each interpolation unit, and the center point of each interpolation unit is selected as the interpolation point. The distance between the interpolation point of each sampling area of ​​the farmland and each sampling node in the interpolation unit is obtained respectively. The weights are assigned to the interpolation points of each sampling area of ​​the farmland and each sampling node in the interpolation unit according to the distance from near to far. The specific nutrient estimation value of the soil in each sampling area of ​​the farmland is obtained by accumulating the product of the weight of each sampling node in each sampling area of ​​the farmland and the specific nutrient content of the corresponding sampling node of the corresponding soil sample, and the position coordinates of the interpolation points in each sampling area of ​​the farmland are obtained. The interpolation surface is constructed by combining the position coordinates of the interpolation points in each sampling area of ​​the farmland and the corresponding soil specific nutrient estimation value. The generated interpolation surface is visualized in the geographic information system, that is, the spatial distribution map of soil specific nutrients.

7. The method for monitoring, processing and analyzing agricultural industry chain information data according to claim 6, characterized in that: The specific method for generating the variable fertilization prescription map is as follows: A stepped nutrient range is set for a specific nutrient. The farmland areas belonging to the same nutrient range are screened out according to the spatial distribution map of soil specific nutrients. The farmland is divided into fertilization areas and numbered according to the specific nutrient content from high to low. , read the impact coefficient of meteorological data on crop nutrient demand, the specific nutrient demand corresponding to the crop growth stage, and calculate the required fertilization amount for each fertilization area ,in Indicates the specific nutrient requirements of crops at different growth stages. is the influence coefficient of meteorological data on crop nutrient demand, For the specific nutrient thresholds for each fertilization area, Based on the preset fertilizer utilization rate of farmland soil, a variable fertilizer prescription map is generated according to the fertilizer amount required in each fertilization area, and crops in each fertilization area are fertilized accordingly.

8. The method for monitoring, processing and analyzing agricultural industry chain information data according to claim 1, characterized in that: The specific operation method of constructing the time series model is as follows: Obtain the historical crop growth data of each round and the meteorological data in the corresponding time period, as well as the crop maturity time and yield of each historical crop round. Select several historical time points from the historical crop growth data of each round and the meteorological data in the corresponding time period according to the principle of equal time intervals, and record the corresponding crop growth data and corresponding meteorological data as the planting data of each historical time point. Sort the historical time points in chronological order to generate time series data, and record the planting data of each historical time point as , Indicates The number of the historical time point, , select according to analysis requirements Moving average, for time series , calculate the moving average ,when hour, ,when Before calculation The average of the items is used as an approximate moving average, When Itself is used as a moving average, thus obtaining the The moving average of each historical time point The time series model is constructed by using the moving average of the items, the crop maturity time and yield of each historical crop cycle.

9. The method for monitoring, processing and analyzing agricultural industry chain information data according to claim 8, characterized in that: The specific operation method of the crop yield prediction is as follows: Obtain the current crop growth data and meteorological data at each time point, and calculate the The moving average of the items is input into the time series model, and the maturity time and yield prediction results of the current crop are output. The expected yield threshold is set. If the yield prediction result of the current crop is less than the expected yield threshold, an early warning is issued. If the yield prediction result of the current crop is greater than or equal to the expected yield threshold, no early warning is required.

10. The method for monitoring, processing and analyzing agricultural industry chain information data according to claim 1, characterized in that: The specific operation method of step S5 is: S51. Obtain the statistical data of agricultural product prices in the market from the website of the Ministry of Agriculture and Rural Affairs, obtain the price of the specific agricultural product at each price time point for the specific agricultural product, set a step price range, and mark the price time point when the price of the specific agricultural product at a certain price time point fluctuates to a new price range, thereby obtaining each marked time point, and obtain the duration of each price range being maintained in the market by subtracting adjacent marked time points, which is recorded as the listing duration of each price range, and at the same time obtain the listing quantity of the specific agricultural product within the listing duration of each price range; S52. Define the duration of each price range on the market as feature 1, and define the quantity of specific agricultural products on the market within each price range on the market as feature 2, obtain the feature 1 data set and the feature 2 data set, divide the data corresponding to feature 1 and feature 2 into several intervals according to the principle of equal spacing, and calculate the feature 1 and feature 2 intervals respectively. , The proportion of intervals in this feature data set , Representation feature 1 The number of the interval, , Representation feature 2 The number of the interval, , calculate the Gini coefficient of each interval of feature 1 and feature 2 according to the interval ratio , ; S53. Compare the Gini coefficients of each interval of feature 1 and feature 2, select the feature and partition point with the smallest Gini coefficient as the optimal partition feature and partition point of feature 1 data set and feature 2 data set, and divide the feature 1 data set and feature 2 data set into two child nodes according to the selected optimal partition feature and partition point; S54. For the newly generated child nodes, the number of data in each child node is less than the set threshold value, which is set as the stopping condition. If the number of data in a child node is greater than or equal to the set threshold value, repeat S52 and S53, continue to select the optimal partitioning features and partitioning points on the child nodes, perform node partitioning, and recursively construct subtrees. If the number of data in a child node is less than the set threshold value, it is marked as a leaf node, and the average price of all data in the leaf node is calculated. The average price is used as the predicted value of the leaf node, and this is repeated until all nodes meet the stopping condition and the decision tree is constructed. Then, the characteristics of the agricultural products to be predicted are input into the decision tree, and the price prediction of the agricultural products is output.

Images