An agricultural planting decision system based on big data analysis

Abstract

The present application relates to the field of agricultural planting technology, and more particularly to an agricultural planting decision system based on big data analysis, which comprises an acquisition module, a preliminary screening module, a first determination module, a second determination module, an identification module and an adjustment module. The present application automatically identifies a decision sub-area with insufficient light and poor crop growth by acquiring the ground slope of the greenhouse planting area, the light uniformity of the greenhouse lamp, the shadow area of the greenhouse film and other multi-environmental data, and the height of the plant and other dry crop growth parameters. The screening accuracy of the decision sub-area is verified by the ground slope and position change characteristics of the decision sub-area within a preset time length to provide targeted planting decisions for managers, effectively solving the problem of low identification accuracy and slow response speed in complex terrain greenhouse planting areas due to excessive reliance on historical data and fixed thresholds, which affects the yield and quality of dry crop.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of agricultural planting technology, and particularly relates to an agricultural planting decision system based on big data analysis. BACKGROUND

[0002] With the rapid development of greenhouse agriculture, crops such as wheat, corn and cotton have high requirements for light, water and soil drainage conditions. However, due to the complex and changeable internal environment of the greenhouse, combined with the uneven terrain of the planting area, the soil humidity is unevenly distributed, the drainage is poor, and the light conditions are significantly different, which brings challenges to the uniform growth of crops. At the same time, the requirements of agricultural production on crop yield and quality are increasing, and higher standards for the accuracy and efficiency of planting decisions are put forward. In this case, how to identify the areas with insufficient light, dry soil or poor crop growth in real time and accurately in the greenhouse planting area with uneven terrain, and provide targeted planting decisions for managers, has become a key problem that needs to be solved to ensure the yield and quality of crops and improve planting efficiency.

[0003] Chinese patent application publication No. CN119494746A discloses an agricultural planting decision method and system. The method includes: first, obtaining historical field data, collecting field data, and preprocessing to obtain a historical agricultural data set and an agricultural data set; then, performing feature extraction, clustering and sensor data fusion, and transmitting to an intelligent agent and an agricultural development platform; finally, the intelligent agent makes a prediction, and the prediction result and the historical field data are sent to the user; based on the agricultural planting decision system implementation, the main structure of the agricultural planting decision system includes a data processing module, an intelligent agent module and an agricultural interaction model module.

[0004] Therefore, the agricultural planting decision method and system have the following problems: emphasizing the acquisition and preprocessing of historical agricultural data sets to guide decision-making, and the static dependence of historical data easily leads to a decision that does not adapt to the current actual situation; only the historical data and real-time data can be combined to give a prediction result of the overall field area, which may not accurately screen out which areas need to be accurately optimized and adjusted; the feature extraction and clustering technology usually analyzes data based on certain preset rules, which may not comprehensively cover various complex dynamic factors in the agricultural environment. SUMMARY

[0005] Therefore, the present application provides an agricultural planting decision system based on big data analysis, which overcomes the problem in the prior art that the yield and quality of crops are affected due to the low recognition accuracy and slow response speed of the greenhouse planting area in complex terrain caused by excessive dependence on historical data and fixed thresholds by fusing multi-environmental data and dynamically optimizing and adjusting mechanisms.

[0006] To achieve the above object, the present application provides an agricultural planting decision system based on big data analysis, comprising:

[0007] The acquisition module is used to acquire the soil evaporation rate, ground slope, light uniformity of the shed lamp above the planting sub-region, incident light intensity, shadow area of the greenhouse film, plant height, leaf area, leaf number, stem diameter, tillering number and leaf water content of various planting sub-regions in the dry-weather crop greenhouse planting area divided based on a preset square side length in real time.

[0008] The preliminary screening module is used to determine a plurality of preliminary screening sub-regions according to the soil evaporation rate and a preset evaporation threshold value.

[0009] The first determination module is used to determine a plurality of first target sub-regions according to the light uniformity, the incident light intensity, the shadow area, a preset light threshold value and a preset area threshold value of each preliminary screening sub-region within a preset screening time length.

[0010] The second determination module is used to determine a plurality of second target sub-regions according to the plant height, the leaf area, the leaf number, the stem diameter, the tillering number and the leaf water content of each planting sub-region within the same preset screening time length.

[0011] The identification module is used to determine a plurality of decision sub-regions according to the coincidence characteristics of the first target sub-regions and the second target sub-regions.

[0012] The adjustment module is used to adjust the preset square side length or the preset evaporation threshold value according to the change characteristics of the ground slope and position of the decision sub-region within a next preset adjustment time length.

[0013] Further, the preliminary screening sub-region is determined based on the preliminary screening module when the soil evaporation rate is less than the preset evaporation threshold value.

[0014] Further, the first determination module comprises:

[0015] The first normalization processing unit is used to perform normalization processing on the light uniformity and the incident light intensity within the preset screening time length respectively to obtain a light uniformity normalized data set and an incident light intensity normalized data set.

[0016] The first index calculation unit, connected with the first normalization processing unit, is used to perform weighted summation on the average value of the light uniformity normalized data set and the average value of the incident light intensity normalized data set to obtain a light illumination comprehensive index of each preliminary screening sub-region.

[0017] a first determining unit connected with the first index calculating unit, configured to determine the preliminary sub-region as a temporary sub-region when the illumination comprehensive index is less than the preset illumination threshold value;

[0018] a second determining unit connected with the first determining unit, configured to determine a plurality of first target sub-regions according to a comparison result of the shadow area of the temporary sub-region and the preset area threshold value within the preset screening time length.

[0019] Further, the second determining unit comprises:

[0020] a second index calculating sub-unit, configured to calculate an average value of the shadow area of the temporary sub-region within the preset screening time length to obtain a shadow area average value of each temporary sub-region;

[0021] a second determining sub-unit connected with the second index calculating sub-unit, configured to determine the temporary sub-region as a first target sub-region when the shadow area average value is greater than a preset area threshold value, to determine a plurality of first target sub-regions.

[0022] Further, the second determining module comprises:

[0023] a second normalization processing unit, configured to perform normalization processing on the plant height, the leaf area, the leaf number, the stem diameter, the tiller number and the leaf moisture content within the preset screening time length to obtain a plant height normalized data set, a leaf area normalized data set, a leaf number normalized data set, a stem diameter normalized data set, a tiller number normalized data set and a leaf moisture content normalized data set;

[0024] a growth index calculating unit connected with the second normalization processing unit, configured to perform weighted summation on an average value of the plant height normalized data set, an average value of the leaf area normalized data set, an average value of the leaf number normalized data set, an average value of the stem diameter normalized data set, an average value of the tiller number normalized data set and an average value of the leaf moisture content normalized data set to obtain a growth comprehensive index of each preliminary sub-region;

[0025] a second determining unit connected with the growth index calculating unit, configured to determine a plurality of second target sub-regions according to a comparison result of the growth comprehensive index and a preset growth threshold value.

[0026] Further, the second target sub-region is determined by the second determining unit when the growth comprehensive index is less than the preset growth threshold value.

[0027] Further, the recognition module comprises:

[0028] a coincidence degree calculation unit configured to calculate a ratio of a number of intersection sub-regions and a number of union sub-regions of the first target sub-region and the second target sub-region to obtain a coincidence degree;

[0029] a recognition unit configured to determine a plurality of decision sub-regions according to a comparison result of the coincidence degree and a preset coincidence degree threshold.

[0030] Further, the decision sub-regions are determined by the recognition unit when the coincidence degree is greater than the preset coincidence degree threshold.

[0031] Further, the adjustment module comprises:

[0032] a distance mean calculation unit configured to calculate an average value of distances between center point coordinates of the decision sub-regions and a preset reference coordinate at each time within a preset adjustment time period to obtain a plurality of position distance means;

[0033] a distance mean fluctuation calculation unit connected with the distance mean calculation unit and configured to calculate a standard deviation of the position distance means to obtain a distance mean fluctuation value;

[0034] a ground slope mean calculation unit configured to calculate an average value of ground slopes of all the decision sub-regions corresponding to each time within the preset adjustment time period when the distance mean fluctuation value is greater than a preset mean fluctuation threshold to obtain a ground slope mean;

[0035] a ground slope change calculation unit connected with the ground slope mean calculation unit and configured to calculate a change rate of the ground slope mean corresponding to any two adjacent times within the preset adjustment time period to obtain a plurality of ground slope change rates;

[0036] a speed fluctuation calculation unit connected with the ground slope change calculation unit and configured to calculate a standard deviation of all the ground slope change rates to obtain a speed fluctuation value;

[0037] an adjustment unit connected with the speed fluctuation calculation unit and configured to adjust the preset square side length or the preset evaporation threshold according to the speed fluctuation value and a preset speed fluctuation threshold.

[0038] Further, the adjustment unit comprises:

[0039] a first adjustment sub-unit configured to increase the preset square side length according to a relative deviation between the speed fluctuation value and the preset speed fluctuation threshold when the speed fluctuation value is greater than the preset speed fluctuation threshold;

[0040] The second adjustment subunit is configured to decrease the preset evaporation threshold according to the relative deviation between the variable speed fluctuation value and the preset variable speed fluctuation threshold when the variable speed fluctuation value is less than the preset variable speed fluctuation threshold.

[0041] Compared with the prior art, the present application has the beneficial effects that by collecting and analyzing the soil evaporation rate, ground slope, light uniformity of the greenhouse lamp above the planting sub-region, incident light intensity, shadow area of the greenhouse film and other multi-environmental data and crop growth parameters in real time, combined with a multi-layer screening mechanism, the light conditions and plant growth conditions of the planting region can be quantitatively analyzed, the decision sub-region of insufficient light and poor growth of the crop can be automatically identified, and the screening accuracy of the decision sub-region can be verified in time through the ground slope and position change characteristics of the decision sub-region within a preset time length, so as to provide the manager with a target of the planting region for optimization and adjustment, and effectively solve the problem that the identification accuracy and response speed of the greenhouse planting region in complex terrain are low due to excessive reliance on historical data and fixed thresholds, thereby affecting the yield and quality of the crop.

[0042] Further, by comparing the real-time acquired soil evaporation rate with the preset evaporation threshold, a plurality of preliminary screening sub-regions can be automatically screened, the region with the soil evaporation rate lower than the preset evaporation threshold can be accurately identified, and the region unsuitable for planting the crop can be accurately screened for further screening, thereby solving the problem that the change of soil humidity is not reacted in time in manual judgment, and ensuring that the region unsuitable for planting is screened in the early stage, so as to provide more accurate basic data for the screening of the decision sub-region.

[0043] Further, by normalizing the light uniformity and incident light intensity within the preset screening time length, the dimensional difference between different light indicators is eliminated, the comparability of the data and the scientificity of the weight allocation are improved; on this basis, the first index calculation unit obtains a light comprehensive index through weighted summation, and the first determination unit comprehensively determines the light comprehensive index and the preset light threshold, so that the region with insufficient light can be quickly and accurately identified. The second determination unit further screens the region with unsuitable light conditions by comparing the shadow area with the preset area threshold, so that the unsuitable region can be effectively identified and excluded in the early stage.

[0044] Further, by calculating the average shadow area of each temporary sub-region within the preset screening time length, the region with unsuitable light conditions can be quantitatively evaluated, on this basis, the first target sub-region with insufficient light can be accurately identified according to the comparison between the average shadow area and the preset area threshold, and objective and continuous judgment of the unsuitable region is realized in the light screening link, the uncertainty of manual experience is avoided, and reliable data basis is provided for subsequent growth state evaluation and decision-making.

[0045] Further, by normalizing the plant height, leaf area, leaf number, stem diameter, tiller number and leaf water content within the preset screening duration, the dimensional differences between different growth indicators are eliminated, and the comparability and scientificity of each indicator are improved; on this basis, the growth index calculation unit performs weighted summation on the mean values of each normalized indicator to obtain a growth comprehensive index of each preliminary screening sub-region, thereby integrating the multi-dimensional growth characteristics into a quantifiable comprehensive index, and by comparing the growth comprehensive index with the preset growth threshold, the second target sub-region with unsatisfactory growth conditions can be accurately identified.

[0046] Further, by comparing the growth comprehensive index with the preset growth threshold, the second determination unit can accurately identify the regions with poor growth conditions. When the growth comprehensive index is less than the preset growth threshold, the system determines the region as the second target sub-region. This way effectively distinguishes regions in different growth states, ensuring that the system can identify regions with poor plant growth and poor environmental suitability.

[0047] Further, by first calculating the ratio of the number of intersection sub-regions to the number of union sub-regions of the first target sub-region and the second target sub-region, a coincidence degree index is obtained. As a measure of the number of intersection sub-regions of two sub-regions, the higher the value, the greater the overlap between the two regions. Then, according to the comparison between the coincidence degree and the preset coincidence degree threshold, the overlapping sub-regions are determined as the decision sub-regions, effectively optimizing the identification process of the decision sub-regions by quantifying the coincidence degree between the first target sub-region and the second target sub-region, avoiding subjectivity and bias in human judgment. By setting a reasonable coincidence degree threshold, the system can accurately identify regions with low light intensity and poor crop growth conditions and mark them as decision sub-regions. After the decision sub-regions are screened out, the manager can provide specific agricultural planting decision recommendations for the deficiencies of these regions, such as reducing irrigation volume, increasing light intensity, adjusting fertilization scheme, or replacing crop varieties more suitable for current environmental conditions. In this way, the system supports precise management of farmland, improves the efficiency and yield of agricultural planting, and reduces resource waste.

[0048] Further, by setting a reasonable coincidence degree threshold, the system can screen out regions with high overlap degree as decision sub-regions, thereby identifying regions with insufficient light and poor crop growth. This not only improves the accuracy and reliability of screening, but also provides a clear basis for subsequent agricultural management and decision adjustment of these regions, allowing them to gradually improve to an environment suitable for the growth of xerophytes.

[0049] Further, by accurately calculating the relevant parameters of the decision sub-region, the dynamic adjustment capability and accuracy of the agricultural planting decision system are significantly improved. By calculating the average distance between the center point of each decision sub-region and the preset reference coordinate, the position change of the decision sub-region can be continuously monitored; by further analyzing the fluctuation of the position change, the amplitude of the fluctuation is identified through the standard deviation, so as to determine whether the position change exceeds the normal range; when the position fluctuation exceeds the preset mean fluctuation threshold, the ground slope average value calculation unit calculates the ground slope average value of all decision sub-regions, to help the system understand whether the ground slope tends to be stable when the position fluctuation is large; by tracking the change rate of the ground slope average value at different time points, and revealing the volatility of the ground slope change through the analysis of the standard deviation, according to the comparison between the variable speed fluctuation value and the preset threshold, the preset square edge length or the preset evaporation threshold is adjusted, to realize the dynamic adjustment and optimization of the screening program.

[0050] Further, by dynamically identifying unreasonable factors in the early screening process, the optimization adjustment of the decision sub-region screening program is realized. Specifically, the early screening module will screen out the decision sub-regions that are not conducive to the growth of dry crops according to different environmental parameters such as soil evaporation rate, light condition, crop growth state, etc. However, due to the complexity of environmental changes, sometimes the early screening will appear some unreasonable situations, at this time, the adjustment unit accurately identifies these abnormal situations by calculating the position change and the ground slope fluctuation, and realizes the adjustment of the preset square edge length or the preset evaporation threshold, to ensure that the screening process of the decision sub-region always remains in a reasonable state. BRIEF DESCRIPTION OF DRAWINGS

[0051] Figure 1 a schematic diagram of the agricultural planting decision system based on big data analysis of the present embodiment;

[0052] Figure 2 a determination logic diagram for determining the early screening sub-region by the early screening module of the present embodiment;

[0053] Figure 3 a determination logic diagram for determining the first target sub-region by the second determination unit of the present embodiment;

[0054] Figure 4 a determination logic diagram for adjusting the preset square edge length or adjusting the preset evaporation threshold by the adjustment unit of the present embodiment. DETAILED DESCRIPTION

[0055] In order to make the objects and advantages of the present application clearer, the present application will be further described below in conjunction with the embodiments; it should be understood that the specific embodiments described herein are only used to explain the present application, and do not limit the present application.

[0056] The preferred embodiments of the present application will be described below with reference to the accompanying drawings. Those skilled in the art will appreciate that the embodiments are only used to explain the technical principles of the present application, and are not intended to limit the scope of protection of the present application.

[0057] Please refer to Figure 1 As shown in the figure, it is a schematic diagram of an agricultural planting decision system based on big data analysis of the present embodiment. The present embodiment provides an agricultural planting decision system based on big data analysis, comprising:

[0058] The acquisition module is used to acquire the soil evaporation rate, ground slope, light uniformity of the greenhouse lamp above the planting sub-region, incident light intensity, shadow area of the greenhouse film, plant height, leaf area, leaf number, stem diameter, tillering number and leaf water content of various planting sub-regions in the dry-tolerant crop greenhouse planting area divided based on a preset square side length in real time;

[0059] The preliminary screening module is connected with the acquisition module and is used to determine a plurality of preliminary screening sub-regions according to the soil evaporation rate and a preset evaporation threshold value;

[0060] The first determination module is connected with the acquisition module and the preliminary screening module respectively, and is used to determine a plurality of first target sub-regions according to the light uniformity, the incident light intensity, the shadow area, a preset light threshold value and a preset area threshold value of each preliminary screening sub-region within a preset screening time length;

[0061] The second determination module is connected with the acquisition module and the preliminary screening module respectively, and is used to determine a plurality of second target sub-regions according to the plant height, the leaf area, the leaf number, the stem diameter, the tillering number and the leaf water content of each planting sub-region within the same preset screening time length;

[0062] The identification module is connected with the first determination module and the second determination module respectively, and is used to determine a plurality of decision sub-regions according to the coincidence characteristics of the first target sub-regions and the second target sub-regions;

[0063] The adjustment module is connected with the acquisition module and the identification module respectively, and is used to adjust the preset square side length or the preset evaporation threshold value according to the change characteristics of the ground slope and position of the decision sub-regions within the next preset adjustment time length.

[0064] In this embodiment, the acquisition module is used to collect multi-dimensional environment and crop growth parameters of each planting sub-area in the greenhouse planting area of drought-tolerant crops in real time to support subsequent accurate screening and decision-making. Drought-tolerant crops refer to crops that are drought-tolerant, have low water requirements, and are sensitive to humidity, such as wheat, corn, cotton, or legume crops, etc. Their growth has high requirements for soil moisture and light conditions. The greenhouse planting area refers to a controllable environment planting area covered with transparent or semi-transparent greenhouse film, which provides relatively stable growth conditions for drought-tolerant crops through environmental regulation such as temperature, humidity, and light. The planting sub-area is a square small area of equal size divided from the entire greenhouse according to a preset grid length, and each sub-area is collected and analyzed as an independent unit to achieve fine monitoring of the environment and crop growth conditions in different areas of the greenhouse. The soil evaporation rate is used to evaluate the soil humidity and dryness, which is obtained through a soil humidity sensor and an evaporation rate calculation module. The ground slope reflects the terrain and drainage of the sub-area, which can be obtained through an inclination sensor or a digital elevation model. The light uniformity and incident light intensity of the greenhouse lamp are used to evaluate the light distribution and photosynthesis potential of crops. The greenhouse lamp is usually uniformly arranged above each sub-area to ensure the uniformity of light in the greenhouse, which is collected through a light sensor. The shadow area of the greenhouse film refers to the area of the shaded area on the ground of the greenhouse formed by the greenhouse film under the action of light. This area is affected by factors such as film wrinkles, inclination angle, hanging height, and solar or light incident angle, etc. It is used to quantify the actual light intensity and uniformity received by each sub-area, thereby evaluating the impact on the growth of drought-tolerant crops. It can be obtained through image recognition or optical measurement technology. Plant height is used to determine the growth stage of crops, which is obtained through laser ranging or structured light sensors. Leaf area, leaf number, stem diameter, and tiller number reflect the growth status and photosynthesis capacity of crops, which are the average values of all crops in each planting sub-area, reflecting the overall growth status of the sub-area, facilitating regional decision-making by the preliminary screening, target area identification, and dynamic adjustment modules. At the same time, the uniformity of crop growth in the region can be evaluated according to the need by combining the standard deviation or other statistical characteristics, which can be counted through computer vision or image recognition technology. The average value of the water content of the leaves of drought-tolerant crops in each planting sub-area is also taken to reflect the overall water status of the sub-area, which assists in evaluating the growth and health of crops and irrigation needs, and can analyze the growth uniformity by combining the standard deviation or coefficient of variation of the water distribution in the region, which is collected through near-infrared spectroscopy or leaf moisture sensors. Through the real-time collection of the above parameters by the acquisition module, the environmental conditions and crop growth conditions of each sub-area in the greenhouse can be fully mastered, providing data support for subsequent preliminary screening, target area identification, and dynamic adjustment.

[0065] The preset grid length is the division scale of the greenhouse planting area, which depends on the actual area of the planting area and the required spatial accuracy, and is usually set between 1 m and 10 m, and is set to 5 m in the embodiment, which can ensure detailed monitoring and data collection of different areas, and optimize the calculation and adjustment process; the preset evaporation threshold is a soil evaporation rate threshold for preliminary screening of sub-regions, which depends on the water requirement of crops and the dryness of soil, and is usually set between 0.1 mm / h and 1.0 mm / h, and is set to 0.5 mm / h in the embodiment, which can effectively screen out areas suitable for growth of dry crops, and ensure that the growth environment of crops is suitable; the preset screening duration is the time period for screening the preliminary screening sub-regions, which depends on the growth period of crops and the frequency of environmental changes, and is usually set between 1 day and 30 days, and is set to 7 days in the embodiment, which can reflect relatively stable environmental conditions and crop growth, and ensure the accuracy of the decision; the preset light threshold is a standard value for determining whether the light of the region is suitable, which depends on the light requirement of crops and the distribution of light in the greenhouse, and is usually set between 100 lx and 1000 lx, and is set to 500 lx in the embodiment, which can ensure that the screened region has suitable light and meets the basic needs of crop growth; the preset area threshold is a standard value for determining whether the shadow area affects the growth of crops, which depends on the light-shielding performance of the greenhouse film and the light requirement of crops, and is usually set between 0.5 m 2 and 1.2 m 2 , and is set to 0.8 m 2 in the embodiment, which can effectively identify those areas that are not suitable for planting due to the influence of shadows; the preset adjustment duration is the time period for dynamically adjusting the grid length or the evaporation threshold, which depends on the frequency of environmental changes and the dynamic adjustment needs of the planting area, and is usually set between 1 day and 15 days, and is set to 5 days in the embodiment, which can optimize the adjustment in real time according to the environmental changes during the growth of crops, and ensure the continuous adaptability of the planting environment.

[0066] By collecting and analyzing the soil evaporation rate, ground slope, light uniformity of the greenhouse lamp above the planting sub-region, incident light intensity, shadow area of the greenhouse film, and other multi-environmental data and crop growth parameters in real time, and combining the multi-layer screening mechanism, the light conditions and plant growth conditions of the planting area can be quantitatively analyzed, and the decision sub-region with insufficient light and poor growth of dry crops can be automatically identified, and the screening accuracy of the decision sub-region can be verified in time through the ground slope and position change characteristics of the decision sub-region within the preset duration, so as to provide the manager with an optimized planting area target, and effectively solve the problem that the identification accuracy and response speed of the greenhouse planting area in complex terrain are low due to excessive reliance on historical data and fixed thresholds, which affects the yield and quality of dry crop.

[0067] Please refer to Figure 2As shown, it is the determination logic diagram of the preliminary screening sub-region determined by the preliminary screening module in this embodiment. In this embodiment, the preliminary screening sub-region is determined by the preliminary screening module when the soil evaporation rate is less than the preset evaporation threshold.

[0068] By comparing the real-time acquired soil evaporation rate with the preset evaporation threshold, a number of preliminary screening sub-regions are automatically screened out, which can accurately identify the regions with soil evaporation rate lower than the preset evaporation threshold, and accurately screen out the regions unsuitable for planting dry crops for further screening, thereby solving the problem of not responding in time to the change of soil humidity in manual judgment, and ensuring that the unsuitable regions are preliminarily screened out in the early stage, thereby providing more accurate basic data for the screening of decision sub-regions.

[0069] Specifically, the first determination module comprises:

[0070] A first normalization processing unit is configured to perform normalization processing on the light uniformity and the incident light intensity in the preset screening time period, respectively, to obtain a light uniformity normalized data set and an incident light intensity normalized data set.

[0071] A first index calculation unit is connected with the first normalization processing unit and configured to perform weighted summation on the average value of the light uniformity normalized data set and the average value of the incident light intensity normalized data set, to obtain a comprehensive light index of each preliminary screening sub-region, M=a×A+b×B, wherein M is the comprehensive light index, a is a preset uniformity weight, A is the average value of the light uniformity normalized data set, b is a preset incident light weight, and B is the average value of the incident light intensity normalized data set.

[0072] A first determination unit is connected with the first index calculation unit and configured to determine the preliminary screening sub-region as a temporary sub-region when the comprehensive light index is less than a preset light threshold.

[0073] A second determination unit is connected with the first determination unit and configured to determine a number of first target sub-regions according to the comparison result of the shadow area of the temporary sub-region in the preset screening time period and the preset area threshold.

[0074] The preset uniformity weight is the weight of the light uniformity in the comprehensive light index, which depends on the importance of the light uniformity to the growth of crops, and is usually set between 0.3 and 0.7, and is set to 0.5 in this embodiment, which can reflect the contribution of the light uniformity to the comprehensive light index; the preset incident light weight is the weight of the incident light intensity in the comprehensive light index, which depends on the sensitivity of crops to light intensity, and is usually set between 0.3 and 0.7, and is set to 0.5 in this embodiment, which can ensure that the incident light intensity accounts for a reasonable proportion in the comprehensive light evaluation.

[0075] The normalization processing of the light uniformity and the incident light intensity in the preset screening duration eliminates the dimensional difference between different illumination indexes, improves the comparability of the data and the scientificity of the weight distribution; on this basis, the first index calculation unit obtains the illumination comprehensive index through weighted summation, and the first determination unit comprehensively determines the illumination comprehensive index and the preset illumination threshold, so that the area with insufficient illumination can be quickly and accurately identified. The second determination unit further screens the area with unsuitable illumination conditions by comparing the shadow area with the preset area threshold, which can effectively identify and exclude the unsuitable area in the early stage.

[0076] Referring to Figure 3 As shown in FIG. 6, which is a determination logic diagram of the second determination unit of the embodiment for determining the first target sub-area, in the embodiment, the second determination unit includes:

[0077] The second index calculation sub-unit is configured to calculate the average value of the shadow area of the temporary sub-area in the preset screening duration, so as to obtain the average value of the shadow area of each temporary sub-area.

[0078] The second determination sub-unit is connected with the second index calculation sub-unit, and is configured to determine that the temporary sub-area is the first target sub-area when the average value of the shadow area is greater than the preset area threshold, so as to determine a plurality of first target sub-areas.

[0079] By calculating the average value of the shadow area of each temporary sub-area in the preset screening duration, the area with unsuitable illumination conditions can be quantitatively evaluated, and on this basis, the first target sub-area with insufficient illumination can be accurately identified according to the comparison between the average value of the shadow area and the preset area threshold, so that the objective and continuous judgment of the unsuitable area is realized in the illumination screening link, the uncertainty of artificial experience is avoided, and a reliable data basis is provided for subsequent growth state evaluation and decision-making.

[0080] Specifically, the second determination module includes:

[0081] The second normalization processing unit is configured to perform normalization processing on the plant height, the leaf area, the leaf number, the stem diameter, the tiller number and the leaf moisture content in the preset screening duration, respectively, to obtain a plant height normalized data set, a leaf area normalized data set, a leaf number normalized data set, a stem diameter normalized data set, a tiller number normalized data set and a leaf moisture content normalized data set.

[0082] a growth index calculation unit, connected with the second normalization processing unit, configured to perform weighted summation on the average of the plant height normalized dataset, the average of the leaf area normalized dataset, the average of the leaf number normalized dataset, the average of the stem diameter normalized dataset, the average of the tiller number normalized dataset and the average of the leaf water content normalized dataset to obtain a growth comprehensive index of each of the preliminary screening sub-regions, N=c×C+d×D+e×E+f×F+g×G+h×H, wherein N is the growth comprehensive index, c is a preset plant height weight, C is the average of the plant height normalized dataset, d is a preset area weight, D is the average of the leaf area normalized dataset, e is a preset number weight, E is the average of the leaf number normalized dataset, f is a preset diameter weight, F is the average of the stem diameter normalized dataset, g is a preset tiller weight, G is the average of the tiller number normalized dataset, h is a preset water weight, and H is the average of the leaf water content normalized dataset;

[0083] a second determination unit, connected with the growth index calculation unit, configured to determine a plurality of second target sub-regions according to a comparison result of the growth comprehensive index and a preset growth threshold.

[0084] The preset plant height weight is an importance coefficient for measuring the plant height on the crop growth in the growth comprehensive index, depends on the influence degree of the plant height on the overall growth condition of the crop, is usually set between 0.1 and 0.3, and is set as 0.2 in the embodiment, which can reflect the contribution of the plant height to the growth comprehensive index; the preset area weight is an importance coefficient for measuring the leaf area on the photosynthesis and growth condition of the crop in the growth comprehensive index, depends on the influence of the leaf area on the photosynthetic capacity of the crop, is usually set between 0.1 and 0.3, and is set as 0.2 in the embodiment, which can reflect the contribution of the leaf area to the growth comprehensive index; the preset number weight is an influence coefficient for measuring the leaf number on the crop growth in the growth comprehensive index, depends on the role of the leaf number on the photosynthesis and growth balance, is usually set between 0.05 and 0.2, and is set as 0.2 in the embodiment, which can reflect the contribution of the leaf number to the growth comprehensive index; the preset diameter weight is an importance coefficient for measuring the stem diameter on the robust growth of the crop in the growth comprehensive index, depends on the influence of the stem thickness on the supporting force and nutrient transportation, is usually set between 0.05 and 0.2, and is set as 0.1 in the embodiment, which can reflect the contribution of the stem diameter to the growth comprehensive index; the preset tillering weight is an influence coefficient for measuring the tiller number on the yield and growth condition of the crop in the growth comprehensive index, depends on the role of the tiller number on the overall growth balance of the crop, is usually set between 0.05 and 0.2, and is set as 0.1 in the embodiment, which can reflect the contribution of the tiller number to the growth comprehensive index. The preset water weight is an influence coefficient for measuring the leaf water content on the growth condition of the crop in the growth comprehensive index, depends on the role of the leaf water content on the physiological health and photosynthesis, is usually set between 0.1 and 0.3, and is set as 0.2 in the embodiment, which can reflect the contribution of the leaf water content to the growth comprehensive index.

[0085] The plant height, the leaf area, the leaf number, the stem diameter, the tiller number and the leaf water content in the preset screening duration are normalized respectively, so as to eliminate the dimensional difference between different growth indexes, improve the comparability and scientificity of each index; on this basis, the growth index calculation unit performs weighted summation on the mean values of the normalized indexes, obtains the growth comprehensive index of each preliminary screening sub-region, integrates the multi-dimensional growth characteristics into a quantifiable comprehensive index, and compares the growth comprehensive index with the preset growth threshold, so as to accurately identify the second target sub-region with an undesirable growth condition.

[0086] Specifically, the second target sub-region is determined by the second determination unit when the growth comprehensive index is less than the preset growth threshold.

[0087] By comparing the comprehensive growth index with a preset growth threshold, the second determining unit can accurately identify areas with poor growth conditions. When the comprehensive growth index is less than the preset growth threshold, the system designates that area as the second target sub-region. This method effectively distinguishes areas with different growth states, ensuring that the system can identify areas with poor plant growth and poor environmental suitability.

[0088] Specifically, the identification module includes:

[0089] The overlap calculation unit is used to calculate the ratio of the number of intersection sub-regions to the number of union sub-regions between the first target sub-region and the second target sub-region, to obtain the overlap degree, R. i,j =|C i ∩C j | / |C i ∪C j |, where C i C is the set of planting sub-regions for the first target sub-region. j R is the set of planting subregions for the second target subregion. i,j The degree of overlap between the first target sub-region and the second target sub-region;

[0090] The identification unit is used to determine several decision sub-regions based on the comparison result between the overlap degree and the preset overlap degree threshold.

[0091] The preset overlap threshold is a threshold used to determine the degree of overlap between the first target sub-region and the second target sub-region. It depends on the distribution characteristics of the differences in light conditions and crop growth status, and is usually set between 0.3 and 0.8. In this embodiment, it is set to 0.6, which can accurately identify areas that have both insufficient light and poor growth status, and use them as decision sub-regions for targeted agricultural management.

[0092] By first calculating the ratio of the intersection sub-region number and the union sub-region number of the first target sub-region and the second target sub-region, a coincidence degree index is obtained. The coincidence degree is a standard for measuring the number of intersection sub-regions of two sub-regions, and the higher the value is, the greater the degree of overlap of the two regions is. Then, the overlapping sub-regions are determined as decision sub-regions by comparing the coincidence degree with a preset coincidence degree threshold. The identification process of the decision sub-regions is optimized by quantifying the coincidence degree between the first target sub-region and the second target sub-region, and the subjectivity and deviation in human judgment are avoided. By setting a reasonable coincidence degree threshold, the system can accurately identify the regions with low light intensity and poor crop growth conditions and mark them as decision sub-regions. After the decision sub-regions are screened out, the manager can provide specific agricultural planting decision suggestions for the defects of these regions, such as reducing irrigation amount, increasing light intensity, adjusting fertilization scheme, or replacing crop varieties more suitable for the current environmental conditions, etc. The problem of how to accurately and efficiently screen out the regions that need further management in a large planting area is solved, and the precision and intelligent degree of the screening process are improved.

[0093] Specifically, the decision sub-region is determined by the identification unit when the coincidence degree is greater than the preset coincidence degree threshold.

[0094] By setting a reasonable coincidence degree threshold, the system can screen out regions with high overlap degree as decision sub-regions, thereby identifying regions with insufficient light and poor crop growth. Not only the accuracy and reliability of the screening are improved, but also a clear basis is provided for subsequent agricultural management and decision adjustment of these regions, making them gradually improve to an environment suitable for the growth of plants that prefer dry conditions.

[0095] Specifically, the adjustment module comprises:

[0096] The distance mean calculation unit is configured to calculate the average of the distances between the center point coordinates of each decision sub-region and the preset reference coordinates at each time within the preset adjustment time period, to obtain a plurality of position distance means.

[0097] The distance mean fluctuation calculation unit is connected with the distance mean calculation unit and is configured to calculate the standard deviation of the position distance means to obtain a distance mean fluctuation value.

[0098] The ground slope average calculation unit is configured to calculate the average of the ground slopes of all decision sub-regions corresponding to each time within the same preset adjustment time period when the distance mean fluctuation value is greater than a preset mean fluctuation threshold, to obtain a ground slope mean.

[0099] a ground slope change calculation unit connected with the ground slope average value calculation unit, configured to calculate the change rate of the ground slope average value corresponding to any two adjacent time points within the preset adjustment time length, to obtain a plurality of ground slope change rates;

[0100] a speed change fluctuation calculation unit connected with the ground slope change calculation unit, configured to calculate the standard deviation of all the ground slope change rates, to obtain a speed change fluctuation value;

[0101] an adjustment unit connected with the speed change fluctuation calculation unit, configured to adjust the preset square side length or the preset evaporation threshold value according to the speed change fluctuation value and a preset speed change fluctuation threshold value.

[0102] The preset reference coordinate is a reference coordinate for measuring the distance between the center point of each decision sub-region and the standard reference position, which depends on the spatial layout of the overall region, the design of the planting area or the location of the specific functional area, and is usually set in the range of 0 to 1000 meters, which is determined according to the size and layout of the specific planting area. In the embodiment, it is set as the geometric center coordinate (500, 500) of the planting area, which can provide a basis for dynamic position adjustment of the decision sub-region and ensure that the system can timely optimize and adjust the parameters according to the position change. The preset average fluctuation threshold value is a standard value for judging whether the position distance average fluctuation exceeds the normal fluctuation range, which depends on the dynamic change range of the decision sub-region, the stability of the growth environment of the crops and the topographic features of the planting area, and is usually set between 0.1 meters and 10 meters. In the embodiment, it is set as 2 meters, which can effectively distinguish between normal fluctuations and abnormal fluctuations. The preset speed change fluctuation threshold value is a standard value for judging whether the ground slope change rate fluctuation exceeds the predetermined range, which depends on the ground slope change characteristics of the decision sub-region, the stable ground slope range required for crop growth, and the topographic conditions, and is usually set between 0.01° / h and 1° / h. In the embodiment, it is set as 0.2° / h, which can ensure timely adjustment of the parameters when the ground slope changes too fast and ensure the rationality of the screening program.

[0103] By accurately calculating the relevant parameters of the decision sub-area, the dynamic adjustment ability and accuracy of the agricultural planting decision system are significantly improved. By calculating the average distance between the center point of each decision sub-area and the preset reference coordinate, the position change of the decision sub-area can be continuously monitored; by further analyzing the fluctuation of the position change, the amplitude of the fluctuation is identified by the standard deviation, so as to judge whether the position change exceeds the normal range; when the position fluctuation exceeds the preset mean fluctuation threshold, the ground slope average value calculation unit calculates the ground slope average value of all decision sub-areas, to help the system understand whether the ground slope tends to be stable when the position fluctuation is large; by tracking the change rate of the ground slope average value at different time points, and revealing the volatility of the ground slope change through the analysis of the standard deviation, according to the comparison between the variable fluctuation value and the preset threshold, the preset square edge length or the preset evaporation threshold is adjusted, so as to realize the dynamic adjustment and optimization of the screening program.

[0104] Please refer to Figure 4 As shown in FIG. 8, which is a determination logic diagram for adjusting the preset square edge length or adjusting the preset evaporation threshold by the adjustment unit in the embodiment, the adjustment unit in the embodiment comprises:

[0105] The first adjustment sub-unit is configured to increase the preset square edge length according to the relative deviation between the variable fluctuation value and the preset variable fluctuation threshold when the variable fluctuation value is greater than the preset variable fluctuation threshold, U'=U×[1+s×(Y-Y0) / Y0], s is a preset square adjustment coefficient, U' is the adjusted preset square edge length, U is the preset square edge length before adjustment, Y is the variable fluctuation value, and Y0 is the preset variable fluctuation threshold.

[0106] The second adjustment sub-unit is configured to decrease the preset evaporation threshold according to the relative deviation between the variable fluctuation value and the preset variable fluctuation threshold when the variable fluctuation value is less than the preset variable fluctuation threshold, P'=P×[1-t×(Y-Y0) / Y0], t is a preset evaporation adjustment coefficient, P' is the adjusted preset evaporation threshold, and P is the preset evaporation threshold before adjustment.

[0107] In the embodiment, the adjustment unit determines that no adjustment is needed when the variable fluctuation value is equal to the preset variable fluctuation threshold.

[0108] The preset square adjustment coefficient is a magnification ratio coefficient for adjusting the preset square side length, depends on the sensitivity of the fluctuation of the change rate of the ground slope of the decision sub-region to the grid division accuracy, is usually set between 0.1 and 0.5, and is set to 0.2 in the embodiment, can flexibly increase the preset square side length according to the deviation of the variable speed fluctuation value, and improves the adaptability and stability of screening; the preset evaporation adjustment coefficient is a reduction ratio coefficient for adjusting the preset evaporation threshold, depends on the requirement of the sensitivity of the fluctuation of the change rate of the ground slope of the decision sub-region to the evaporation threshold, is usually set between 0.05 and 0.3, and is set to 0.1 in the embodiment, can appropriately reduce the evaporation threshold according to the deviation of the variable speed fluctuation value, and optimizes the determination accuracy of the preliminary screening sub-region.

[0109] By dynamically identifying unreasonable factors in the preliminary screening process, the optimization adjustment of the decision sub-region screening program is realized. Specifically, the preliminary screening module will screen out the decision sub-region that is not conducive to the growth of the dry crop according to different environmental parameters such as soil evaporation rate, illumination condition, crop growth state, etc. However, due to the complexity of environmental changes, sometimes the preliminary screening will appear some unreasonable situations. At this time, the adjustment unit accurately identifies these abnormal situations by calculating the position change and the ground slope fluctuation, and realizes the adjustment of the preset square side length or the preset evaporation threshold, so as to ensure that the screening process of the decision sub-region always remains in a reasonable state.

[0110] The above only describes the preferred embodiments of the present application and is not used to limit the present application; for those skilled in the art, the present application can have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A big data analysis based agricultural plantation decision system characterized by, The method comprises the following steps: acquiring a soil evaporation rate, a ground slope, a light uniformity of a greenhouse lamp, an incident light intensity, a shadow area of a greenhouse film, a plant height, a leaf area, a leaf number, a stem diameter, a tillering number, and a leaf water content of each planting sub-region in a greenhouse planting area of a dry-tolerant crop, which is divided based on a preset square side length; determining a plurality of preliminary screening sub-regions according to the soil evaporation rate and a preset evaporation threshold value; determining a plurality of first target sub-regions according to the light uniformity, the incident light intensity, the shadow area, a preset light threshold value, and a preset area threshold value of each preliminary screening sub-region within a preset screening time period; determining a plurality of second target sub-regions according to the plant height, the leaf area, the leaf number, the stem diameter, the tillering number, and the leaf water content of each planting sub-region within the same preset screening time period; determining a plurality of decision sub-regions according to overlapping characteristics of the first target sub-regions and the second target sub-regions; The method comprises the following steps: calculating a ratio of a number of intersection sub-regions and a number of union sub-regions of the first target sub-regions and the second target sub-regions to obtain an overlapping degree; determining an intersection sub-region as the decision sub-region when the overlapping degree is greater than a preset overlapping degree threshold value; adjusting the preset square side length or the preset evaporation threshold value according to a change characteristic of the ground slope and the position of the decision sub-region within a next preset adjustment time period; The method comprises the following steps: calculating an average value of distances between center point coordinates of each decision sub-region and a preset reference coordinate within a preset adjustment time period to obtain a plurality of position distance average values; calculating a standard deviation of the position distance average values to obtain a distance average value fluctuation value; calculating an average value of ground slopes of all decision sub-regions corresponding to each time within the same preset adjustment time period when the distance average value fluctuation value is greater than a preset average value fluctuation threshold value to obtain a ground slope average value; calculating a change rate of the ground slope average values corresponding to any two adjacent times within the preset adjustment time period to obtain a plurality of ground slope change rates; calculating a standard deviation of all ground slope change rates to obtain a change rate fluctuation value; adjusting the preset square side length or the preset evaporation threshold value according to the change rate fluctuation value and a preset change rate fluctuation threshold value; The method comprises the following steps: The first adjusting subunit is configured to increase the preset square side length according to a relative deviation between the gear shifting fluctuation value and the preset gear shifting fluctuation threshold when the gear shifting fluctuation value is greater than the preset gear shifting fluctuation threshold. The second adjusting subunit is configured to decrease the preset evaporation threshold according to a relative deviation between the gear shifting fluctuation value and the preset gear shifting fluctuation threshold when the gear shifting fluctuation value is less than the preset gear shifting fluctuation threshold.

2. The big data analytics based agriculture plantation decision system as claimed in claim 1, wherein, The preliminary screening sub-regions are determined based on the preliminary screening module when the soil evaporation rate is less than the preset evaporation threshold.

3. The big data analytics based agriculture plantation decision system as claimed in claim 2, wherein, The first determining module comprises: The first normalization processing unit is configured to perform normalization processing on the light uniformity and the incident light intensity in the preset screening time period, respectively, to obtain a light uniformity normalized data set and an incident light intensity normalized data set. The first index calculation unit, connected with the first normalization processing unit, is configured to perform weighted summation on the average value of the light uniformity normalized data set and the average value of the incident light intensity normalized data set, to obtain an illumination comprehensive index of each preliminary screening sub-region. The first determining unit, connected with the first index calculation unit, is configured to determine that the preliminary screening sub-region is a temporary sub-region when the illumination comprehensive index is less than the preset illumination threshold. The second determining unit, connected with the first determining unit, is configured to determine a plurality of first target sub-regions according to a comparison result of the shadow area of the temporary sub-region in the preset screening time period and the preset area threshold.

4. The big data analytics based agriculture plantation decision system as claimed in claim 3, wherein, The second determining unit comprises: The second index calculation subunit is configured to calculate an average value of the shadow area of the temporary sub-region in the preset screening time period, to obtain a shadow area average value of each temporary sub-region. The second determining subunit, connected with the second index calculation subunit, is configured to determine that the temporary sub-region is a first target sub-region when the shadow area average value is greater than the preset area threshold, to determine a plurality of first target sub-regions.

5. The big data analytics based agriculture plantation decision system as claimed in claim 4, wherein, The second determining module comprises: The second normalization processing unit is configured to perform normalization processing on the plant height, the leaf area, the leaf number, the stem diameter, the tillering number, and the leaf moisture content in the preset screening time period, respectively, to obtain a plant height normalized data set, a leaf area normalized data set, a leaf number normalized data set, a stem diameter normalized data set, a tillering number normalized data set, and a leaf moisture content normalized data set. The growth index calculation unit, connected with the second normalization processing unit, is configured to perform weighted summation on the average value of the plant height normalized data set, the average value of the leaf area normalized data set, the average value of the leaf number normalized data set, the average value of the stem diameter normalized data set, the average value of the tillering number normalized data set, and the average value of the leaf moisture content normalized data set, to obtain a growth comprehensive index of each preliminary screening sub-region. The second determining unit, connected with the growth index calculation unit, is configured to determine a plurality of second target sub-regions according to a comparison result of the growth comprehensive index and a preset growth threshold.

6. The big data analytics based agriculture plantation decision system as claimed in claim 5, wherein, The second target sub-region is determined based on the second determining unit when the growth comprehensive index is less than the preset growth threshold.

Images