A crop precision fertilization method and system based on big data platform

Through the method of the big data platform, the problem of difficult to implement crop soil measurement and fertilization technology has been solved, the accuracy of fertilization has been improved, and the guidance of scientific fertilization has been achieved.

CN116629494BActive Publication Date: 2024-11-19WUXI BRANCH CHONGQING CITY COMPANY OF CHINA NAT TOBACCO
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310657426.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-06-05
Publication Date
2024-11-19
Estimated Expiration
2043-06-05

AI Technical Summary

Technical Problem

In the prior art, it is difficult to implement the technical plan for soil measurement and fertilization, resulting in low fertilization accuracy.

Method used

Using the precision fertilization method of crops based on the big data platform, soil nutrient determination is carried out by collecting farmland soil samples, and soil nutrient full coverage information is constructed using spatial interpolation method, an electronic map of soil nutrients is established, and nutrient factor analysis and accumulation are carried out based on crop variety yield information. , construct a crop recommended fertilization model, calculate and send the recommended fertilization amount to the user's smart terminal.

Benefits of technology

The guidance of scientific fertilization has been achieved, the accuracy of crop fertilization has been improved, and the accuracy and effectiveness of the fertilization amount has been ensured.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116629494B_ABST
    Figure CN116629494B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system for crop precision fertilization based on a big data platform, and relates to the field of data processing technology. The method comprises: obtaining sample soil nutrient information, converting sample point data into surface data using a spatial interpolation method according to the distribution characteristics of farmland soil samples, constructing soil nutrient farmland full coverage information of the sampling area, combining the sampling area positioning information, establishing a soil nutrient electronic map and sending it to a user intelligent terminal, partitioning the sampling area soil, obtaining a field test data set, building a crop recommendation fertilization model in combination with the field test, determining the soil partition of interest based on the soil nutrient electronic map, calculating the recommended fertilization amount in combination with the crop recommendation fertilization model, and sending it to the user intelligent terminal. The present invention solves the technical problem of low fertilization accuracy due to the difficulty in implementing the crop soil testing and fertilization technical solution in the prior art, and achieves the technical effect of effectively guiding farmers to carry out scientific fertilization based on the big data platform and improving the accuracy of crop fertilization.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for precise crop fertilization based on a big data platform. Background Art

[0002] At present, agricultural fertilization mainly relies on farmers' experience, which not only causes a decrease in crop yield and quality, but also leads to environmental pollution and waste of resources. In order to solve these problems, experts, scholars and agricultural departments have proposed soil testing and formula fertilization, which determines the fertilization formula based on soil nutrient status and crop fertilizer requirements, and to a certain extent alleviates the problem of farmers fertilizing based on experience. However, in the actual operation of soil testing and formula fertilization technology, it is difficult for farmers to accurately grasp the soil nutrient status and fertilization technical solutions of specific fields in a timely manner, resulting in good technology being difficult to implement accurately. Summary of the invention

[0003] The present application provides a method and system for precision fertilization of crops based on a big data platform, which is used to solve the technical problem in the prior art that the technical solution of crop soil testing and fertilization is difficult to implement, resulting in low fertilization accuracy.

[0004] In a first aspect of the present application, a method for precise crop fertilization based on a big data platform is provided, the method comprising: collecting farmland soil samples, determining soil nutrients of the farmland soil samples, and obtaining sample soil nutrient information; according to the distribution characteristics of the farmland soil samples, converting sample point data into surface data using a spatial interpolation method, and constructing soil nutrient farmland coverage information of the sampling area; based on the sampling area positioning information and the sampling area soil nutrient farmland coverage information, establishing a soil nutrient electronic map and sending it to a user smart terminal; performing nutrient factor analysis according to crop variety yield information, determining key nutrient factors, clustering soil nutrients in the sampling area based on the key nutrient factors, and partitioning the sampling area soil according to the clustering results, wherein the key nutrient factor levels in each partition are within the same range; obtaining a field test data set, performing a preset multi-dimensional relationship analysis according to the field test data set, and constructing a crop recommendation fertilization model; determining a soil partition of interest based on the soil nutrient electronic map, and calculating a recommended fertilization amount through a crop recommendation fertilization model according to the soil nutrient information and crop variety yield information of the soil partition of interest, and sending the calculated fertilization amount to the user smart terminal.

[0005] The second aspect of the present application provides a crop precision fertilization system based on a big data platform, the system comprising: a sample soil nutrient information acquisition module, the sample soil nutrient information acquisition module is used to collect farmland soil samples, perform soil nutrient determination on the farmland soil samples, and obtain sample soil nutrient information; a farmland full coverage information construction module, the farmland full coverage information construction module is used to convert sample point data into surface data according to the distribution characteristics of the farmland soil samples using a spatial interpolation method, and construct soil nutrient farmland full coverage information of the sampling area; a soil nutrient electronic map establishment module, the soil nutrient electronic map establishment module is used to establish a soil nutrient electronic map based on the sampling area positioning information and the soil nutrient farmland full coverage information of the sampling area, and send it to the user's smart terminal; a sampling area soil zoning module, the The sampling area soil partitioning module is used to perform nutrient factor analysis based on crop variety yield information, determine key nutrient factors, cluster the soil nutrients in the sampling area based on the key nutrient factors, and partition the soil in the sampling area according to the clustering results, wherein the key nutrient factor levels in each partition are within the same range; the crop recommendation fertilization model construction module, the crop recommendation fertilization model construction module is used to obtain a field test data set, perform a preset multi-dimensional relationship analysis based on the field test data set, and construct a crop recommendation fertilization model; the fertilization recommendation amount calculation module, the fertilization recommendation amount calculation module is used to determine the soil partition of interest based on the soil nutrient electronic map, and calculate the fertilization recommendation amount through the crop recommendation fertilization model according to the soil nutrient information and crop variety yield information of the soil partition of interest, and send it to the user's smart terminal.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] The present application provides a method for precise crop fertilization based on a big data platform, which relates to the field of data processing technology. The method obtains sample soil nutrient information, converts sample point data into surface data using a spatial interpolation method according to the distribution characteristics of the soil samples, constructs soil nutrient farmland coverage information of the sampling area, combines the sampling area positioning information, establishes a soil nutrient electronic map and sends it to a user's smart terminal, partitions the soil in the sampling area, obtains a field test data set, constructs a crop recommendation fertilization model, determines the soil partition of interest based on the soil nutrient electronic map, calculates the recommended fertilization amount through the crop recommendation fertilization model, and sends it to the user's smart terminal. The method solves the technical problem of low fertilization accuracy due to the difficulty in implementing the technical solution of crop soil testing and fertilization in the prior art, and achieves the technical effect of effectively guiding farmers to carry out scientific fertilization based on the big data platform and improving the accuracy of crop fertilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0009] Figure 1 A schematic diagram of a process flow of a crop precision fertilization method based on a big data platform provided in an embodiment of the present application;

[0010] Figure 2 A schematic diagram of a process for constructing full coverage information of soil nutrients in a sampling area in a crop precision fertilization method based on a big data platform provided in an embodiment of the present application;

[0011] Figure 3 A schematic diagram of a process for zoning the soil in a sampling area in a method for precise crop fertilization based on a big data platform provided in an embodiment of the present application;

[0012] Figure 4 A schematic diagram of the structure of a crop precision fertilization system based on a big data platform provided in an embodiment of the present application.

[0013] Explanation of the reference numerals: sample soil nutrient information acquisition module 11, farmland full coverage information construction module 12, soil nutrient electronic map establishment module 13, sampling area soil zoning module 14, crop recommended fertilization model construction module 15, recommended fertilization amount calculation module 16. DETAILED DESCRIPTION

[0014] The present application provides a method for precision fertilization of crops based on a big data platform, which is used to solve the technical problem in the prior art that the technical solution of crop soil testing and fertilization is difficult to implement, resulting in low fertilization accuracy.

[0015] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0016] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0017] Embodiment 1

[0018] like Figure 1 As shown, the present application provides a method for precise fertilization of crops based on a big data platform, the method comprising:

[0019] S100: collecting farmland soil samples, measuring soil nutrients of the farmland soil samples, and obtaining sample soil nutrient information;

[0020] Specifically, multiple soil samples are collected from the target farmland area, and professional experimenters conduct soil nutrient measurements on the farmland soil samples in turn to obtain nutrient information of the sample soil, such as the content of nutrients such as nitrogen, phosphorus, and potassium in the soil, their existence forms, etc., which serve as basic data for subsequent construction of full coverage information of soil nutrient farmland in the sampling area.

[0021] Furthermore, step S100 in the embodiment of the present application further includes:

[0022] S110: Obtain a target sampling area, collect soil distribution and environmental resource distribution in the target sampling area, and obtain a target sampling area database;

[0023] S120: performing difference calculation and average calculation on the target sampling area database to obtain soil distribution difference, average and environmental resource distribution difference, average;

[0024] S130: Determine a first soil sampling point according to the soil distribution difference and average amount and a preset collection quantity;

[0025] S140: Determine a second soil sampling point according to the environmental resource distribution difference and average amount and a preset collection quantity;

[0026] S150: Eliminate duplicate points of the first soil sampling point and the second soil sampling point, and determine a sampling target area for sample collection.

[0027] Specifically, the geographical location of the farmland that needs to be sampled is obtained, that is, the target sampling area, and the soil distribution and environmental resource distribution of the target sampling area are investigated to determine the soil type of the current farmland area and the distribution of surrounding environmental resources. For example, the soil types include brick red soil, red soil, red-yellow soil, yellow-brown soil, brown soil, dark brown soil, cold brown soil, and brown soil. The surrounding environmental resources include water resources, mineral resources, and biological resources. The collected soil distribution and environmental resource distribution are used as construction data to generate a target sampling area database. The soil distribution and environmental resource distribution data in the target sampling area database are respectively calculated for difference and average, because each sub-area in the target sampling area There are differences in soil types. By calculating the difference ratio of soil between every two sub-areas, the soil distribution difference of each sub-area in the target collection area is obtained. By weighted averaging the soil components of the target collection area according to the area ratio, the average amount of soil distribution is obtained. Similarly, the difference and average amount of environmental resource distribution in the target area are calculated. According to the soil distribution difference and average amount, the first soil sampling point is determined according to the preset collection number. The first soil sampling point includes multiple soil sampling points, which are preferentially arranged in different sub-areas with large distribution differences to ensure the comprehensiveness of sample data. The preset collection number is set according to the area size of the target collection area and can be adaptively adjusted according to actual conditions. According to the environmental resource distribution difference and average amount, the second soil sampling point is determined in the target collection area according to the preset collection number. The second soil sampling point is distributed in multiple areas with different environmental resource distributions, which can reflect the distribution of environmental resources in the target area. The first soil sampling point and the second soil sampling point are compared and screened, and repeated sampling points are eliminated. Then the remaining sampling points are merged as the final sampling point. Samples are collected from the sampling target area where the sampling points are located, which can be used to determine the soil nutrients in the target area.

[0028] S200: According to the distribution characteristics of the farmland soil samples, the sample point data is converted into surface data using a spatial interpolation method to construct the farmland full coverage information of soil nutrients in the sampling area;

[0029] Specifically, according to the soil distribution difference and average amount of the farmland soil samples and the environmental resource distribution difference and average amount, the spatial interpolation method is used to supplement the data of the unsampled area and convert the sample point data into surface data. The spatial interpolation method is often used to convert the measurement data of discrete points into a continuous data surface for comparison with the distribution pattern of other spatial phenomena. It includes two algorithms: spatial interpolation and extrapolation. The spatial interpolation algorithm is to infer the data of other unknown points in the same area through the data of known points, and the spatial extrapolation algorithm is to infer the data of other areas through the data of known areas. The complete sample data constitutes the full coverage information of soil nutrients in the sampling area, which can be used as the basic data for the subsequent establishment of soil nutrient electronic maps and sent to the user's smart terminal.

[0030] Further, such as Figure 2 As shown, step S200 of the embodiment of the present application also includes:

[0031] S210: Obtaining distribution characteristics of the farmland soil sample according to the soil distribution difference and average amount and the environmental resource distribution difference and average amount;

[0032] S220: performing data correlation analysis according to the sample point data and distribution characteristics, supplementing the sampling span area with data based on the data correlation, and obtaining regional surface data;

[0033] S230: Mapping the entire target sampling area based on the regional surface data to construct soil nutrient farmland coverage information in the sampling area.

[0034] Specifically, the distribution characteristics of the farmland soil samples, including the dispersion degree of soil samples, the composition difference degree between soil samples, etc., are analyzed through the soil composition data of each sample point and the overall distribution characteristic data of the sample, and the data correlation analysis is performed. The correlation analysis refers to the analysis of two or more variable elements with correlation, so as to measure the degree of correlation between the two variable factors. The sampling span area is supplemented with data based on the correlation between the sample point data and the distribution characteristic data. The sampling span area refers to the farmland area where no sampling is performed, and the actual soil data is between the two sampling points. The data between the sampling points is supplemented to obtain the regional surface data of the entire target area, and the regional surface data is associated and mapped with the full range of the target sampling area to obtain the full coverage information of the soil nutrients in the sampling area. The full coverage information of the soil nutrients in the sampling area can reflect the soil data in the full range of the target sampling area, and can be used as the basic data for the subsequent establishment of the soil nutrient electronic map and sent to the user's smart terminal.

[0035] S300: Based on the sampling area positioning information and the soil nutrient farmland coverage information of the sampling area, a soil nutrient electronic map is established and sent to the user's smart terminal;

[0036] Specifically, the location information of the target sampling area and the electronic map of the target sampling area are obtained through map software, and the soil nutrient farmland full coverage information of the sampling area is mapped to the electronic map to generate the soil nutrient electronic map. The soil nutrient electronic map can reflect the soil nutrient conditions of each area of ​​the sampling area. The soil nutrient electronic map is sent to the user's smart terminal, which can be a mobile phone, electric power or other networked electronic device. Using digital technology, the farmland nutrient status is pushed to farmers through the mobile phone. Users can use the mobile phone positioning system to display the soil nutrient status of the current field, and can also query the soil nutrient status of any field through a mobile phone or computer.

[0037] S400: performing nutrient factor analysis according to crop variety yield information to determine key nutrient factors, clustering soil nutrients in the sampling area based on the key nutrient factors, and partitioning the soil in the sampling area according to the clustering results, wherein the key nutrient factor levels in each partition are within the same range;

[0038] Specifically, according to the relationship between the yield of each crop and the required nutrients, the key nutrient factors that can determine the yield of each crop are determined. For example, the key nutrient factors of vegetables mainly composed of stems and leaves are nitrogen, and the key nutrient factors of crops such as seeds and tubers are nitrogen, phosphorus, and potassium. The soil nutrients in the sampling area are clustered based on the key nutrient factors, and the areas with the same level of the key nutrient factors are classified into one category. The soil in the sampling area is partitioned according to the distribution of the key nutrient factors, wherein the levels of the key nutrient factors in each partition are in the same range. The soil in the sampling area after partitioning can reflect the distribution of the key nutrient factors in the sampling area.

[0039] Further, such as Figure 3 As shown, step S400 of the embodiment of the present application also includes:

[0040] S410: Determine a first key nutrient factor, a second key nutrient factor, and an Nth key nutrient factor according to the key nutrient factor, where N is a positive integer greater than 2;

[0041] S420: Based on the first key nutrient factor, the second key nutrient factor, and the Nth key nutrient factor, soil nutrient distribution in the sample area is performed to determine the highest value, the middle value, the lowest value, the second highest value between the highest value and the middle value, and the second lowest value between the lowest value and the middle value;

[0042] S430: clustering the soil nutrients in the sampling area using the highest value, the second highest value, the middle value, the second lowest value, and the lowest value as cluster centers, respectively, to obtain a first key nutrient factor clustering layer, a second key nutrient factor clustering layer, and an Nth key nutrient factor clustering layer;

[0043] S440: Overlay the first key nutrient factor clustering layer, the second key nutrient factor clustering layer, and the Nth key nutrient factor clustering layer to obtain the soil zoning result of the sampling area.

[0044] Specifically, the key nutrient factors of all crops are classified into the first key nutrient factor, the second key nutrient factor, and the Nth key nutrient factor according to different nutrient categories, where N is a positive integer greater than 2, indicating that there are at least two key nutrient factors. The soil nutrient distribution amounts of the first key nutrient factor, the second key nutrient factor, and the Nth key nutrient factor in the sample area are extracted respectively, and the highest value, the middle value, the lowest value, the second highest value between the highest value and the middle value, and the second lowest value between the lowest value and the middle value of the distribution amount of each key nutrient factor are determined respectively. Then, the highest value, second highest value, middle value, second lowest value and lowest value of the distribution amount of each key nutrient factor are taken as cluster centers, and the soil nutrients in the sampling area are clustered. The values ​​similar to the highest value, second highest value, middle value, second lowest value and lowest value of the distribution amount of each key nutrient factor are classified into one category and marked, and the first key nutrient factor clustering layer, the second key nutrient factor clustering layer and the Nth key nutrient factor clustering layer are generated in sequence. The first key nutrient factor clustering layer, the second key nutrient factor clustering layer and the Nth key nutrient factor clustering layer are superimposed to obtain the clustering area range of each type of key nutrient factor in the sampling area, and the clustering area range of each type of key nutrient factor is used to perform soil zoning to obtain the soil zoning results of the sampling area, which can reflect the distribution of the key nutrient factors in the sampling area.

[0045] S500: obtaining a field test data set, performing a preset multi-dimensional relationship analysis according to the field test data set, and constructing a crop fertilization recommendation model in combination with the field test;

[0046] Specifically, by setting up field tests, we study and clarify parameters such as soil nutrient supply rules, crop fertilizer requirements, and fertilizer nutrient utilization rules, and organize the test data into field test data sets. The field test is an evaluation test of plant seeds, cultivation techniques, and the use of fertilizers and pesticides under actual cultivation environments. The field test data sets are analyzed from multiple preset dimensions, including fertilizer dosage, key nutrient factor content, crop yield, etc. Based on the mapping relationship between fertilizer application amount and crop yield, the crop recommendation fertilization model is constructed, which can be used to subsequently calculate the recommended fertilization amount based on soil nutrients, crop varieties, and other information to guide farmers in fertilization.

[0047] Furthermore, step S500 of the embodiment of the present application further includes:

[0048] S510: Determine the measurement results of key nutrient factors affecting crop quality and yield according to the field test data set;

[0049] S520: Based on the field test data set, obtain a nutrient correction coefficient and a fertilizer utilization rate;

[0050] S530: According to the nutrient correction coefficient, fertilizer utilization rate, and key nutrient factor measurement results, a functional relationship between different target yields and fertilization amounts of key nutrient factors is fitted to construct the crop recommendation fertilization model.

[0051] Specifically, the content measurement data of key nutrient factors that affect crop quality and yield are extracted from the field test data set, and the nutrient correction coefficient is set based on the field test data set. Due to the accuracy of the detection instrument and other reasons, the nutrient detection results may have deviations. The nutrient correction coefficient is used to correct the deviation of the nutrient detection data, and the utilization rate of various fertilizers is calculated according to the comparison of crop yields before and after fertilization. According to the nutrient correction coefficient, fertilizer utilization rate, key nutrient factor measurement results and other data, the soil nutrient supply law, crop fertilizer requirement law, fertilizer nutrient utilization law, etc. are derived. According to these laws, the functional relationship between the yield of different target crops and the fertilization amount of key nutrient factors is derived, and the crop recommendation fertilization model is constructed according to the functional relationship.

[0052] Furthermore, step S520 of the embodiment of the present application further includes:

[0053] S531: fitting the power function relationship between fertilizer application amount and soil fertility and the linear correlation of crop quality according to the key nutrient factor measurement results and the field test data set;

[0054] S532: Based on the power function relationship between the fertilizer amount and soil fertility and the linear correlation of crop quality, the fitting fertilization formula is: z=ax+by c , where z is the amount of fertilizer applied, x is the proportion of top-quality crops, and y is the soil fertility level;

[0055] S533: constructing a data correction module using the nutrient correction coefficient, constructing a fertilization calculation module using the fertilization formula, and constructing a fertilization result correction module using the fertilizer utilization rate;

[0056] S534: Connect the data correction module, the fertilization calculation module, and the fertilization result correction module to construct the crop recommendation fertilization model.

[0057] Specifically, the power function relationship between the amount of fertilizer and soil fertility, as well as the linear correlation between the amount of fertilizer and crop quality, are derived by using the measurement results of the key nutrient factor content before and after fertilization, combined with the data on crop growth and quality, fertilizer dosage, etc. in the field test data set before and after fertilization. The fertilization formula is derived as follows: z = ax + by c , where z is the amount of fertilizer, x is the proportion of high-quality crops, and y is the soil fertility level. Since there may be deviations in the nutrient detection results, the nutrient correction coefficient is used to construct a data correction module to correct the nutrient detection results, and the fertilization calculation module is constructed using the fertilization formula. The fertilization calculation module is used to calculate the amount of fertilizer required for high-quality crops. Finally, according to the fertilizer utilization rate, a fertilization result correction module is constructed to eliminate the error of unusable fertilization amount and obtain the correct fertilization amount. The data correction module, the fertilization calculation module, and the fertilization result correction module are connected and integrated to construct the crop recommendation fertilization model. The crop recommendation fertilization model can calculate the recommended amount of fertilizer based on soil nutrients, crop varieties and other information to guide farmers in fertilization.

[0058] For example, the model is applied to tobacco planting, collecting data such as field tests and soil tests in a tobacco planting area and county over the years, and using the fitting fertilization formula: z = ax + by c Calculate the amount of fertilizer to be applied. First, obtain the nitrogen, phosphorus, and potassium soil nutrient correction coefficient formulas:

[0059]

[0060]

[0061]

[0062] The soil nutrient determination value is corrected using the nutrient correction formula, and the calculation process is as follows:

[0063]

[0064]

[0065]

[0066] In the formula, S N , S P , S K are the correction values ​​of alkaline hydrolyzable nitrogen, available phosphorus and available potassium (unit: kg·mu-1), S' N , S' P , S' Kare the soil measured values ​​of alkaline nitrogen, available phosphorus and quick-acting potassium (unit: mg·kg-1), 2.29 is the conversion factor of P to P2O5, 1.2 is the conversion factor of K to K2O, and 0.15 is the unit conversion factor.

[0067] The corrected soil nutrient measured values ​​and the high-quality tobacco ratio are input into the crop recommended fertilization model. The high-quality tobacco ratio and the soil nutrient measured values ​​are used as variables. The crop recommended fertilization model is used to perform multiple simulations to obtain the recommended fertilization amounts of nitrogen, phosphorus and potassium under different target high-quality tobacco ratios. The calculation process of the recommended fertilization amount is as follows:

[0068] N=0.024Y+16.054S N -0.734

[0069] P2O5=0.032Y+5.142S P -0.065

[0070] K2O=0.072Y+20.421S K -0.191

[0071] Where N, P2O5, K2O are the recommended fertilizer amounts of nitrogen, phosphorus, and potassium, Y is the target high-quality tobacco ratio (unit: %), S N , S P , S K They are the correction values ​​of alkaline nitrogen, available phosphorus and available potassium, respectively. The recommended application amount of nitrogen, phosphorus and potassium can be calculated by using the proportion of local tobacco leaves of previous years and the soil nutrient measurement values ​​of soil alkaline nitrogen, available phosphorus and available potassium. According to the soil fertilization zoning and the recommended fertilization amount, the corresponding fertilization strategy can be formulated to achieve the effect of accurately guiding soil fertilization.

[0072] S600: Determine the soil partition of interest based on the soil nutrient electronic map, calculate the recommended fertilization amount through the crop recommendation fertilization model according to the soil nutrient information and crop variety yield information of the soil partition of interest, and send it to the user's smart terminal.

[0073] Furthermore, step S600 of the embodiment of the present application further includes:

[0074] S610: Determine the concerned soil partition in the soil nutrient electronic map through a user intelligent terminal, wherein the concerned soil partition is any partition in the soil nutrient electronic map;

[0075] S620: Based on the concerned soil partition, obtaining the partition soil nutrient information;

[0076] S630: Set the proportion of high-quality crops;

[0077] S640: Input the partitioned soil nutrient information and the proportion of high-quality crops into the crop recommendation fertilization model, correct the soil nutrient measurement value through the data correction module, input the corrected nutrient measurement value and the preset high-quality crop proportion into the fertilization calculation module for fertilization calculation, obtain the recommended fertilization amount of key nutrient factors, correct the recommended fertilization amount of key nutrient factors based on the utilization rate through the fertilization result correction module, and output the fertilization recommendation result;

[0078] S650: Send the fertilization recommendation result to the user smart terminal.

[0079] Specifically, the user intelligent terminal is used to find the soil partition of current concern in the soil nutrient electronic map. The soil partition of concern is any area on the map selected by the user. It can be the area to view one's own cultivation, or the soil nutrient status of any field through a mobile phone or computer. Based on the soil area where the soil partition of concern is located, the partition soil nutrient information is extracted from the soil nutrient electronic map, including the content of key nutrient factors, soil type, etc., and the required proportion of high-quality crops is set, for example, set to 80%. The partition soil nutrient information and the proportion of high-quality crops are input into the crop recommendation fertilization model. First, the soil nutrient measurement value is corrected by the data correction module, and then the corrected nutrient measurement value and the preset proportion of high-quality crops are input into the fertilization calculation module for fertilization calculation to obtain the recommended fertilization amount calculated by the key nutrient factor. Finally, based on the fertilizer utilization rate, the recommended fertilization amount of the key nutrient factor is corrected by the fertilization result correction module, and the corrected recommended fertilization amount is output as the fertilization recommendation result, and the fertilization recommendation result is sent to the user intelligent terminal through the Internet, so as to effectively guide farmers to carry out scientific fertilization.

[0080] Furthermore, the embodiment of the present application further includes step S700, and step S700 further includes:

[0081] S710: Obtaining a fertilization operation node according to the fertilization recommendation result;

[0082] S720: Collecting meteorological information of the soil partition of interest;

[0083] S730: Perform fertilization operation matching analysis according to the meteorological information and the fertilization operation node, and generate fertilization reminder information.

[0084] Specifically, the time node for fertilization operation is derived according to the fertilization recommendation result. Since the growth of crops and the fertilization effect are closely related to weather conditions, light, temperature, humidity, etc. will affect the absorption of nutrients by crops. Therefore, the meteorological information of the soil partition is obtained through the weather forecast platform, and the corresponding weather information is matched to the fertilization operation node according to the meteorological information. According to the weather conditions of each fertilization operation node, it is judged whether the current fertilization node is reasonable. If the weather has no effect on the current fertilization node, a fertilization reminder message is sent to remind the farmer user to perform fertilization operation in time. If the weather has an impact on the current fertilization node, a weather warning message is generated, and a more reasonable fertilization time is calculated and sent to the user to remind the user to suspend fertilization. In order to avoid the situation where bad weather affects the fertilization effect.

[0085] In summary, the embodiments of the present application have at least the following technical effects:

[0086] This application obtains sample soil nutrient information, converts sample point data into surface data using spatial interpolation method according to the distribution characteristics of farmland soil samples, constructs full coverage information of soil nutrient farmland in the sampling area, combines the sampling area positioning information, establishes a soil nutrient electronic map and sends it to the user's smart terminal, partitions the soil in the sampling area, obtains a field test data set, constructs a crop recommendation fertilization model, determines the soil partitions of concern based on the soil nutrient electronic map, calculates the recommended fertilization amount through the crop recommendation fertilization model, and sends it to the user's smart terminal.

[0087] The technical effect of effectively guiding farmers to apply fertilizers scientifically based on the big data platform and improving the accuracy of crop fertilization has been achieved.

[0088] Embodiment 2

[0089] Based on the same inventive concept as the crop precision fertilization method based on a big data platform in the aforementioned embodiment, Figure 4 As shown, the present application provides a crop precision fertilization system based on a big data platform, and the system and method embodiments in the present application embodiments are based on the same inventive concept. The system includes:

[0090] A sample soil nutrient information acquisition module 11, the sample soil nutrient information acquisition module 11 is used to collect farmland soil samples, perform soil nutrient determination on the farmland soil samples, and obtain sample soil nutrient information;

[0091] The farmland full coverage information construction module 12 is used to convert the sample point data into surface data according to the distribution characteristics of the farmland soil samples by using the spatial interpolation method to construct the farmland full coverage information of soil nutrients in the sampling area;

[0092] A soil nutrient electronic map establishment module 13, which is used to establish a soil nutrient electronic map based on the sampling area positioning information and the soil nutrient farmland full coverage information of the sampling area, and send it to the user's smart terminal;

[0093] A sampling area soil partitioning module 14, wherein the sampling area soil partitioning module 14 performs nutrient factor analysis based on crop variety yield information to determine key nutrient factors, clusters soil nutrients in the sampling area based on the key nutrient factors, and partitions the sampling area soil according to the clustering results, wherein the key nutrient factor levels in each partition are within the same range;

[0094] A crop recommendation fertilization model construction module 15, wherein the crop recommendation fertilization model construction module 15 is used to obtain a field test data set, perform a preset multi-dimensional relationship analysis based on the field test data set, and construct a crop recommendation fertilization model in combination with the field test;

[0095] The recommended fertilization amount calculation module 16 is used to determine the soil partition of interest based on the soil nutrient electronic map, calculate the recommended fertilization amount through the crop recommended fertilization model according to the soil nutrient information and crop variety yield information of the soil partition of interest, and send it to the user's smart terminal.

[0096] Furthermore, the sample soil nutrient information obtaining module 11 is also used to perform the following steps:

[0097] Obtaining a target sampling area, collecting soil distribution and environmental resource distribution in the target sampling area, and obtaining a target sampling area database;

[0098] Performing difference calculation and average calculation on the target sampling area database to obtain soil distribution difference, average and environmental resource distribution difference, average;

[0099] Determine a first soil sampling point according to the soil distribution difference and average amount and a preset collection quantity;

[0100] Determine a second soil sampling point according to the difference and average amount of the environmental resource distribution and the preset collection quantity;

[0101] The first soil sampling point and the second soil sampling point are duplicated and eliminated, and a sampling target area is determined for sample collection.

[0102] Furthermore, the farmland full coverage information construction module 12 is also used to perform the following steps:

[0103] Obtaining the distribution characteristics of the farmland soil sample according to the soil distribution difference and average amount and the environmental resource distribution difference and average amount;

[0104] According to the sample point data and distribution characteristics, data correlation analysis is performed, and data of the sampling span area is supplemented based on the data correlation to obtain regional surface data;

[0105] The target sampling area is fully mapped based on the regional surface data to construct the soil nutrient and farmland coverage information of the sampling area.

[0106] Furthermore, the sampling area soil partitioning module 14 is also used to perform the following steps:

[0107] According to the key nutrient factors, determining a first key nutrient factor, a second key nutrient factor, and an Nth key nutrient factor, where N is a positive integer greater than 2;

[0108] Based on the first key nutrient factor, the second key nutrient factor, and the Nth key nutrient factor, soil nutrient distribution in the sample area is performed to determine the highest value, the middle value, the lowest value, the second highest value between the highest value and the middle value, and the second lowest value between the lowest value and the middle value;

[0109] The highest value, the second highest value, the middle value, the second lowest value, and the lowest value are used as cluster centers to cluster the soil nutrients in the sampling area, and the first key nutrient factor clustering layer, the second key nutrient factor clustering layer, and the Nth key nutrient factor clustering layer are obtained;

[0110] The first key nutrient factor clustering layer, the second key nutrient factor clustering layer, and the Nth key nutrient factor clustering layer are superimposed to obtain the soil zoning result of the sampling area.

[0111] Furthermore, the crop recommended fertilization model construction module 15 is also used to perform the following steps:

[0112] Determine the results of key nutrient factors affecting crop quality and yield based on the field test data set;

[0113] Based on the field test data set, nutrient correction coefficient and fertilizer utilization efficiency are obtained;

[0114] According to the nutrient correction coefficient, fertilizer utilization rate, and key nutrient factor measurement results, the functional relationship between different target yields and the fertilization amount of key nutrient factors is fitted to construct the crop recommendation fertilization model.

[0115] Furthermore, the crop recommended fertilization model construction module 15 is also used to perform the following steps:

[0116] According to the measurement results of the key nutrient factors and the field test data set, fitting the power function relationship between fertilizer application amount and soil fertility and the linear correlation of crop quality;

[0117] Based on the power function relationship between the fertilizer amount and soil fertility and the linear correlation of crop quality, the fitting fertilization formula is: z = ax + by c , where z is the amount of fertilizer applied, x is the proportion of top-quality crops, and y is the soil fertility level;

[0118] Using the nutrient correction coefficient, a data correction module is constructed, using the fertilization formula, a fertilization calculation module is constructed, and using the fertilizer utilization rate, a fertilization result correction module is constructed;

[0119] The data correction module, the fertilization calculation module, and the fertilization result correction module are connected to construct the crop recommendation fertilization model.

[0120] Furthermore, the recommended fertilization amount calculation module 16 is also used to perform the following steps:

[0121] Determining the concerned soil partition in the soil nutrient electronic map through a user intelligent terminal, wherein the concerned soil partition is any partition in the soil nutrient electronic map;

[0122] Based on the soil zoning, obtain the nutrient information of the zoning soil;

[0123] Set the proportion of high-quality crops;

[0124] The partitioned soil nutrient information and the proportion of high-quality crops are input into the crop fertilization recommendation model, the soil nutrient measurement value is corrected by the data correction module, the corrected nutrient measurement value and the preset high-quality crop proportion are input into the fertilization calculation module for fertilization calculation, and the recommended fertilization amount of key nutrient factors is obtained, and the recommended fertilization amount of key nutrient factors is corrected based on the utilization rate by the fertilization result correction module, and the fertilization recommendation result is output;

[0125] The fertilization recommendation result is sent to the user intelligent terminal.

[0126] Furthermore, the system also includes:

[0127] A fertilization operation node acquisition module, wherein the fertilization operation node acquisition module is used to obtain a fertilization operation node according to the fertilization recommendation result;

[0128] A meteorological information collection module, wherein the meteorological information collection module is used to collect meteorological information of soil partitions;

[0129] A fertilization reminder information generation module is used to perform fertilization operation matching analysis according to the meteorological information and fertilization operation nodes to generate fertilization reminder information.

[0130] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0131] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0132] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for precise fertilization of crops based on a big data platform, characterized in that: The method comprises: Collecting farmland soil samples, measuring soil nutrients on the farmland soil samples, and obtaining sample soil nutrient information; According to the distribution characteristics of the farmland soil samples, the sample point data is converted into surface data using the spatial interpolation method to construct the full coverage information of the farmland soil nutrients in the sampling area; Based on the sampling area positioning information and the soil nutrient farmland full coverage information of the sampling area, a soil nutrient electronic map is established and sent to the user's smart terminal; Nutrient factor analysis is performed based on crop variety yield information to determine key nutrient factors, soil nutrients in the sampling area are clustered based on the key nutrient factors, and the soil in the sampling area is partitioned according to the clustering results, wherein the key nutrient factor levels in each partition are within the same range; Obtaining a field test data set, performing a preset multi-dimensional relationship analysis based on the field test data set, and constructing a crop fertilization recommendation model; Determine the soil partition of interest based on the soil nutrient electronic map, calculate the recommended fertilization amount through the crop fertilization recommendation model according to the soil nutrient information and crop variety yield information of the soil partition of interest, and send it to the user smart terminal; The step of obtaining a field test data set, performing a preset multi-dimensional relationship analysis based on the field test data set, and constructing a crop fertilization recommendation model includes: Determine the results of key nutrient factors affecting crop quality and yield based on the field test data set; Based on the field test data set, nutrient correction coefficient and fertilizer utilization efficiency are obtained; According to the nutrient correction coefficient, fertilizer utilization rate, and key nutrient factor measurement results, the functional relationship between different target yields and the fertilization amount of key nutrient factors is fitted to construct the crop fertilization recommendation model, including: According to the measurement results of the key nutrient factors and the field test data set, fitting the power function relationship between fertilizer application amount and soil fertility and the linear correlation of crop quality; Based on the power function relationship between the fertilizer amount and soil fertility and the linear correlation of crop quality, the fitting fertilization formula is: z = ax + by c , where z is the amount of fertilizer applied, x is the proportion of top-quality crops, and y is the soil fertility level; Using the nutrient correction coefficient, a data correction module is constructed, using the fertilization formula, a fertilization calculation module is constructed, and using the fertilizer utilization rate, a fertilization result correction module is constructed; The data correction module, the fertilization calculation module, and the fertilization result correction module are connected to construct the crop fertilization recommendation model; Wherein, the collecting of farmland soil samples includes: Obtaining a target sampling area, collecting soil distribution and environmental resource distribution in the target sampling area, and obtaining a target sampling area database; Performing difference calculation and average calculation on the target sampling area database to obtain soil distribution difference, average and environmental resource distribution difference, average; Determine a first soil sampling point according to the soil distribution difference and average amount and a preset collection quantity; Determine a second soil sampling point according to the difference and average amount of the environmental resource distribution and a preset collection quantity; Eliminate duplicate points of the first soil sampling point and the second soil sampling point, and determine the sampling target area for sample collection; According to the distribution characteristics of the farmland soil samples, the sample point data is converted into surface data using the spatial interpolation method to construct the full coverage information of soil nutrients in the sampling area, including: Obtaining the distribution characteristics of the farmland soil sample according to the soil distribution difference and average amount and the environmental resource distribution difference and average amount; According to the sample point data and distribution characteristics, data correlation analysis is performed, and data of the sampling span area is supplemented based on the data correlation to obtain regional surface data; Mapping the entire target sampling area based on the regional surface data to construct soil nutrient farmland coverage information in the sampling area; Clustering the soil nutrients in the sampling area based on the key nutrient factors and partitioning the soil in the sampling area according to the clustering results includes: According to the key nutrient factors, determining a first key nutrient factor, a second key nutrient factor, and an Nth key nutrient factor, where N is a positive integer greater than 2; Based on the first key nutrient factor, the second key nutrient factor, and the Nth key nutrient factor, soil nutrient distribution in the sample area is performed to determine the highest value, the middle value, the lowest value, the second highest value between the highest value and the middle value, and the second lowest value between the lowest value and the middle value; The highest value, the second highest value, the middle value, the second lowest value, and the lowest value are used as cluster centers to cluster the soil nutrients in the sampling area, and the first key nutrient factor clustering layer, the second key nutrient factor clustering layer, and the Nth key nutrient factor clustering layer are obtained; The first key nutrient factor clustering layer, the second key nutrient factor clustering layer, and the Nth key nutrient factor clustering layer are superimposed to obtain the soil zoning result of the sampling area; The method further comprises: Determining the concerned soil partition in the soil nutrient electronic map through a user intelligent terminal, wherein the concerned soil partition is any partition in the soil nutrient electronic map; Based on the soil zoning, the nutrient information of the zoning soil is obtained; Set the proportion of high-quality crops; The partitioned soil nutrient information and the proportion of high-quality crops are input into the crop fertilization recommendation model, the soil nutrient measurement value is corrected by the data correction module, the corrected nutrient measurement value and the preset high-quality crop proportion are input into the fertilization calculation module for fertilization calculation, and the recommended fertilization amount of the key nutrient factor is obtained, and the recommended fertilization amount of the key nutrient factor is corrected based on the utilization rate by the fertilization result correction module, and the fertilization recommendation result is output; The fertilization recommendation result is sent to the user intelligent terminal.

2. The method according to claim 1, characterized in that Also includes: According to the fertilization recommendation result, obtaining a fertilization operation node; Collect meteorological information focusing on soil zoning; A fertilization operation matching analysis is performed according to the meteorological information and the fertilization operation nodes to generate fertilization reminder information.

3. A crop precision fertilization system based on a big data platform, characterized in that: The system is used to execute the method according to any one of claims 1 to 2, and the system comprises: A sample soil nutrient information acquisition module, which is used to collect farmland soil samples, perform soil nutrient determination on the farmland soil samples, and obtain sample soil nutrient information; A farmland full coverage information construction module, which is used to convert sample point data into surface data using a spatial interpolation method according to the distribution characteristics of the farmland soil samples, and to construct farmland full coverage information of soil nutrients in the sampling area; A soil nutrient electronic map establishment module, which is used to establish a soil nutrient electronic map based on the sampling area positioning information and the soil nutrient farmland full coverage information of the sampling area, and send it to the user's smart terminal; A sampling area soil partitioning module, wherein the sampling area soil partitioning module performs nutrient factor analysis according to crop variety yield information, determines key nutrient factors, clusters soil nutrients in the sampling area based on the key nutrient factors, and partitions the sampling area soil according to the clustering results, wherein the key nutrient factor levels in each partition are within the same range; A crop fertilization recommendation model construction module, the crop fertilization recommendation model construction module is used to obtain a field test data set, perform a preset multi-dimensional relationship analysis based on the field test data set, and construct a crop fertilization recommendation model; A fertilization recommendation amount calculation module, the fertilization recommendation amount calculation module is used to determine the soil partition of interest based on the soil nutrient electronic map, calculate the fertilization recommendation amount through the crop fertilization recommendation model according to the soil nutrient information and crop variety yield information of the soil partition of interest, and send it to the user smart terminal; The crop fertilization recommendation model building module is also used to perform the following steps: Determine the results of key nutrient factors affecting crop quality and yield based on the field test data set; Based on the field test data set, nutrient correction coefficient and fertilizer utilization efficiency are obtained; According to the nutrient correction coefficient, fertilizer utilization rate, and key nutrient factor measurement results, the functional relationship between different target yields and the fertilization amount of key nutrient factors is fitted to construct the crop fertilization recommendation model; According to the measurement results of the key nutrient factors and the field test data set, fitting the power function relationship between fertilizer application amount and soil fertility and the linear correlation of crop quality; Based on the power function relationship between the fertilizer amount and soil fertility and the linear correlation of crop quality, the fitting fertilization formula is: z = ax + by c , where z is the amount of fertilizer applied, x is the proportion of top-quality crops, and y is the soil fertility level; Using the nutrient correction coefficient, a data correction module is constructed, using the fertilization formula, a fertilization calculation module is constructed, and using the fertilizer utilization rate, a fertilization result correction module is constructed; The data correction module, the fertilization calculation module, and the fertilization result correction module are connected to construct the crop fertilization recommendation model; The sample soil nutrient information acquisition module is also used to perform the following steps: Obtaining a target sampling area, collecting soil distribution and environmental resource distribution in the target sampling area, and obtaining a target sampling area database; Performing difference calculation and average calculation on the target sampling area database to obtain soil distribution difference, average and environmental resource distribution difference, average; Determine a first soil sampling point according to the soil distribution difference and average amount and a preset collection quantity; Determine a second soil sampling point according to the difference and average amount of the environmental resource distribution and a preset collection quantity; Eliminate duplicate points of the first soil sampling point and the second soil sampling point, and determine the sampling target area for sample collection; The farmland coverage information building module is also used to perform the following steps: Obtaining the distribution characteristics of the farmland soil sample according to the soil distribution difference and average amount and the environmental resource distribution difference and average amount; According to the sample point data and distribution characteristics, data correlation analysis is performed, and data of the sampling span area is supplemented based on the data correlation to obtain regional surface data; The target sampling area is fully mapped based on the regional surface data to construct the soil nutrient and farmland coverage information of the sampling area.