A soil improvement evaluation system for agricultural planting based on big data

Abstract

The present invention discloses a soil improvement evaluation system for agricultural planting based on big data, which belongs to the field of soil improvement evaluation system, including a soil primary collection module, a soil primary detection and analysis module, an improvement method determination module, a regional division and improvement module, a soil secondary collection module, a comparison and analysis module, an evaluation result generation module, a sampling effectiveness evaluation module, a big data platform and a data import module; the soil primary collection module is used to collect samples before the land is improved; the soil primary detection and analysis module is used to detect and analyze the soil samples collected for the first time to determine the soil index. The present invention can first screen out successful cases with similar indicators to the soil to be improved, and then use the improvement schemes of these successful cases to improve the soil to be improved by region, and finally evaluate the most suitable area for planting and its corresponding improvement scheme, so as to select the best soil improvement scheme.

Description

Technical Field

[0001] The present invention relates to a soil improvement evaluation system, in particular to a soil improvement evaluation system for agricultural planting based on big data. Background Art

[0002] Soil improvement is to eliminate or prevent adverse factors that affect crop growth and cause soil degradation, improve soil properties, increase soil fertility, and create a good soil environment for crops. Soil improvement can increase the content of microorganisms and organic matter in the soil, improve soil fertility, and increase production and income. In recent years, in order to increase production and save time and effort, people have used chemical fertilizers when planting crops. Chemical fertilizers have significant effects in a short period of time, but they destroy the physical and chemical properties of the soil and are not conducive to the long-term development of agriculture. It is necessary to increase the application of organic fertilizers for soil improvement to ensure the sustainable development of agriculture.

[0003] There are many ways to improve soil, the most common ones are microbial method, plant method, fertilization method, additive method, and soil removal and importation method. However, different soil indicators require different improvement plans. If the improvement plan adopted is inappropriate, it will easily lead to a significant decrease in the soil improvement effect, seriously affecting the later agricultural planting. Therefore, how to select a suitable soil improvement plan and evaluate the effects of each improvement plan after soil improvement, and select the best soil improvement plan is a problem that needs to be solved urgently.

[0004] Therefore, those skilled in the art provide a soil improvement evaluation system for agricultural planting based on big data to solve the problems raised in the above background technology. Summary of the invention

[0005] The purpose of the present invention is to provide a soil improvement evaluation system for agricultural planting based on big data, which can first screen out successful cases with similar indicators to the soil to be improved, and then use the improvement plans of these successful cases to improve the soil to be improved by region, and finally evaluate the most suitable area for planting and its corresponding improvement plan, so as to select the best soil improvement plan to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A soil improvement evaluation system for agricultural planting based on big data, comprising a soil primary collection module, a soil primary detection and analysis module, an improvement method determination module, a regional division and improvement module, a soil secondary collection module, a comparison and analysis module, an evaluation result generation module, a sampling effectiveness evaluation module, a big data platform and a data import module; the soil primary collection module is used to collect samples of the land before it is improved; the soil primary detection and analysis module is used to detect and analyze the soil samples collected for the first time to determine soil indicators, wherein the soil indicators include pH value, nutrient element content, organic matter content, water content, soil structure, microbial activity, soil bulk density and soil saturation; the improvement method determination module is used to screen out all the schemes adopted for the corresponding successful soil improvement from the big data platform according to the determined soil indicators, and each scheme is marked as Ai, i=1···n, and n is a positive integer; the regional division module is used to collect samples of the land before it is improved; the soil primary detection and analysis module is used to detect and analyze the soil samples collected for the first time to determine the soil indicators, wherein the soil indicators include pH value, nutrient element content, organic matter content, water content, soil structure, microbial activity, soil bulk density and soil saturation; the improvement method determination module is used to screen out all the schemes adopted for the corresponding successful soil improvement from the big data platform according to the determined soil indicators, and each scheme is marked as Ai, i=1···n, and n is a positive integer; The improvement module is used to divide the land to be improved into n areas, and implement an improvement plan for each area; the soil secondary collection module is used to determine the number of sampling points in each area, and then collect samples of the improved land in each area according to the number of sampling points and mix them; the soil secondary collection module is used to detect and analyze the secondary collected soil samples to determine the soil indicators; the comparison and analysis module is used to receive the soil indicators required by the crops to be planted from the data import module, and compare and analyze the soil indicators required by the crops to be planted with the improved soil indicators of each area, and evaluate and determine the most suitable area for planting; the evaluation result generation module is used to generate the best soil improvement plan, that is, the improvement plan adopted by the area that is determined to be most suitable for planting is used as the best soil improvement plan; the sampling effectiveness evaluation module is used to analyze and evaluate the sampling data in the secondary soil collection, and arrange resampling if the evaluation is unqualified.

[0008] As a further solution of the present invention: the specific process of the soil secondary collection module determining the number of sampling points in each area is as follows:

[0009] Each region corresponding to Ai is marked as Bi, i = 1···n;

[0010] Mark the area of ​​Bi as Ci, and then mark the preset area as C preset;

[0011] Compare Ci with the preset C. If Ci=preset C, set up X sampling points in the Bi area corresponding to Ci, otherwise proceed to the next step;

[0012] If Ci<Cpreset, calculate the difference between Cpreset and Ci, and subtract one sampling point for every 100 square meters of difference, that is, set up X-(Cpreset-Ci) / 100 sampling points;

[0013] If Ci>C preset, then calculate the difference between Ci and C preset, and add one sampling point for every hundred square meters of difference, that is, set up X+(Ci-C preset) / 100 sampling points.

[0014] As a further solution of the present invention: the sampling validity assessment module includes:

[0015] The drone unit is used to collect sampling data from sampling personnel in each area. The sampling data includes sampling point images and sampling environment information, where the sampling environment information includes temperature, air pressure, wind speed, and humidity;

[0016] A data receiving unit, used for receiving sampling point images and sampling environment information;

[0017] Data analysis unit, used to build analysis models and output analysis results;

[0018] The result output unit is used to output whether resampling is required according to the analysis result. If the analysis result is qualified, resampling is not required. If the analysis result is unqualified, resampling is required.

[0019] As a further solution of the present invention: the specific analysis process of the analysis model is:

[0020] Construct a sampling point location analysis sub-model and output the analysis results. The specific analysis process of the sampling point location analysis sub-model is as follows:

[0021] (1) According to the collected sampling point image, the sampling point position of each area Bi is marked as Pj, j = 1...m, and m is a positive integer;

[0022] (2) Connect each Pj with the other Pj, and use the outermost connecting line as the boundary line of the sampling area;

[0023] (3) Calculate the area of ​​the sampling area based on the determined sampling area boundary line and mark it as C sampling;

[0024] (4) Compare the C sample with the corresponding Ci. If the difference between Ci and C is greater than the preset value, the sampling point is output as unqualified, otherwise proceed to the next step;

[0025] (5) The distance between Pj and the other Pj is marked as Qj, j = 1···m-1;

[0026] (6) Compare Qj with the preset value. If Qj is greater than the preset value, the sampling point is unqualified; if Qj is less than or equal to the preset value, the sampling point is qualified.

[0027] Construct a sampling environment information analysis sub-model and output the analysis results. The specific analysis process of the sampling environment information analysis sub-model is as follows:

[0028] 1) Match the collected temperature value with the preset temperature range. If the collected temperature value does not fall within the preset temperature range, the sampling environment is output as unqualified. If the collected temperature value falls within the preset temperature range, proceed to the next step.

[0029] 2) Match the collected air pressure value with the preset air pressure range. If the collected air pressure value does not fall within the preset air pressure range, the sampling environment is output as unqualified. If the collected air pressure value falls within the preset air pressure range, proceed to the next step;

[0030] 3) Match the collected wind speed value with the preset wind speed range. If the collected wind speed value does not fall within the preset wind speed range, the sampling environment is output as unqualified. If the collected wind speed value falls within the preset wind speed range, proceed to the next step.

[0031] 4) Match the collected humidity value with the preset humidity range. If the collected humidity value does not fall within the preset humidity range, the sampling environment is output as unqualified. If the collected humidity value falls within the preset humidity range, the sampling environment is output as qualified.

[0032] If the analysis results of the sampling point location analysis sub-model and the sampling environment information analysis sub-model are both qualified, the analysis result of the output analysis model is qualified; otherwise, the analysis result of the output analysis model is unqualified.

[0033] As a further solution of the present invention: the specific process of the improvement method determination module screening out all the solutions adopted for successful soil improvement from the big data platform according to the determined soil indicators is as follows:

[0034] The soil index determined by the initial soil test analysis is marked as R real time;

[0035] The soil index of each soil improvement case before improvement in the big data platform is marked as Ri, i = 1···k, k is a positive integer;

[0036] Compare R with Ri in real time for similarity, and arrange the similarities from high to low;

[0037] Filter out the top n soil improvement cases with the highest similarity;

[0038] Output the improvement plan adopted by the screened soil improvement cases.

[0039] As a further solution of the present invention: in the process of the similarity comparison between the real-time R and Ri, a separate comparison is adopted, that is, the real-time pH value of R is compared with the pH value of Ri separately to obtain a similarity value Z1; the real-time nutrient element content of R is compared with the nutrient element content of Ri separately to obtain a similarity value Z2; the real-time organic matter content of R is compared with the organic matter content of Ri separately to obtain a similarity value Z3; the real-time moisture content of R is compared with the moisture content of Ri separately to obtain a similarity value Z4; the real-time soil structure of R is compared with The soil structure of Ri is compared separately to obtain a similarity value Z5; the real-time microbial activity of R is compared separately with the microbial activity of Ri to obtain a similarity value Z6; the real-time soil bulk density of R is compared separately with the soil bulk density of Ri to obtain a similarity value Z7; the real-time soil saturation of R is compared separately with the soil saturation of Ri to obtain a similarity value Z8; then the average similarity Z average = (Z1+Z2+Z3+Z4+Z5+Z6+Z7+Z8) / 8 is calculated, and Z average is output as the similarity between R real-time and Ri.

[0040] As a further solution of the present invention: the specific process of the comparison and analysis module to evaluate and determine the most suitable area for planting is:

[0041] The soil indicators required by the crops to be planted are marked, that is, the pH value in the soil indicators required by the crops to be planted is marked as V1, the nutrient element content in the soil indicators required by the crops to be planted is marked as V2, the organic matter content in the soil indicators required by the crops to be planted is marked as V3, the water content in the soil indicators required by the crops to be planted is marked as V4, the soil structure in the soil indicators required by the crops to be planted is marked as V5, the microbial activity in the soil indicators required by the crops to be planted is marked as V6, the soil bulk density in the soil indicators required by the crops to be planted is marked as V7, and the soil saturation in the soil indicators required by the crops to be planted is marked as V8;

[0042] The improved soil indicators of each region are marked, that is, the pH value of the improved soil indicators of each region is marked as v1, the nutrient element content of the improved soil indicators of each region is marked as v2, the organic matter content of the improved soil indicators of each region is marked as v3, the moisture content of the improved soil indicators of each region is marked as v4, the soil structure of the improved soil indicators of each region is marked as v5, the microbial activity of the improved soil indicators of each region is marked as v6, the soil bulk density of the improved soil indicators of each region is marked as v7, and the soil saturation of the improved soil indicators of each region is marked as v8;

[0043] Compare V1-V8 with v1-v8 respectively to obtain similarities z1, z2, z3, z4, z5, z6, z7, z8;

[0044] Calculate the average similarity z average = (z1+z2+z3+z4+z5+z6+z7+z8) / 8, and determine the area with the highest z average as the most suitable area for planting.

[0045] As a further solution of the present invention: the soil index required by the crops to be planted imported by the data import module can be set according to the needs of the staff.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] 1. This application can first screen out successful cases with similar soil indicators to those to be improved, and then use the improvement plans of these successful cases to improve the soil to be improved by region, and finally evaluate the most suitable areas for planting and their corresponding improvement plans, so as to select the best soil improvement plan.

[0048] 2. The present application can allocate different numbers of sampling points according to the size of the previously divided sampling areas, thereby avoiding too many sampling times in sampling areas with too small an area, which reduces the sampling speed, and avoiding too few sampling times in sampling areas with too large an area, which affects the sampling accuracy, thereby improving the accuracy and comprehensiveness of the sampling data.

[0049] 3. On-site sampling plays a very important role in soil assessment and is one of the tasks that must be completed. It is an important basic condition for the entire assessment work. The level and quality of on-site sampling also play a vital role. If the sampled soil is not representative, it will seriously affect the subsequent detection and evaluation of soil improvement. The sampling validity evaluation module of this application can eliminate invalid sampling data and re-sample, thereby avoiding affecting the subsequent soil detection accuracy. Among them, the constructed sampling point location analysis sub-model can effectively judge whether the sampling personnel’s determination of the sampling point is reasonable, and avoid the sampling personnel being lazy and concentrating on a certain piece of soil for detection, thereby avoiding the sampling points being too concentrated and not representative. The constructed sampling environment information analysis sub-model can eliminate soil samples collected in harsh environments, and avoid the soil samples being unrepresentative due to harsh environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a structural diagram of a soil improvement evaluation system for agricultural planting based on big data. DETAILED DESCRIPTION

[0051] 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.

[0052] See also Figure 1 In an embodiment of the present invention, a soil improvement evaluation system for agricultural planting based on big data includes a soil primary collection module, a soil primary detection and analysis module, an improvement method determination module, a regional division and improvement module, a soil secondary collection module, a comparison and analysis module, an evaluation result generation module, a sampling effectiveness evaluation module, a big data platform and a data import module; the soil primary collection module is used to collect samples before the land is improved; the soil primary detection and analysis module is used to detect and analyze the soil samples collected for the first time to determine soil indicators, wherein the soil indicators include pH value, nutrient element content, organic matter content, water content, soil structure, microbial activity, soil bulk density and soil saturation; the improvement method determination module is used to screen out all the schemes adopted for the corresponding successful soil improvement from the big data platform according to the determined soil indicators, and each scheme is marked as Ai, i=1···n, and n is a positive integer; the The regional division and improvement module is used to divide the land to be improved into n areas, and each area implements an improvement plan; the soil secondary collection module is used to determine the number of sampling points in each area, and then collect the improved samples of the land in each area according to the number of sampling points and mix them; the soil secondary collection module is used to detect and analyze the soil samples collected twice to determine the soil index; the comparison and analysis module is used to receive the soil index required by the crops to be planted from the data import module, and compare and analyze the soil index required by the crops to be planted with the improved soil index of each area, and evaluate and determine the most suitable area for planting; the evaluation result generation module is used to generate the best soil improvement plan, that is, the improvement plan adopted by the area most suitable for planting is used as the best soil improvement plan; the sampling effectiveness evaluation module is used to analyze and evaluate the sampling data in the soil secondary collection, and arrange resampling if the evaluation is unqualified. This application can first screen out successful cases with similar soil indicators to be improved, and then use the improvement plans of these successful cases to improve the soil to be improved in different regions, and finally evaluate the most suitable area for planting and its corresponding improvement plan, so as to select the best soil improvement plan.

[0053] In this embodiment: the specific process of the soil secondary collection module determining the number of sampling points in each area is as follows: mark each area corresponding to Ai as Bi, i=1···n; mark the area of ​​Bi as Ci, and then mark the preset area as Cpreset; compare Ci with Cpreset, if Ci=Cpreset, then set up X sampling points in the Bi area corresponding to Ci, otherwise proceed to the next step; if Ci<Cpreset, calculate the difference between Cpreset and Ci, and subtract one sampling point for every hundred square meters of difference, that is, set up X-(Cpreset-Ci) / 100 sampling points; if Ci>Cpreset, calculate the difference between Ci and Cpreset, and add one sampling point for every hundred square meters of difference, that is, set up X+(Ci-Cpreset) / 100 sampling points. This setting can allocate different numbers of sampling points according to the size of the previously divided sampling area, thereby avoiding too many sampling times in a sampling area with a small area, which reduces the sampling speed, and avoiding too few sampling times in a sampling area with a large area, which affects the sampling accuracy, thereby improving the accuracy and comprehensiveness of the sampling data.

[0054] In this embodiment: the sampling effectiveness evaluation module includes: a drone unit, which is used to collect sampling data of sampling personnel in each area, and the sampling data includes sampling point images and sampling environment information, wherein the sampling environment information includes temperature, air pressure, wind speed, and humidity; a data receiving unit, which is used to receive sampling point images and sampling environment information; a data analysis unit, which is used to build an analysis model and output analysis results; a result output unit, which is used to output whether resampling is required according to the analysis results, if the analysis result is qualified, resampling is not required, and if the analysis result is unqualified, resampling is required. The sampling effectiveness evaluation module can eliminate invalid sampling data resampling, thereby avoiding affecting the subsequent soil detection accuracy.

[0055] In this embodiment, the specific analysis process of the analysis model is: constructing a sampling point position analysis sub-model and outputting analysis results, wherein the specific analysis process of the sampling point position analysis sub-model is:

[0056] (1) According to the collected sampling point image, the sampling point position of each area Bi is marked as Pj, j = 1...m, and m is a positive integer;

[0057] (2) Connect each Pj with the other Pj, and use the outermost connecting line as the boundary line of the sampling area;

[0058] (3) Calculate the area of ​​the sampling area based on the determined sampling area boundary line and mark it as C sampling;

[0059] (4) Compare the C sample with the corresponding Ci. If the difference between Ci and C is greater than the preset value, the sampling point is output as unqualified, otherwise proceed to the next step;

[0060] (5) The distance between Pj and the other Pj is marked as Qj, j = 1···m-1;

[0061] (6) Compare Qj with the preset value. If Qj is greater than the preset value, the sampling point is unqualified; if Qj is less than or equal to the preset value, the sampling point is qualified.

[0062] Construct a sampling environment information analysis sub-model and output the analysis results. The specific analysis process of the sampling environment information analysis sub-model is as follows:

[0063] 1) Match the collected temperature value with the preset temperature range. If the collected temperature value does not fall within the preset temperature range, the sampling environment is output as unqualified. If the collected temperature value falls within the preset temperature range, proceed to the next step.

[0064] 2) Match the collected air pressure value with the preset air pressure range. If the collected air pressure value does not fall within the preset air pressure range, the sampling environment is output as unqualified. If the collected air pressure value falls within the preset air pressure range, proceed to the next step;

[0065] 3) Match the collected wind speed value with the preset wind speed range. If the collected wind speed value does not fall within the preset wind speed range, the sampling environment is output as unqualified. If the collected wind speed value falls within the preset wind speed range, proceed to the next step.

[0066] 4) Match the collected humidity value with the preset humidity range. If the collected humidity value does not fall within the preset humidity range, the sampling environment is output as unqualified. If the collected humidity value falls within the preset humidity range, the sampling environment is output as qualified.

[0067] If the analysis results of the sampling point location analysis submodel and the sampling environment information analysis submodel are both qualified, the analysis result of the output analysis model is qualified, otherwise, the analysis result of the output analysis model is unqualified. On-site sampling plays a very important role in soil assessment and is one of the tasks that must be completed. It is an important basic condition for the entire assessment work. The level and quality of on-site sampling also play a vital role. If the sampled soil is not representative, it will seriously affect the later detection and evaluation of soil improvement. The sampling validity evaluation module of this application can eliminate invalid sampling data and resample, thereby avoiding affecting the subsequent soil detection accuracy. Among them, the constructed sampling point location analysis submodel can effectively judge whether the sampling personnel’s determination of the sampling point is reasonable, and avoid the sampling personnel being lazy and concentrating on a certain piece of soil for detection, thereby avoiding the sampling point being too concentrated and not representative. The constructed sampling environment information analysis submodel can eliminate soil samples collected in harsh environments, and avoid soil samples being unrepresentative due to harsh environments.

[0068] In this embodiment: the specific process of the improvement method determination module screening out all the schemes adopted for the corresponding successful soil improvement from the big data platform according to the determined soil index is as follows: marking the soil index determined by the initial soil detection and analysis as R real-time; marking the soil index of each soil improvement case before improvement in the big data platform as Ri, i=1···k, k is a positive integer; performing a similarity comparison between R real-time and Ri, and arranging the similarities of the comparisons in order from high to low; screening out the top n soil improvement cases with the highest similarity; and outputting the improvement schemes adopted by the screened soil improvement cases. This setting can quickly screen out improvement schemes that meet the soil index to be improved.

[0069] In this embodiment: in the process of the similarity comparison between the real-time R and Ri, a separate comparison is adopted, that is, the real-time pH value of R is compared with the pH value of Ri separately to obtain a similarity value Z1; the real-time nutrient element content of R is compared with the nutrient element content of Ri separately to obtain a similarity value Z2; the real-time organic matter content of R is compared with the organic matter content of Ri separately to obtain a similarity value Z3; the real-time moisture content of R is compared with the moisture content of Ri separately to obtain a similarity value Z4; the real-time soil structure of R is compared with the soil structure of Ri separately to obtain a similarity value Z5; the real-time soil structure of R is compared with the soil structure of Ri separately to obtain a similarity value Z6; the real-time soil structure of R is compared with the soil structure of Ri separately to obtain a similarity value Z7; the real-time soil structure of R is compared with the soil structure of Ri separately to obtain a similarity value Z8; the real-time soil structure of R is compared with the soil structure of Ri separately to obtain a similarity value Z9; the real-time soil structure of R is compared with the soil structure of Ri separately to obtain a similarity value Z10; the real-time soil structure of R is compared with the soil structure of Ri separately to obtain a similarity value Z11; the real-time soil structure of R is compared with the soil structure of Ri separately to obtain a similarity value Z12; the real-time soil structure of R is compared with the soil structure of Ri separately to obtain a similarity value Z13; the real-time soil structure of R is compared with the soil structure of Ri separately to obtain a similarity value Z2. Soil structure is compared separately to obtain similarity value Z5; microbial activity of R in real time is compared separately with microbial activity of Ri to obtain similarity value Z6; soil bulk density of R in real time is compared separately with soil bulk density of Ri to obtain similarity value Z7; soil saturation of R in real time is compared separately with soil saturation of Ri to obtain similarity value Z8; then average similarity Z average is calculated = (Z1+Z2+Z3+Z4+Z5+Z6+Z7+Z8) / 8, and Z average is output as the similarity of comparison between R in real time and Ri. This setting effectively improves the accuracy of comparison.

[0070] In this embodiment: the specific process of the comparison and analysis module evaluating and determining the most suitable area for planting is: marking the soil indicators required by the crops to be planted, that is, marking the pH value in the soil indicators required by the crops to be planted as V1, marking the nutrient element content in the soil indicators required by the crops to be planted as V2, marking the organic matter content in the soil indicators required by the crops to be planted as V3, marking the moisture content in the soil indicators required by the crops to be planted as V4, marking the soil structure in the soil indicators required by the crops to be planted as V5, marking the microbial activity in the soil indicators required by the crops to be planted as V6, marking the soil bulk density in the soil indicators required by the crops to be planted as V7, and marking the soil saturation in the soil indicators required by the crops to be planted as V8; marking the improved soil indicators of each area, that is, marking the pH value in the improved soil indicators of each area as v1 , mark the nutrient content in the improved soil index of each region as v2, mark the organic matter content in the improved soil index of each region as v3, mark the water content in the improved soil index of each region as v4, mark the soil structure in the improved soil index of each region as v5, mark the microbial activity in the improved soil index of each region as v6, mark the soil bulk density in the improved soil index of each region as v7, and mark the soil saturation in the improved soil index of each region as v8; compare V1-V8 with v1-v8 for similarity, and obtain similarities z1, z2, z3, z4, z5, z6, z7, z8; calculate the average similarity z average = (z1+z2+z3+z4+z5+z6+z7+z8) / 8, and determine the area with the highest z average as the most suitable area for planting. This setting can quickly and effectively determine the most suitable area for planting.

[0071] In this embodiment: the soil index required by the crops to be planted imported by the data import module can be set according to the needs of the staff.

[0072] The present invention can first screen out successful cases with similar soil indicators to be improved, then use the improvement plans of these successful cases to improve the soil to be improved in different regions, and finally evaluate the most suitable areas for planting and their corresponding improvement plans, thereby selecting the best soil improvement plan. In addition, the present application can allocate different numbers of sampling points according to the size of the sampling area previously divided, thereby avoiding too many sampling times in a sampling area with a small area, which reduces the sampling speed, and also avoiding too few sampling times in a sampling area with a large area, which affects the sampling accuracy, thereby improving the accuracy and comprehensiveness of the sampling data. It should be noted that on-site sampling plays a very important role in soil assessment and is one of the tasks that must be completed. It is an important basic condition for the entire assessment work. The level and quality of on-site sampling also play a vital role. If the sampled soil is not representative, it will seriously affect the subsequent detection and evaluation of soil improvement. The sampling validity evaluation module of this application can eliminate invalid sampling data and re-sample, thereby avoiding affecting the subsequent soil detection accuracy. Among them, the constructed sampling point location analysis sub-model can effectively judge whether the sampling personnel’s determination of the sampling point is reasonable, and avoid the sampling personnel being lazy and concentrating on a certain piece of soil for detection, thereby avoiding the sampling points being too concentrated and not representative. The constructed sampling environment information analysis sub-model can eliminate soil samples collected in harsh environments, and avoid the soil samples being unrepresentative due to harsh environments.

[0073] 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.

[0074] What is described above is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A soil improvement evaluation system for agricultural planting based on big data, It is characterized in that It includes soil primary collection module, soil primary detection and analysis module, improvement method determination module, regional division and improvement module, soil secondary collection module, comparison and analysis module, evaluation result generation module, sampling effectiveness evaluation module, big data platform and data import module; The primary soil collection module is used to collect samples before the land is improved; the primary soil detection and analysis module is used to detect and analyze the initially collected soil samples to determine soil indicators, wherein the soil indicators include pH value, nutrient content, organic matter content, moisture content, soil structure, microbial activity, soil bulk density and soil saturation; the improvement method determination module is used to screen out all the schemes adopted for the corresponding successful soil improvement from the big data platform according to the determined soil indicators, and each scheme is marked as Ai, i=1···n, and n is a positive integer; the area division and improvement module is used to divide the land to be improved into n areas, and implement an improvement plan in each area; the secondary soil collection module is used to determine the sampling points of each area The number of improved land in each area is collected according to the number of sampling points and mixed; the soil secondary collection module is used to detect and analyze the soil samples collected for the second time to determine the soil index; the comparison and analysis module is used to receive the soil index required by the crops to be planted from the data import module, and compare and analyze the soil index required by the crops to be planted with the improved soil index of each area, and evaluate and determine the most suitable area for planting; the evaluation result generation module is used to generate the best soil improvement plan, that is, the improvement plan adopted by the area most suitable for planting is used as the best soil improvement plan; the sampling effectiveness evaluation module is used to analyze and evaluate the sampling data in the secondary soil collection, and arrange re-sampling if the evaluation is unqualified; The specific process of determining the number of sampling points in each area by the soil secondary collection module is as follows: Each region corresponding to Ai is marked as Bi, i = 1···n; Mark the area of ​​Bi as Ci, and then mark the preset area as C preset; Compare Ci with the preset C. If Ci=preset C, set up X sampling points in the Bi area corresponding to Ci, otherwise proceed to the next step; If Ci<Cpreset, calculate the difference between Cpreset and Ci, and subtract one sampling point for every 100 square meters of difference, that is, set up X-(Cpreset-Ci) / 100 sampling points; If Ci>C preset, calculate the difference between Ci and C preset, and add one sampling point for every 100 square meters of difference, that is, set up X+(Ci-C preset) / 100 sampling points; The sampling effectiveness assessment module includes: The drone unit is used to collect sampling data from sampling personnel in each area. The sampling data includes sampling point images and sampling environment information, where the sampling environment information includes temperature, air pressure, wind speed, and humidity; A data receiving unit, used for receiving sampling point images and sampling environment information; Data analysis unit, used to build analysis models and output analysis results; A result output unit, used to output whether resampling is required according to the analysis result. If the analysis result is qualified, resampling is not required; if the analysis result is unqualified, resampling is required; The specific analysis process of the analysis model is as follows: Construct a sampling point location analysis sub-model and output the analysis results. The specific analysis process of the sampling point location analysis sub-model is as follows: (1) According to the collected sampling point image, the sampling point position of each area Bi is marked as Pj, j = 1...m, and m is a positive integer; (2) Connect each Pj with the other Pj, and use the outermost connecting line as the boundary line of the sampling area; (3) Calculate the area of ​​the sampling area based on the determined sampling area boundary line and mark it as C sampling; (4) Compare the C sample with the corresponding Ci. If the difference between Ci and C is greater than the preset value, the sampling point is output as unqualified, otherwise proceed to the next step; (5) The distance between Pj and the other Pj is marked as Qj, j = 1···m-1; (6) Compare Qj with the preset value. If Qj is greater than the preset value, the sampling point is unqualified; if Qj is less than or equal to the preset value, the sampling point is qualified. Construct a sampling environment information analysis sub-model and output the analysis results. The specific analysis process of the sampling environment information analysis sub-model is as follows: 1) Match the collected temperature value with the preset temperature range. If the collected temperature value does not fall within the preset temperature range, the sampling environment is output as unqualified. If the collected temperature value falls within the preset temperature range, proceed to the next step. 2) Match the collected air pressure value with the preset air pressure range. If the collected air pressure value does not fall within the preset air pressure range, the sampling environment is output as unqualified. If the collected air pressure value falls within the preset air pressure range, proceed to the next step; 3) Match the collected wind speed value with the preset wind speed range. If the collected wind speed value does not fall within the preset wind speed range, the sampling environment is output as unqualified. If the collected wind speed value falls within the preset wind speed range, proceed to the next step. 4) Match the collected humidity value with the preset humidity range. If the collected humidity value does not fall within the preset humidity range, the sampling environment is output as unqualified. If the collected humidity value falls within the preset humidity range, the sampling environment is output as qualified. If the analysis results of the sampling point location analysis sub-model and the sampling environment information analysis sub-model are both qualified, the analysis result of the output analysis model is qualified; otherwise, the analysis result of the output analysis model is unqualified.

2. According to claim 1, a soil improvement evaluation system for agricultural planting based on big data, It is characterized in that The specific process of the improvement method determination module screening out all the corresponding solutions adopted for successful soil improvement from the big data platform according to the determined soil indicators is as follows: The soil index determined by the initial soil test analysis is marked as R real time; The soil index of each soil improvement case before improvement in the big data platform is marked as Ri, i = 1···k, k is a positive integer; Compare R with Ri in real time for similarity, and arrange the similarities from high to low; Filter out the top n soil improvement cases with the highest similarity; Output the improvement plan adopted by the screened soil improvement cases.

3. According to claim 2, a soil improvement evaluation system for agricultural planting based on big data, It is characterized in that In the process of the similarity comparison between R and Ri, a separate comparison is adopted, that is, the pH value of R in real time is compared with the pH value of Ri in real time to obtain a similarity value Z1; the nutrient element content of R in real time is compared with the nutrient element content of Ri in real time to obtain a similarity value Z2; the organic matter content of R in real time is compared with the organic matter content of Ri in real time to obtain a similarity value Z3; the moisture content of R in real time is compared with the moisture content of Ri in real time to obtain a similarity value Z4; the soil structure of R in real time is compared with the soil structure of Ri in real time to obtain a similarity value Z5; the soil structure of R in real time is compared with the soil structure of Ri in real time to obtain a similarity value Z6; the soil structure of R in real time is compared with the soil structure of Ri in real time to obtain a similarity value Z7; the soil structure of R in real time is compared with the soil structure of Ri in real time to obtain a similarity value Z8; the soil structure of R in real time is compared with the soil structure of Ri in real time to obtain a similarity value Z9; the soil structure of R in real time is compared with the soil structure of Ri in real time to obtain a similarity value Z1; the soil structure of R in real time is compared with the soil structure of Ri in real time to obtain a similarity value Z2; the soil structure of R in real time is compared with the soil structure of Ri in real time to obtain a similarity value Z3 ...1; the soil structure of R in real The real-time microbial activity of R is compared with that of Ri to obtain a similarity value Z5; the real-time soil bulk density of R is compared with that of Ri to obtain a similarity value Z7; the real-time soil saturation of R is compared with that of Ri to obtain a similarity value Z8; and the average similarity Z average = (Z1+Z2+Z3+Z4+Z5+Z6+Z7+Z8) / 8 is calculated, and Z average is output as the similarity between the real-time and Ri comparisons.

4. According to claim 1, a soil improvement evaluation system for agricultural planting based on big data, It is characterized in that The specific process of the comparison and analysis module to evaluate and determine the most suitable area for planting is as follows: The soil indicators required by the crops to be planted are marked, that is, the pH value in the soil indicators required by the crops to be planted is marked as V1, the nutrient element content in the soil indicators required by the crops to be planted is marked as V2, the organic matter content in the soil indicators required by the crops to be planted is marked as V3, the water content in the soil indicators required by the crops to be planted is marked as V4, the soil structure in the soil indicators required by the crops to be planted is marked as V5, the microbial activity in the soil indicators required by the crops to be planted is marked as V6, the soil bulk density in the soil indicators required by the crops to be planted is marked as V7, and the soil saturation in the soil indicators required by the crops to be planted is marked as V8; The improved soil indicators of each region are marked, that is, the pH value of the improved soil indicators of each region is marked as v1, the nutrient element content of the improved soil indicators of each region is marked as v2, the organic matter content of the improved soil indicators of each region is marked as v3, the moisture content of the improved soil indicators of each region is marked as v4, the soil structure of the improved soil indicators of each region is marked as v5, the microbial activity of the improved soil indicators of each region is marked as v6, the soil bulk density of the improved soil indicators of each region is marked as v7, and the soil saturation of the improved soil indicators of each region is marked as v8; Compare V1-V8 with v1-v8 respectively to obtain similarities z1, z2, z3, z4, z5, z6, z7, z8; Calculate the average similarity z average = (z1+z2+z3+z4+z5+z6+z7+z8) / 8, and determine the area with the highest z average as the most suitable area for planting.

5. According to claim 1, a soil improvement evaluation system for agricultural planting based on big data, It is characterized in that The soil index required by the crops to be planted imported by the data import module can be set according to the needs of the staff.

Images