Crop planting area planning method based on big data

Abstract

The invention discloses a crop planting area planning method based on big data, and relates to the technical field of crop planting planning management. The crop planting area planning method based on big data comprises the following steps of crop data processing, preprocessing effect judgment, resource utilization coincidence judgment and pre-planning effect judgment. According to the method, the effect of preprocessing the crop related data is evaluated to judge whether planting resource utilization conformity evaluation is executed, then the crop resource utilization score after the planting resource utilization conformity evaluation is executed is obtained, and whether crop planting area pre-planning is executed is judged; and finally, the crop planting area pre-planning effect is evaluated to judge whether to execute crop planting area secondary planning, so that the effect of improving the crop planting area planning accuracy is achieved, and the problem of low crop planting area planning accuracy in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of crop planting planning and management, and in particular to a crop planting area planning method based on big data. Background Art

[0002] With the rapid development of information technology, Internet of Things, remote sensing technology, geographic information system and other technologies, agriculture has gradually entered the era of big data. Traditional crop planting area planning usually relies on empirical data, local surveys, historical data, farmers' experience and climate forecasts issued by the government. Although it has certain practicality, it is difficult to provide comprehensive and scientific solutions in the face of complex agricultural production environment, climate change and environmental protection requirements. The application of big data technology makes agricultural planning more scientific and intelligent, promotes the process of agricultural modernization, and provides strong technical support for the sustainable development of agriculture in the future.

[0003] The existing crop planting area planning methods integrate a variety of advanced technologies such as data collection, spatial analysis, prediction models, and decision support systems, striving to achieve accurate, personalized, and sustainable agricultural planning. Through big data, artificial intelligence, the Internet of Things, remote sensing technology, and other means, it can help farmers and agricultural decision makers make scientific and effective decisions in a complex agricultural environment, thereby improving agricultural production efficiency, ensuring food security, and promoting the sustainable development of agriculture.

[0004] For example, a patent application with publication number: CN115511158A discloses a method and system for intelligent crop breeding analysis based on big data, including: obtaining historical image data of a farmland area, and performing comparative analysis between the historical image data and the big data pest data to obtain farmland pest data; screening crops according to the farmland pest data to obtain first result crop information; obtaining disease information of crops in a specific farmland area, and obtaining second result crop information according to the disease information and the first result crop information; obtaining farmland area environmental data, and performing comprehensive environmental analysis according to the farmland area environmental data to obtain farmland irrigation information; performing combination matching analysis based on the farmland irrigation information and the second result crop information to obtain preferred crop plan information.

[0005] For example, the invention patent with announcement number: CN117541177B announces a smart agricultural monitoring and management method and system based on big data, including: Step 1: Obtain crop planting big data, and at the same time, obtain the planting distribution of the target area that needs agricultural monitoring; Step 2: Based on the crop planting big data, formulate an agricultural monitoring strategy suitable for the planting distribution; Step 3: Based on the agricultural monitoring strategy, correspondingly control at least one first monitoring vehicle in the target area.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application found that the above technology has at least the following technical problems:

[0007] In precision agriculture, data sources are complex and involve multiple sources, such as weather stations, remote sensing satellites, farmland sensors, etc. However, data quality varies, and data coverage is incomplete in many places. Especially in remote areas or less developed areas, incomplete sensor deployment and insufficient data collection coverage may lead to missing data and affect the accuracy of analysis results. In addition, agricultural data often contains noise, especially data from remote sensing and sensors. How to remove noise and obtain effective data is a major challenge.

[0008] Another thing that needs to be considered is that the agricultural production environment is affected by multiple factors (such as climate, soil, etc.). The interactions between these factors are complex and highly dynamic. At the same time, a large amount of agricultural data needs to be uploaded to the cloud or other platforms. Since agricultural data may involve sensitive data, there may be problems such as privacy leakage and data abuse during data sharing and use, and there is a problem of low accuracy in crop planting area planning. Summary of the invention

[0009] The embodiment of the present application solves the problem of low accuracy of crop planting area planning in the prior art by providing a crop planting area planning method based on big data, thereby improving the accuracy of crop planting area planning.

[0010] The embodiment of the present application provides a method for planning crop planting areas based on big data, comprising the following steps: S1, collecting crop-related data within a crop planting area to be planned within a preset time interval, and preprocessing the crop-related data to obtain crop planting data; S2, evaluating the effect of preprocessing the crop-related data to obtain a crop preprocessing effect score, and judging whether to perform a planting resource utilization compliance assessment based on the crop preprocessing effect score, wherein the crop preprocessing effect score is used to quantitatively evaluate the effect of preprocessing of the crop-related data; S3, obtaining a crop resource utilization score after performing a planting resource utilization compliance assessment, and judging whether to perform crop planting area pre-planning based on the crop resource utilization score, wherein the crop resource utilization score is used to quantitatively evaluate the degree of compliance of crop planting resource utilization; S4, after performing crop planting area pre-planning, evaluating the effect of crop planting area pre-planning to obtain a crop planning effect score, and judging whether to perform crop planting area secondary planning based on the crop planning effect score, wherein the crop planning effect score is used to quantitatively evaluate the effect of crop planting area pre-planning.

[0011] Furthermore, the crop-related data include crop-related resource data and crop-related planting data; the crop-related resource data include crop soil resource data, crop climate resource data, crop water resource data and terrain resource data; the crop-related planting data include crop planting variety information data, crop planting temperature information data, crop planting pH information data, crop planting water demand information data and crop planting maximum slope information data.

[0012] Furthermore, the specific steps of evaluating the effect of preprocessing crop-related data to obtain a crop preprocessing effect score are as follows: obtaining preprocessing evaluation effect data within a preset time interval, the preprocessing evaluation effect data including the amount of processed data outliers, the total amount of processed data, the processed data evaluation skewness value, and the processed data evaluation kurtosis value; obtaining a crop preprocessing effect score based on the preprocessing evaluation effect data combined with preprocessing evaluation reference data obtained from a preset database; the preprocessing evaluation reference data including a preprocessing evaluation reference optimal value and a preprocessing evaluation weight; the preprocessing evaluation reference optimal value including a reference evaluation optimal skewness value and a reference evaluation optimal kurtosis value; the preprocessing evaluation weights including a processing outlier evaluation weight, a processing skewness evaluation weight, and a processing kurtosis evaluation weight.

[0013] Furthermore, the specific process of judging whether to execute the planting resource utilization compliance assessment based on the crop pretreatment effect score is: comparing the crop pretreatment effect score with the preset treatment effect threshold range obtained from a preset database; if the crop pretreatment effect score is within the preset treatment effect threshold range, then executing the planting resource utilization compliance assessment, and simultaneously obtaining the crop resource utilization score after executing the planting resource utilization compliance assessment; if the crop pretreatment effect score exceeds the preset treatment effect threshold range, then not executing the planting resource utilization compliance assessment, and simultaneously reminding the preset personnel to re-execute crop-related data preprocessing until the crop pretreatment effect score is within the preset treatment effect threshold range.

[0014] Furthermore, the specific steps for obtaining the crop resource utilization score after executing the planting resource utilization compliance assessment are as follows: obtaining resource utilization related data within a preset time interval, the resource utilization related data including the compliance score of crop pretreatment effect, the average planting resource temperature, the planting resource pH value, the maximum planting water resource and the planting land slope value; combining the resource utilization related data with the resource utilization assessment data obtained from a preset database to obtain the crop resource utilization score, the resource utilization assessment data including resource utilization assessment reference values ​​and resource utilization assessment factors; the resource utilization assessment reference values ​​including the best reference effect score, the crop growth temperature reference value, the crop growth pH reference value, the crop growth water demand reference value and the crop growth maximum slope reference value; the resource utilization assessment factors including resource assessment influencing factors, pest and disease risk factors, resource climate compliance weights, resource pH compliance weights, water resource compliance weights, land slope resource compliance weights and pest and disease risk compliance weights.

[0015] Furthermore, the method for obtaining the crop resource utilization score is as follows:

[0016]

[0017] In the formula, NL represents the crop resource utilization score, γ represents the resource assessment influencing factor, NY' represents the score that meets the crop pretreatment effect, and ΔNY represents the best reference effect score. represents the average temperature of planting resources, W' represents the reference value of crop growth temperature, Indicates the pH value of planting resources, PH ‘ Indicates the pH reference value for crop growth. represents the maximum value of planting water resources, M' represents the reference value of crop growth water demand, Sl represents the slope value of planting land, MAX Sl It represents the maximum slope reference value for crop growth, φ represents the pest and disease risk factor, α1 represents the resource climate compliance weight, α2 represents the resource PH compliance weight, α3 represents the water resource compliance weight, α4 represents the land slope resource compliance weight, and α5 represents the pest and disease risk compliance weight.

[0018] Furthermore, the specific process of judging whether to execute crop planting area pre-planning based on the crop resource utilization score is: comparing the crop resource utilization score with a preset resource utilization threshold range obtained from a preset database; if the crop resource utilization score is within the preset resource utilization threshold range, then executing crop planting area pre-planning, and at the same time evaluating the effect of crop planting area pre-planning to obtain a crop planning effect score; if the crop resource utilization score exceeds the preset resource utilization threshold range, then not executing crop planting area pre-planning, and at the same time reminding the preset personnel to optimize the planting resource utilization.

[0019] Furthermore, the specific process of optimizing the utilization of planting resources is as follows: A1, optimizing soil conditions in the crop planting area, when the crop resource utilization score after soil condition optimization is within the preset resource utilization threshold range, stopping the optimization of the utilization of planting resources, otherwise executing A2; A2, optimizing water resources in the crop planting area, when the crop resource utilization score after water resource optimization is within the preset resource utilization threshold range, stopping the optimization of the utilization of planting resources, otherwise executing A3; A3, performing precise management optimization on the crop planting area, and the precise management optimization includes land suitability optimization and pest and disease risk optimization.

[0020] Furthermore, the specific steps of evaluating the effect of the pre-planning of the crop planting area to obtain the crop planning effect score are as follows: obtaining planning effect evaluation data after executing the pre-planning of the crop planting area, the planning effect evaluation data including the planned crop resource utilization score, the area of ​​the crop planting area, the annual respiration of the crop planting and the crop Shannon diversity index; obtaining the crop planning effect score according to the planning effect evaluation data combined with the planning effect reference data obtained from a preset database, the planning effect reference data including a planning effect reference value and a planning effect evaluation weight; the planning effect reference value including the best reference resource utilization score, the reference optimal carbon emissions and the reference maximum Shannon diversity index of crops; the planning effect evaluation weights including the resource planning effect evaluation weight, the carbon emission effect evaluation weight and the crop diversity evaluation weight.

[0021] Furthermore, the specific process of judging whether to execute secondary planning of crop planting areas based on crop planning effect scores is: comparing the crop planning effect score with a preset planning effect threshold range obtained from a preset database; if the crop planning effect score is within the preset planning effect threshold range, secondary planning of crop planting areas is executed, and data sharing optimization of crop planting data is performed at the same time; if the crop planning effect score exceeds the preset planning effect threshold range, secondary planning of crop planting areas is not executed, and preset personnel are reminded to re-acquire crop-related data.

[0022] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0023] 1. Evaluate the effect of preprocessing crop-related data to determine whether the implementation of planting resource utilization conforms to the assessment, then obtain the crop resource utilization score after the implementation of the planting resource utilization conformity assessment, and determine whether to implement crop planting area pre-planning, and finally evaluate the effect of crop planting area pre-planning to determine whether to implement crop planting area secondary planning, thereby achieving numerical evaluation of the degree of compliance of crop planting resource utilization and the effect of planting area pre-planning, thereby achieving improved accuracy of crop planting area planning, and effectively solving the problem of low accuracy of crop planting area planning in the prior art.

[0024] 2. By obtaining resource utilization related data within a preset time interval, and then combining the resource utilization related data with the resource utilization assessment data obtained from a preset database, a crop resource utilization score is obtained, thereby realizing a numerical assessment of the degree of compliance with crop planting resource utilization, and further realizing a more accurate assessment of the degree of compliance with crop planting resource utilization.

[0025] 3. By obtaining the planning effect evaluation data after executing the pre-planning of the crop planting area, and then combining the planning effect evaluation data with the planning effect reference data obtained from the preset database to obtain the crop planning effect score, the numerical evaluation of the pre-planning effect of the crop planting area is realized, thereby realizing a more accurate evaluation of the pre-planning effect of the crop planting area. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A flowchart of a method for crop planting area planning based on big data provided in an embodiment of the present application;

[0027] Figure 2 A schematic diagram of the change of crop pretreatment effect score provided in an embodiment of the present application, wherein (a) is a schematic diagram of the change of crop pretreatment effect score with the amount of abnormal value data in the processing data, and (b) is a schematic diagram of the change of crop pretreatment effect score with the skewness value of the processing data evaluation. DETAILED DESCRIPTION

[0028] The embodiment of the present application solves the problem of low accuracy of crop planting area planning in the prior art by providing a crop planting area planning method based on big data. The crop planting data is obtained by preprocessing crop-related data, and then the effect of the preprocessing of the crop-related data is evaluated to obtain a crop preprocessing effect score. Based on the crop preprocessing effect score, it is determined whether to execute the planting resource utilization compliance assessment, and then the crop resource utilization score after the execution of the planting resource utilization compliance assessment is obtained, and it is determined whether to execute crop planting area pre-planning. Finally, the effect of the crop planting area pre-planning is evaluated to obtain a crop planning effect score. Based on the crop planning effect score, it is determined whether to execute crop planting area secondary planning, thereby improving the accuracy of crop planting area planning.

[0029] The technical solution in the embodiment of the present application is to solve the problem of low accuracy of the above-mentioned crop planting area planning, and the overall idea is as follows:

[0030] The effect of preprocessing crop-related data is evaluated to determine whether the utilization of planting resources complies with the assessment. Then, the crop resource utilization score after the utilization of planting resources complies with the assessment is obtained, and it is determined whether to implement crop planting area pre-planning. Finally, the effect of crop planting area pre-planning is evaluated to determine whether to implement crop planting area secondary planning, thereby achieving the effect of improving the accuracy of crop planting area planning.

[0031] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0032] like Figure 1As shown, it is a flowchart of a method for planning crop planting areas based on big data provided by an embodiment of the present application, and the method includes the following steps: S1, collecting crop-related data in the crop planting area to be planned within a preset time interval, and preprocessing the crop-related data to obtain crop planting data; S2, evaluating the effect of preprocessing the crop-related data to obtain a crop preprocessing effect score, judging whether to perform a planting resource utilization compliance assessment based on the crop preprocessing effect score, and the crop preprocessing effect score is used to quantitatively evaluate the effect of preprocessing of the crop-related data; S3, obtaining the crop resource utilization score after performing the planting resource utilization compliance assessment, judging whether to perform crop planting area pre-planning based on the crop resource utilization score, and the crop resource utilization score is used to quantitatively evaluate the degree of compliance of crop planting resource utilization; S4, after performing crop planting area pre-planning, evaluating the effect of crop planting area pre-planning to obtain a crop planning effect score, judging whether to perform crop planting area secondary planning based on the crop planning effect score, and the crop planning effect score is used to quantitatively evaluate the effect of crop planting area pre-planning.

[0033] It should be added that crop-related data and historical crop-related data are obtained through big data technologies (such as geographic information systems), and crop-related data are distributedly stored through big data storage tools such as Hadoop and HDFS (Hadoop Distributed File System); among them, crop-related data include crop-related resource data and crop-related planting data; crop-related resource data include crop soil resource data, crop climate resource data, crop water resource data and terrain resource data.

[0034] Specifically, crop soil resource data is obtained by deploying soil sensors in the planned crop planting area, crop climate resource data is obtained through meteorological stations, crop water resource data is obtained through hydrological monitoring stations, and terrain resource data is obtained through laser scanning technology.

[0035] Crop-related planting data include crop variety information data, crop planting temperature information data, crop planting pH information data, crop planting water demand information data and crop planting maximum slope information data; among them, crop planting temperature information data refers to the most suitable temperature data for crop planting and growth, for example, the most suitable temperature data for general crops (such as rice) is 25 degrees Celsius; crop planting pH information data refers to the most suitable pH data for crop planting and growth, for example, the most suitable pH data for general crops (such as rice) is 6; crop planting water demand information data refers to the water resources data required for crop planting and growth, for example, the water resources data required for general crops (such as rice) is 5,000 cubic meters / hectare; crop planting maximum slope information data refers to the maximum slope data tolerated by crop planting and growth, for example, the maximum slope data tolerated by general crops (such as rice) is 10°.

[0036] Specifically, crop variety information data is obtained through agricultural databases (such as the agricultural information platform of the Chinese Academy of Agricultural Sciences), and crop planting temperature information data, crop planting pH information data, crop planting water demand information data and crop planting maximum slope information data are obtained through crop growth simulation software such as DSSAT (Decision Support System for Agrotechnological Transfer).

[0037] It should be understood that preprocessing includes data cleaning and data filtering. Data cleaning refers to processing missing values ​​of crop-related data through interpolation algorithms and outlier processing of crop-related data through the Z-score method (data that deviate from the mean by more than 3 standard deviations are outliers); data filtering refers to filtering crop-related data through moving average.

[0038] By preprocessing crop-related data to obtain crop planting data, the effect of crop-related data preprocessing and the degree of compliance of crop planting resource utilization are evaluated, thereby improving the reliability of crop planting area planning.

[0039] Furthermore, the specific steps of evaluating the effect of preprocessing crop-related data to obtain a crop preprocessing effect score are as follows: obtaining preprocessing evaluation effect data within a preset time interval, the preprocessing evaluation effect data including the amount of outlier data in the processed data (i.e., the number of outliers), the total amount of processed data, the skewness value of the processed data evaluation, and the kurtosis value of the processed data evaluation; obtaining a crop preprocessing effect score based on the preprocessing evaluation effect data combined with preprocessing evaluation reference data obtained from a preset database; the preprocessing evaluation reference data including a preprocessing evaluation reference optimal value and a preprocessing evaluation weight; the preprocessing evaluation reference optimal value including a reference evaluation optimal skewness value and a reference evaluation optimal kurtosis value; the preprocessing evaluation weights including a processing outlier evaluation weight, a processing skewness evaluation weight, and a processing kurtosis evaluation weight.

[0040] The method for obtaining the crop pretreatment effect score is as follows:

[0041]

[0042] In the formula, NY represents the crop pretreatment effect score, δ1 represents the treatment outlier evaluation weight, δ2 represents the treatment skewness evaluation weight, δ3 represents the treatment kurtosis evaluation weight, and Y cp A represents the amount of abnormal data in the processing data within the preset time interval. cp Indicates the total amount of processed data within a preset time interval, S cp Indicates the skewness value of the processed data evaluation, S ‘ cp represents the optimal skewness value for reference evaluation, K cp Indicates the kurtosis value of the processed data, K ’ cp Denotes the optimal kurtosis value for reference evaluation.

[0043] In this embodiment, the amount of outlier data and the total amount of processed data are obtained through Python libraries (such as Pandas and NumPy); the skewness value of processed data evaluation is obtained through Python libraries (such as scipy.stats.skew function); and the kurtosis value of processed data evaluation is obtained through Python libraries (such as scipy.stats.kurtosis function).

[0044] The optimal skewness value for reference evaluation refers to the optimal skewness value for crop planting data preprocessing, which is obtained from the preset database and is generally a positive number infinitely close to 0; the optimal kurtosis value for reference evaluation refers to the optimal kurtosis value for crop planting data preprocessing, which is obtained from the preset database and is generally 3.

[0045] The outlier processing evaluation weight, skewness processing evaluation weight and kurtosis processing evaluation weight are used to reflect the influence of the crop planting data preprocessing outliers, skewness and kurtosis on the crop preprocessing effect score. They can be directly obtained from the preset database when used. Specifically, the crop planting data preprocessing outliers, skewness and kurtosis are respectively matched with the outlier processing evaluation weights, skewness processing evaluation weights and kurtosis processing evaluation weights preset in the preset database to form a mapping set, and the real-time crop planting data preprocessing outliers, skewness and kurtosis are input into the mapping set to obtain the corresponding weights, wherein the mapping relationship is one-to-one correspondence. In this example, the value range is [0, 1], and the sum of the outlier processing evaluation weight, skewness processing evaluation weight and kurtosis processing evaluation weight in this example is 1.

[0046] like Figure 2 As shown, it is a schematic diagram of the change of the crop pretreatment effect score provided in the embodiment of the present application, wherein it is set that: the processing outlier evaluation weight is 0.4, the processing skewness evaluation weight is 0.3, the processing kurtosis evaluation weight is 0.3, the total processing data volume is 1000, the reference evaluation optimal skewness value is 0, the processing data evaluation kurtosis value is 3, and the reference evaluation optimal kurtosis value is 3; wherein (a) is a schematic diagram of the change of the crop pretreatment effect score with the amount of processing data outlier data, specifically, the processing data evaluation skewness value is set to 0.5, and as the amount of processing data outlier data increases, the crop pretreatment effect score decreases accordingly; (b) is a schematic diagram of the change of the crop pretreatment effect score with the processing data evaluation skewness value, specifically, the processing data outlier data volume is set to 500, and as the degree of deviation between the processing data evaluation skewness value and the reference evaluation optimal skewness value increases, the crop pretreatment effect score also decreases accordingly.

[0047] The crop pretreatment effect score is used to quantitatively evaluate the effect of crop-related data preprocessing. Specifically, the crop pretreatment effect score includes multiple parameters, and each parameter is related to each other and does not exist independently. For example, as the deviation between the skewness value of the processed data evaluation and the optimal skewness value of the reference evaluation increases, the data set will have more outliers, that is, the amount of processed data outliers increases, which in turn leads to a decrease in the crop pretreatment effect score; in addition, as the amount of processed data outliers increases, the distribution of the data becomes more extreme, that is, the deviation between the kurtosis value of the processed data evaluation and the optimal kurtosis value of the reference evaluation increases, which in turn leads to a decrease in the crop pretreatment effect score; therefore, the amount of processed data outliers, the processing The skewness value of data evaluation and the kurtosis value of processed data evaluation both have an impact on the crop pretreatment effect score. Specifically, with the increase in the amount of processed data outliers, the crop pretreatment effect score decreases accordingly. With the increase in the degree of deviation between the skewness value and kurtosis value of processed data evaluation and the corresponding optimal skewness value and optimal kurtosis value of reference evaluation, the crop pretreatment effect score also decreases accordingly. Therefore, considering the correlation and mutual influence between various factors, the crop pretreatment effect score is obtained through comprehensive analysis, and the numerical evaluation of the crop-related data pretreatment effect is realized. The crop-related data pretreatment effect is judged through numerical evaluation, thereby achieving the improvement of the accuracy of the evaluation of the crop-related data pretreatment effect.

[0048] Furthermore, the specific process of judging whether to execute the planting resource utilization compliance assessment based on the crop pretreatment effect score (referring to obtaining the crop resource utilization score after executing the planting resource utilization compliance assessment) is as follows: compare the crop pretreatment effect score with the preset treatment effect threshold range obtained from the preset database; if the crop pretreatment effect score is within the preset treatment effect threshold range, then the planting resource utilization compliance assessment is executed, and the crop resource utilization score after executing the planting resource utilization compliance assessment is obtained; if the crop pretreatment effect score exceeds the preset treatment effect threshold range, then the planting resource utilization compliance assessment is not executed, and the preset personnel are reminded to re-execute crop-related data preprocessing until the crop pretreatment effect score is within the preset treatment effect threshold range.

[0049] In this embodiment, specifically, the preset processing effect threshold range is set by professionals according to standards in the field. For example, the preset processing effect threshold range is set to 0.690 to 0.750. By combining the preset processing effect threshold range for judgment and performing a planting resource utilization compliance assessment, a more accurate judgment of the preprocessing effect of crop-related data is achieved.

[0050] Furthermore, the specific steps for obtaining the crop resource utilization score after executing the planting resource utilization compliance assessment are as follows: obtaining resource utilization related data within a preset time interval, the resource utilization related data including the compliance score of crop pretreatment effect, the average planting resource temperature, the planting resource pH value, the maximum planting water resource and the planting land slope value; combining the resource utilization related data with the resource utilization assessment data obtained from a preset database to obtain the crop resource utilization score, the resource utilization assessment data including resource utilization assessment reference values ​​and resource utilization assessment factors; the resource utilization assessment reference values ​​including the best reference effect score, the crop growth temperature reference value, the crop growth pH reference value, the crop growth water demand reference value and the crop growth maximum slope reference value; the resource utilization assessment factors including resource assessment influencing factors, pest and disease risk factors, resource climate compliance weights, resource pH compliance weights, water resource compliance weights, land slope resource compliance weights and pest and disease risk compliance weights.

[0051] The method to obtain the crop resource utilization score is as follows:

[0052]

[0053]

[0054] In the formula, NL represents the crop resource utilization score, γ represents the resource assessment influencing factor, NY' represents the score that meets the crop pretreatment effect, and ΔNY represents the best reference effect score. represents the average temperature of planting resources, W' represents the reference value of crop growth temperature, Indicates the pH value of planting resources, PH ‘ Indicates the pH reference value for crop growth. represents the maximum value of planting water resources, M' represents the reference value of crop growth water demand, Sl represents the slope value of planting land, MAX Sl Indicates the maximum slope reference value for crop growth. It represents the pest and disease risk factor, α1 represents the resource climate compliance weight, α2 represents the resource PH compliance weight, α3 represents the water resource compliance weight, α4 represents the land slope resource compliance weight, and α5 represents the pest and disease risk compliance weight.

[0055] In this embodiment, the crop pretreatment effect score refers to the crop pretreatment effect score after the planting resource utilization compliance assessment is performed. The average planting resource temperature value is represented by averaging the crop climate resource data. The planting resource pH value is obtained by deploying a soil pH sensor in the planned crop planting area. The maximum planting water resource value is represented by the maximum value in the collected crop water resource data. The planting land slope value is obtained by the total station.

[0056] The optimal reference effect score is generally set to the middle value of the preset treatment effect threshold range. The crop growth temperature reference value is represented by summing and averaging the collected historical crop planting temperature information data. The crop growth pH reference value is represented by summing and averaging the collected historical crop planting pH information data. The crop growth water demand reference value is represented by summing and averaging the collected historical crop planting water demand information data. The crop growth maximum slope reference value is represented by the maximum value of the collected historical crop planting maximum slope information data.

[0057] The resource assessment influencing factor is used to reflect the degree of influence of the preprocessing effect of crop-related data in the planting resource utilization compliance assessment on the crop resource utilization score. A mapping set is formed by the preprocessing effect of crop-related data in the planting resource utilization compliance assessment and the influencing factors corresponding to the resource assessment preset in the preset database. The preprocessing effect of crop-related data in the real-time planting resource utilization compliance assessment is input into the mapping set to obtain the corresponding weight. The mapping relationship can be one-to-one or many-to-one. In this example, the value range is [0, 1].

[0058] In this example, the resource climate compliance weight, resource pH compliance weight, water resource compliance weight, land slope resource compliance weight, and pest and disease risk compliance weight all have a value range of [0, 1], and the sum is 1. Specifically, they can be directly obtained from the preset database when used, wherein the climate, pH, water resources, land slope, and pest and disease risk in the real-time planting resource utilization compliance assessment are input into the preset mapping set in the database to obtain the corresponding weights, wherein the mapping relationship can be one-to-one or many-to-one. The resource climate compliance weight, resource pH compliance weight, water resource compliance weight, land slope resource compliance weight, and pest and disease risk compliance weight are used to reflect the influence of climate, pH, water resources, land slope, and pest and disease risk in the planting resource utilization compliance assessment on the crop resource utilization score.

[0059] The crop resource impact score is used to quantitatively evaluate the compliance of crop planting resource utilization. Specifically, the crop resource impact score includes multiple parameters, and each parameter is related and does not exist independently. For example, as the deviation between the average planting resource temperature and the crop growth temperature reference value decreases, it indicates that the resource climate compliance increases, and thus the crop resource utilization score increases accordingly. In addition, as the deviation between the planting land slope value and the maximum crop growth slope reference value decreases, it indicates that the land slope resource compliance decreases. At the same time, as the planting land slope value increases, the slope affects water loss and soil stability, that is, the maximum planting water resource value decreases accordingly. The deviation between the maximum value of planting water resources and the reference value of crop growth water demand increases, which in turn reduces the crop resource utilization score. At the same time, with the increase of the average temperature of planting resources, the increase in temperature will accelerate the evaporation of water, resulting in an increase in crop water demand, that is, the maximum value of planting water resources decreases accordingly. Therefore, through a quantitative approach, the correlation and mutual influence between various factors are taken into account, and the crop resource impact score is obtained through a comprehensive analysis, which realizes the numerical evaluation of the compliance degree of crop planting resource utilization. The compliance degree of crop planting resource utilization is judged through numerical evaluation, thereby achieving the improvement of the accuracy of the assessment of the compliance degree of crop planting resource utilization in the process of crop planting area planning.

[0060] Furthermore, the specific process of judging whether to execute crop planting area pre-planning based on the crop resource utilization score is as follows: comparing the crop resource utilization score with a preset resource utilization threshold range obtained from a preset database; if the crop resource utilization score is within the preset resource utilization threshold range, then executing crop planting area pre-planning, and at the same time evaluating the effect of crop planting area pre-planning to obtain a crop planning effect score; if the crop resource utilization score exceeds the preset resource utilization threshold range, then not executing crop planting area pre-planning, and at the same time reminding the preset personnel to optimize the utilization of planting resources.

[0061] In this embodiment, geographic information system tools (such as ArcGIS (Arc Geograph ic Information System) and QGIS (Quantum Geograph ic Information System)) are used to perform geographic space overlay and visualization analysis, and spatial optimization algorithms such as genetic algorithms, simulated annealing algorithms, ant colony algorithms and other optimization algorithms are used to perform regional division. Visualization tools (such as Power BI and Tableau) are used for visualization processing to achieve pre-planning of crop planting areas.

[0062] Among them, the preset resource utilization threshold range is set by professionals according to the standards in the field. For example, the range of crop pretreatment effect scores (generally 0.70 to 0.75), the average temperature range of planting resources (generally 0 degrees Celsius to 30 degrees Celsius), the pH value range of planting resources (generally 4 to 9), the maximum value range of planting water resources (generally 100 cubic meters / hectare to 1000 cubic meters / hectare), and the slope value range of planting land (generally 0° to 45°) are set to determine the preset resource utilization threshold range; by combining the preset resource utilization threshold range for judgment, a more accurate judgment of the degree of compliance of crop planting resource utilization is achieved.

[0063] It should be added that the specific process of optimizing the utilization of planting resources is as follows: A1, optimizing soil conditions in crop planting areas. When the crop resource utilization score after soil condition optimization is within the preset resource utilization threshold range, the optimization of planting resource utilization is stopped, otherwise A2 is executed; A2, optimizing water resources in crop planting areas. When the crop resource utilization score after water resource optimization is within the preset resource utilization threshold range, the optimization of planting resource utilization is stopped, otherwise A3 is executed; A3, precise management optimization of crop planting areas, precise management optimization includes land suitability optimization and pest and disease risk optimization.

[0064] In this embodiment, soil condition optimization is achieved through precision fertilization algorithms and optimization algorithms (such as genetic algorithms and particle swarm optimization). For example, multiple fertilization schemes are randomly generated and the optimal scheme is output according to the fitness function. Water resource optimization is achieved through a water resource allocation algorithm. For example, the particle position (i.e., water allocation amount) is updated by minimizing water resource allocation and the fitness of particles. Land suitability optimization is achieved through machine learning algorithms (such as support vector machines and random forests). For example, the features that have the greatest impact on land suitability are selected using feature selection methods (such as random forest importance assessment). Pest and disease risk optimization is achieved through machine learning algorithms (such as decision trees and time series analysis). The reliability of crop resource utilization in crop planting area planning under abnormal conditions is improved through optimization of crop resource utilization.

[0065] Furthermore, the specific steps for evaluating the effect of pre-planning of crop planting areas to obtain crop planning effect scores are as follows: obtaining planning effect evaluation data after executing pre-planning of crop planting areas, the planning effect evaluation data including planned crop resource utilization score, crop planting area, crop planting annual respiration volume and crop Shannon diversity index; obtaining crop planning effect scores according to the planning effect evaluation data combined with planning effect reference data obtained from a preset database, the planning effect reference data including planning effect reference values ​​and planning effect evaluation weights; planning effect reference values ​​including optimal reference resource utilization score, reference optimal carbon emissions and crop reference maximum Shannon diversity index; planning effect evaluation weights including resource planning effect evaluation weights, carbon emission effect evaluation weights and crop diversity evaluation weights.

[0066] The method to obtain the crop planning effect score is as follows:

[0067]

[0068] In the formula, NG represents the crop planning effect score, β1 represents the resource planning effect evaluation weight, β2 represents the carbon emission effect evaluation weight, β3 represents the crop diversity evaluation weight, and NL ’ represents the planned crop resource utilization score, ΔNL represents the optimal reference resource utilization score, SJ represents the crop planting area, RH represents the annual respiration of crop planting, γ C represents the carbon emission influencing factor, ΔY represents the reference optimal carbon emission, SW represents the crop Shannon diversity index, MAX SW Represents the reference maximum Shannon diversity index of crops.

[0069] In this embodiment, the planned crop resource utilization score refers to the crop resource utilization score after the pre-planning of the crop planting area is executed. The area of ​​the crop planting area is obtained through satellite data (such as Landsat or Sentinel satellite) or drone images, and the annual respiration of crop planting is obtained through crop biomass models (such as CropSyst, APSIM). The Shannon diversity index of crops is obtained by using the diversity() function in the vegan package in the R language.

[0070] The optimal reference resource utilization score is generally set as the middle value of the preset resource utilization threshold range. The reference optimal carbon emissions are represented by summing and averaging the collected historical crop carbon emissions. The maximum value obtained by statistically analyzing the collected historical crop Shannon diversity index represents the reference maximum Shannon diversity index of crops.

[0071] The carbon emission impact factor is obtained from the preset database, with a value range of [0, 1], which is used to reflect the influence of carbon emission impact factors (such as greenhouse gas content) on the crop planning effect score. The real-time carbon emission impact factors (such as greenhouse gas content) are input into the preset mapping set in the database to obtain the corresponding impact factor.

[0072] The degree of compliance with crop planting resource utilization (i.e., the planned crop resource utilization score), crop carbon emissions, and crop Shannon diversity index are respectively matched with the resource planning effect evaluation weights, carbon emission effect evaluation weights, and crop diversity evaluation weights preset in the preset database to form a mapping set, and the real-time crop planting resource utilization compliance, crop carbon emissions, and crop Shannon diversity index are input into the mapping set preset in the database to obtain the corresponding weights. Specifically, the resource planning effect evaluation weights, carbon emission effect evaluation weights, and crop diversity evaluation weights are used to reflect the influence of the degree of compliance with crop planting resource utilization, crop carbon emissions, and crop Shannon diversity index on the crop planning effect score. In this example, the value range is [0, 1].

[0073] Specific assumptions: the resource planning effect evaluation weight is 0.5, the carbon emission effect evaluation weight is 0.3, the crop diversity evaluation weight is 0.2, the optimal reference resource utilization score is 0.8, the carbon emission impact factor is 0.7, the reference optimal carbon emission is 700tCO2 / year, and the crop reference maximum Shannon diversity index is 10; the crop planning effect score can be calculated by the above method, and the change statistics of the crop planning effect score are shown in Table 1:

[0074] Table 1 Statistics of changes in crop planning effect scores

[0075]

[0076] It can be seen from the first, second and third groups of data in Table 1 that with the decrease of planned crop resource utilization score, the crop planning effect score decreases accordingly; at the same time, as can be seen from the third, fourth and fifth groups of data, with the decrease of crop Shannon diversity index, the crop planning effect score also decreases; in addition, the area of ​​crop planting area also affects the crop planning effect score, specifically, with the increase of the deviation between the product of crop planting area, annual crop planting respiration and carbon emission impact factor and the reference optimal carbon emission, the crop Shannon diversity index also decreases.

[0077] The crop planning effect score is used to quantitatively evaluate the effect of pre-planning of crop planting areas. Among them, the planned crop resource utilization score, the area of ​​crop planting area, the annual respiration of crop planting and the change of crop Shannon diversity index all have an impact on the crop planning effect score. Specifically, for example, as the planned crop resource utilization score decreases, the crop planning effect score also decreases; in addition, the crop planning effect score includes multiple parameters, and the various parameters are related and do not exist independently. For example, as the planned crop resource utilization score increases, it shows that efficient resource utilization can increase biodiversity. That is, the Shannon diversity index of crops increases, and thus the crop planning effect score increases accordingly; at the same time, with the increase of the planned crop resource utilization score, it is often accompanied by the expansion of the planting area, that is, the area of ​​crop planting area increases, and thus the crop planning effect score also increases accordingly; therefore, through a quantitative approach, the correlation and mutual influence between various factors are taken into account, and the crop planning effect score is obtained through comprehensive analysis, which realizes the numerical evaluation of the pre-planning effect of crop planting areas, and the crop pre-planning effect is judged through numerical evaluation, thereby realizing a more accurate evaluation of the pre-planning effect of crop planting areas.

[0078] Furthermore, the specific process of judging whether to execute secondary planning of crop planting areas based on the crop planning effect score is as follows: comparing the crop planning effect score with a preset planning effect threshold range obtained from a preset database; if the crop planning effect score is within the preset planning effect threshold range, secondary planning of crop planting areas is executed, and data sharing optimization of crop planting data is performed at the same time; if the crop planning effect score exceeds the preset planning effect threshold range, secondary planning of crop planting areas is not executed, and preset personnel are reminded to re-acquire crop-related data.

[0079] In this embodiment, since the crop planting data is confidential, in order to ensure the security of the crop planting data when relevant parties (such as agricultural companies, research institutions, government departments, farmers, etc.) access it, it is necessary to optimize the data sharing of the crop planting data. Specifically, the data sharing optimization is performed by encrypting the crop planting data using hybrid encryption. For example, a symmetric encryption key is transmitted through asymmetric encryption, and then the data is encrypted using symmetric encryption; secondly, the crop planting data is encrypted and shared through an encrypted transmission channel (such as IPSec).

[0080] Specifically, the preset planning effect threshold range is set by professionals according to standards in the field. For example, the preset planning effect threshold range is set to 0.68 to 0.80. By combining the preset planning effect threshold range to determine whether to conduct secondary planning of the crop planting area, a more accurate judgment of the pre-planning effect of the crop planting area is achieved.

[0081] To summarize, the embodiment of the present application evaluates the effect of preprocessing crop-related data to determine whether to execute the planting resource utilization compliance assessment, then obtains the crop resource utilization score after the planting resource utilization compliance assessment, and determines whether to execute crop planting area pre-planning, and finally evaluates the effect of crop planting area pre-planning to determine whether to execute crop planting area secondary planning, thereby achieving a numerical evaluation of the degree of compliance of crop planting resource utilization and the effect of planting area pre-planning, and then achieving an improvement in the accuracy of crop planting area planning, effectively solving the problem of low accuracy of crop planting area planning in the prior art.

[0082] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0083] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0084] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0085] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0086] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0087] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A crop planting area planning method based on big data, characterized in that: The following steps are involved: S1, collecting crop-related data in the planned crop planting area within a preset time interval, and preprocessing the crop-related data to obtain crop planting data; S2, evaluating the effect of preprocessing the crop-related data to obtain a crop preprocessing effect score, and judging whether to perform the planting resource utilization compliance assessment based on the crop preprocessing effect score, wherein the crop preprocessing effect score is used to quantitatively evaluate the effect of preprocessing the crop-related data; S3, obtaining a crop resource utilization score after executing the planting resource utilization compliance assessment, and judging whether to execute the crop planting area pre-planning based on the crop resource utilization score, wherein the crop resource utilization score is used to quantitatively assess the compliance degree of the crop planting resource utilization; S4, after executing the pre-planning of the crop planting area, evaluate the effect of the pre-planning of the crop planting area to obtain a crop planning effect score, and determine whether to execute secondary planning of the crop planting area based on the crop planning effect score. The crop planning effect score is used to quantitatively evaluate the effect of the pre-planning of the crop planting area.

2. A method for crop planting area planning based on big data as claimed in claim 1, characterized in that: The crop-related data includes crop-related resource data and crop-related planting data; The crop-related resource data include crop soil resource data, crop climate resource data, crop water resource data and terrain resource data; The crop-related planting data includes crop planting variety information data, crop planting temperature information data, crop planting pH information data, crop planting water demand information data and crop planting maximum slope information data.

3. A method for crop planting area planning based on big data as claimed in claim 1, characterized in that: The specific steps of evaluating the effect of preprocessing the crop-related data to obtain the crop preprocessing effect score are as follows: Acquire preprocessing evaluation effect data within a preset time interval, wherein the preprocessing evaluation effect data includes the amount of abnormal value data of the processed data, the total amount of processed data, the skewness value of the processed data evaluation, and the kurtosis value of the processed data evaluation; The crop pretreatment effect score is obtained by combining the pretreatment evaluation effect data with the pretreatment evaluation reference data obtained from a preset database; The preprocessing assessment reference data includes a preprocessing assessment reference optimal value and a preprocessing assessment weight; The pre-processing evaluation reference optimal value includes a reference evaluation optimal skewness value and a reference evaluation optimal kurtosis value; The preprocessing evaluation weights include processing outlier evaluation weights, processing skewness evaluation weights, and processing kurtosis evaluation weights.

4. The method for crop planting area planning based on big data as claimed in claim 1, characterized in that: The specific process of judging whether to perform the planting resource utilization compliance assessment based on the crop pretreatment effect score is as follows: comparing the crop pretreatment effect score with a preset treatment effect threshold range obtained from a preset database; If the crop pretreatment effect score is within the preset treatment effect threshold range, the planting resource utilization compliance assessment is performed, and the crop resource utilization score after the planting resource utilization compliance assessment is performed is obtained; If the crop pretreatment effect score exceeds the preset treatment effect threshold range, the planting resource utilization compliance assessment will not be performed, and the preset personnel will be reminded to re-perform crop-related data preprocessing until the crop pretreatment effect score is within the preset treatment effect threshold range.

5. A method for crop planting area planning based on big data as claimed in claim 4, characterized in that: The specific steps of obtaining the crop resource utilization score after the planting resource utilization compliance assessment is as follows: Obtaining resource utilization related data within a preset time interval, wherein the resource utilization related data includes a score of crop pretreatment effect, an average temperature of planting resources, a pH value of planting resources, a maximum value of planting water resources, and a slope value of planting land; Combining the resource utilization related data with the resource utilization assessment data obtained from a preset database to obtain a crop resource utilization score, wherein the resource utilization assessment data includes a resource utilization assessment reference value and a resource utilization assessment factor; The resource utilization assessment reference values ​​include the best reference effect score, crop growth temperature reference value, crop growth pH reference value, crop growth water requirement reference value and crop growth maximum slope reference value; The resource utilization assessment factors include resource assessment impact factors, pest and disease risk factors, resource climate compliance weights, resource pH compliance weights, water resource compliance weights, land slope resource compliance weights, and pest and disease risk compliance weights.

6. A method for crop planting area planning based on big data as claimed in claim 5, characterized in that: The method for obtaining the crop resource utilization score is as follows: In the formula, NL represents the crop resource utilization score, γ represents the resource assessment influencing factor, NY' represents the score that meets the crop pretreatment effect, and ΔNY represents the best reference effect score. represents the average temperature of planting resources, W' represents the reference value of crop growth temperature, Indicates the pH value of planting resources, PH ‘ Indicates the pH reference value for crop growth. represents the maximum value of planting water resources, M' represents the reference value of crop growth water demand, Sl represents the slope value of planting land, MAX Sl Indicates the maximum slope reference value for crop growth. It represents the pest and disease risk factor, α1 represents the resource climate compliance weight, α2 represents the resource PH compliance weight, α3 represents the water resource compliance weight, α4 represents the land slope resource compliance weight, and α5 represents the pest and disease risk compliance weight.

7. A method for crop planting area planning based on big data as claimed in claim 1, characterized in that: The specific process of judging whether to execute the crop planting area pre-planning based on the crop resource utilization score is as follows: comparing the crop resource utilization score to a preset resource utilization threshold range obtained from a preset database; If the crop resource utilization score is within the preset resource utilization threshold range, the crop planting area pre-planning is performed, and the effect of the crop planting area pre-planning is evaluated to obtain the crop planning effect score; If the crop resource utilization score exceeds the preset resource utilization threshold range, the crop planting area pre-planning will not be executed, and the preset personnel will be reminded to optimize the planting resource utilization.

8. A method for crop planting area planning based on big data as claimed in claim 7, characterized in that: The specific process of optimizing the utilization of planting resources is as follows: A1, optimize the soil conditions in the crop planting area. When the crop resource utilization score after soil condition optimization is within the preset resource utilization threshold range, stop planting and resource utilization is in line with optimization, otherwise execute A2; A2, optimize water resources in the crop planting area. When the crop resource utilization score after water resource optimization is within the preset resource utilization threshold range, stop planting and resource utilization is in line with optimization, otherwise execute A3; A3, precise management optimization of crop planting areas, including land suitability optimization and pest and disease risk optimization.

9. A method for crop planting area planning based on big data as claimed in claim 7, characterized in that: The specific steps of evaluating the effect of the pre-planning of the crop planting area to obtain the crop planning effect score are as follows: Acquiring planning effect evaluation data after executing the pre-planning of the crop planting area, wherein the planning effect evaluation data includes the planned crop resource utilization score, the area of ​​the crop planting area, the annual respiration of the crop planting, and the crop Shannon diversity index; Obtaining a crop planning effect score according to the planning effect evaluation data combined with planning effect reference data obtained from a preset database, wherein the planning effect reference data includes a planning effect reference value and a planning effect evaluation weight; The planning effect reference values ​​include the best reference resource utilization score, the best reference carbon emission and the maximum reference Shannon diversity index of crops; The planning effect evaluation weights include resource planning effect evaluation weights, carbon emission effect evaluation weights and crop diversity evaluation weights.

10. A method for crop planting area planning based on big data as claimed in claim 1, characterized in that: The specific process of judging whether to perform secondary planning of crop planting areas based on the crop planning effect score is as follows: comparing the crop planning effect score with a preset planning effect threshold range obtained from a preset database; If the crop planning effect score is within the preset planning effect threshold, the crop planting area secondary planning is performed, and the crop planting data is optimized for data sharing; If the crop planning effect score exceeds the preset planning effect threshold range, the secondary planning of the crop planting area will not be performed, and the preset personnel will be reminded to re-acquire crop-related data.

Images