A smart agriculture intelligent monitoring system and method based on big data

Abstract

The present invention discloses a smart agriculture intelligent monitoring system and method based on big data, which relates to the technical field of smart agriculture. The system comprises: an agricultural data monitoring module, a crop growth prediction module, and an agricultural machinery harvesting allocation module; the agricultural data monitoring module uses remote sensing technology to monitor all farmlands and image information of crops planted in a supervision area, performs grid segmentation on the farmlands, and performs crop maturity analysis and calculation on the crops; the crop growth prediction module is used to construct a crop growth state prediction model, and predict the expected crop maturity of farmland crops at a future time point; the agricultural machinery harvesting allocation module calculates the harvesting effect of each agricultural machinery allocated to each harvesting area, and analyzes the agricultural machinery allocation strategy with the maximum total harvesting effect of all farmlands in the supervision area.

Description

Technical Field

[0001] The present invention relates to the technical field of smart agriculture, and specifically to a smart agriculture intelligent monitoring system and method based on big data. Background Art

[0002] The process of modernization of agricultural machinery and management is constantly advancing, prompting agriculture to develop in the direction of clustered and large-scale production. Under the trend of continuously promoting agricultural land transfer in my country, in the large-scale concentrated and small-scale dispersed farmland structure, how to use intelligent monitoring of agricultural crop information to make accurate harvesting decisions for mainstream crops such as rice and wheat at different farming times to maximize harvesting results is a more critical issue in the current development of modern agriculture. Summary of the invention

[0003] The purpose of the present invention is to provide a smart agriculture intelligent monitoring system and method based on big data to solve the problems raised in the prior art.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A smart monitoring method for smart agriculture based on big data includes the following analysis steps:

[0006] Step S100: setting the width of the farmland grid unit, dividing all farmland into farmland grid units, monitoring farmland image information through remote sensing technology, and measuring the filling degree of each farmland grid unit;

[0007] Step S200: obtaining the remote sensing image historical data of each farmland grid unit in each time period during the crop growth process through remote sensing technology, recording the time point of remote sensing image historical data acquisition, synchronously obtaining the crop final harvest time data in the remote sensing image historical data, calculating and obtaining the crop maturity data of each farmland grid unit in the remote sensing image historical data to construct a crop growth status prediction model;

[0008] Step S300: predicting the expected maturity period of crops in each farmland grid unit, obtaining meteorological parameter forecast information for the future time period, and analyzing the harvest deadline of crops in each farmland grid unit;

[0009] Step S400: using the external navigation interface to monitor and summarize the position data and traversable road information of all agricultural machinery within the management scope in real time, and analyzing the time required for each agricultural machinery to reach each farmland grid unit;

[0010] Step S500: Calculate the harvesting effect of each agricultural machine assigned to each farmland grid unit at each time node, and use dynamic programming method to analyze the maximum total harvesting effect strategy of all farmlands in the supervision area.

[0011] In the above technical solution, step S100 includes the following contents:

[0012] Set the width of the farmland grid unit a, where the farmland grid unit is in the shape of a square with a side length of a, and densely pave all farmland areas so that all farmland areas are covered by the farmland grid units;

[0013] Acquire remote sensing image data of farmland area. For irregular areas at the edge of farmland area, according to the formula: , calculate the filling degree of the farmland grid cells covering the area;

[0014] Among them, r is the filling degree of the farmland grid unit covering the area, is the number of pixels in the farmland area in the remote sensing image covering the farmland grid unit in this area, a is the width of the farmland grid unit, is the number of pixels contained in the remote sensing image per unit area;

[0015] Through remote sensing technology, images of farmland within the supervision area are acquired and gridded, ensuring the accurate collection and analysis of farmland area information under the development trend of large-scale agriculture, providing a good data basis for subsequent strategic decision-making. When processing farmland area image information, pixel-level fill calculation is adopted, and the feedback on farmland area information is more detailed.

[0016] In the above technical solution, step S200 includes the following contents:

[0017] Extract the historical data of remote sensing images during the crop growth process in each farmland grid unit, obtain the reflectance of each band reflectance spectrum, and calculate the crop maturity in each farmland grid unit in the historical data of remote sensing images at different time points. For any farmland grid unit x, according to the formula:

[0018] ;

[0019] in, is the farmland grid unit x crop maturity, is the number of pixels contained in the farmland area in the farmland grid unit x, i is the pixel number contained in the farmland area in the farmland grid unit x, G is the digital amplification gain, is the near-infrared band reflectivity of pixel i, is the red light band reflectivity of pixel i, is the blue light band reflectivity of pixel i, and They refer to the atmospheric scattering correction coefficients for the red and blue light bands, respectively, and L is the ground reflection correction coefficient;

[0020] For different crop types, the interval between the remote sensing data collection time point and the final harvest time point and the crop maturity are used to fit the crop growth state curve to obtain the crop growth state prediction model, which is as follows:

[0021] ;

[0022] in, is the predicted crop maturity of farmland grid unit x, A and B are the prediction model parameters, e is the natural logarithm, k is the growth rate coefficient of the current type of crop, and t is the time difference between the predicted time point and the final harvest of the crop;

[0023] Spectral splitting is used to extract reflected light wave information of different bands from remote sensing images of farmland crops. The growth and maturity status of farmland crops is analyzed in combination with the enhanced vegetation index. Effective image feedback is provided on the gradual maturation of crops during their growth. Compared with the normalized vegetation index, it also has a stronger ability to resist atmospheric interference, further realizing accurate assessment of crop maturity.

[0024] In the above technical solution, step S300 includes the following contents:

[0025] Crop maturity threshold ranges are set according to crop types, and for any farmland grid unit, the crop maturity at the current time point is calculated, and the crop growth state prediction model is used to calculate the estimated time difference from the crop to maturity and harvesting, and then the estimated crop maturity at a future time point is analyzed;

[0026] Calculate the earliest time point in the current farmland grid unit where the crop maturity is expected to be included in the maturity threshold range, and set this time point as the initial maturity time point of the farmland grid unit; calculate the latest time point in the current farmland grid unit where the crop maturity is expected to be included in the maturity threshold range, and set this time point as the cut-off maturity time point of the farmland grid unit; set the time from the initial maturity time point to the cut-off maturity time point as the cut-off harvesting deadline T of the farmland grid unit x. x , denoted as ;in, is the left threshold of the harvest deadline for farmland grid unit x, indicating the initial maturity time point of farmland grid unit x. The left threshold of the harvest deadline for farmland grid unit x, indicating the deadline for maturity of farmland grid unit x;

[0027] Obtain the forecast information of meteorological parameters within the harvest deadline of all monitored farmland areas, screen the parameters that affect the harvest of crops grown in each farmland grid unit, and set the threshold range for interference with harvesting;

[0028] For any farmland grid unit, if there is a time point within the harvest deadline where the value of the selected parameter is included in the interference harvest threshold range, the harvest deadline of the current farmland grid unit is corrected to the time point from the initial maturity time point to the time point where the parameter value is included in the interference harvest threshold range;

[0029] Fully consider the harvesting window period of crop maturity in each farmland area, simultaneously analyze the negative interference of weather changes on crop harvesting, further limit the crop harvesting time, and provide an analytical data basis for subsequent agricultural machinery harvesting allocation.

[0030] In the above technical solution, step S500 includes the following contents:

[0031] Obtain the harvest deadline data for each monitored farmland grid unit, and divide all farmland grid units according to the harvest deadline left threshold Sorting, then setting the harvesting time window, selecting the sorted farmland grid units with the harvesting time window, setting the farmland grid units in the same harvesting time window as the same harvesting batch, and then dividing the geographically adjacent farmland grid units in the same harvesting batch into the same harvesting area;

[0032] When performing harvesting strategy analysis, the harvesting time window of each harvesting area is obtained. When the time point reaches any time window, the agricultural machinery allocation strategy analysis is performed on all harvesting areas within the time window. For agricultural machinery that is currently harvesting, the harvesting effect calculation is performed when the time point reaches the estimated time point for completing the harvesting operation.

[0033] The farmland grid units with adjacent geographical locations and similar maturity times are regionalized to ensure the detailed distribution of farmland crop harvesting while reducing the redundant round-trips of agricultural machinery between farmland grid units, avoiding redundant traffic losses caused by the round-trips of agricultural machinery between grid units due to excessive precise harvesting strategies.

[0034] In the above technical solution, the harvesting effect calculation and total harvesting effect maximum strategy analysis method of different agricultural machines allocated to each harvesting area at each time node in step S500 are as follows:

[0035] Calculate the harvesting results of different agricultural machines assigned to each harvesting area at each time node. For any agricultural machine m and any harvesting area p, according to the formula:

[0036] ;

[0037] ;

[0038] ;

[0039] in, is the harvesting performance of agricultural machine m assigned to harvesting area p, is the traffic loss of agricultural machinery m traveling to the nearest farmland grid unit in the harvesting area p, To avoid constant parameters with denominators equal to zero, e is the natural logarithm and α is the time scale scaling factor. is the time difference between the current time point and the earliest time point of the right threshold of the harvest deadline for the farmland grid unit in the harvest area p, is the area of ​​harvesting area a, j is the farmland grid unit number in harvesting area p, is the number of farmland grid units in the harvesting area p, a is the side length of the farmland grid unit, T is the time taken by the agricultural machine m to harvest one farmland grid unit, in days, is the filling degree of farmland grid unit j, is the agricultural machinery m transportation loss evaluation parameter, is the travel time of the agricultural machine m to the nearest farmland grid unit in the harvesting area p, in hours, The fuel consumption of the agricultural machine m when traveling to the nearest farmland grid unit in the harvesting area p;

[0040] Then, the harvesting results of all harvesting areas are added together to obtain the total harvesting results of farmland in the supervision area, and the dynamic programming method is used to analyze the strategy for maximizing the total harvesting results.

[0041] Combined with the transportation time and fuel consumption of agricultural machinery in different harvesting areas, the area of ​​the allocated harvesting area is analyzed synchronously to maximize the harvesting area completed by a single regional transfer of agricultural machinery. Parameters are also added. , ensuring that when analyzing the harvesting results of each harvesting area at the same time, it avoids the loss caused by not allocating harvesting for a long time after the crops are mature.

[0042] A smart agriculture intelligent monitoring system based on big data using a smart agriculture intelligent monitoring method based on big data described in the above technical solution, the system comprising: an agricultural data monitoring module, a crop growth prediction module, and an agricultural machinery harvesting allocation module;

[0043] The agricultural data monitoring module uses remote sensing technology to monitor the image information of all farmlands and crops planted in the supervision area, grid-segment the farmlands, and perform crop maturity analysis and calculation on the crops; the crop growth prediction module is used to construct a crop growth status prediction model, and predict the expected crop maturity of farmland crops at future time points, and analyze the harvest deadline for each farmland grid unit; the agricultural machinery harvesting allocation module calculates the harvesting results of each agricultural machinery assigned to each harvesting area, and analyzes the agricultural machinery allocation strategy that maximizes the total harvesting results of all farmlands in the supervision area.

[0044] In the above technical solution, the agricultural data monitoring module includes: a remote sensing monitoring unit, a farmland area segmentation unit, and a crop monitoring unit;

[0045] The remote sensing monitoring unit is used to obtain remote sensing image data of the farmland area; the farmland area segmentation unit is used to perform grid segmentation on the farmland area; and the crop monitoring unit is used to monitor the growth status of crops in the supervision area and calculate the crop maturity data.

[0046] In the above technical solution, the crop growth prediction module includes: a model building unit, a crop maturity prediction unit, and a harvest deadline analysis unit;

[0047] The model building unit is used to build a crop growth status prediction model; the crop maturity prediction unit is used to calculate and analyze the expected maturity of the crops; and the harvest deadline analysis unit is used to correct the harvest deadline of the grown crops according to future weather parameters of each farmland grid unit.

[0048] In the above technical solution, the agricultural machinery harvesting allocation module includes: a harvesting area division unit, a harvesting effect calculation unit, and an agricultural machinery allocation unit;

[0049] The harvesting area division unit divides the farmland in the supervision area into different harvesting areas according to the expected maturity of the crops in each farmland grid unit; the harvesting effect calculation unit is used to calculate the harvesting effect of different agricultural machinery allocated to each harvesting area; the agricultural machinery allocation unit is used to analyze the maximum total harvesting effect strategy of all farmlands in the supervision area and allocate agricultural machinery.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] In the present invention, remote sensing technology is used to carry out large-scale monitoring of farmland in the supervision area. By gridding the farmland, the area-based monitoring and management of farmland crops is realized. Then, the spectral reflectance analysis results are obtained according to the remote sensing image data processing, and the growth and maturity status of the crops in the farmland are reflected by detailed analysis. In the present invention, a model is constructed according to the growth and maturity status of crops in each farmland grid unit, the expected maturity of crops in each grid unit is predicted, and then the maturity time of crops in each grid unit is predicted, and the harvest deadline of each grid unit is limited in combination with the changes in future meteorological parameters, which provides a data basis for the time-sharing harvesting of crops in different farmland areas. The farmland grid is divided into different areas by setting a time window. The grid cells are divided into harvesting areas by frame selection, which avoids excessive deployment of agricultural machinery due to precise grid analysis, resulting in unnecessary round trips of agricultural machinery between areas and generating unnecessary traffic losses. The present invention also calculates the harvesting effectiveness of agricultural machinery allocated to each harvesting area at different time points, wherein the earliest time difference between the calculation time point and the right threshold of the grid cell deadline in the harvesting area and the area of ​​the harvesting area are introduced as calculation parameters to ensure that the harvesting area with a shorter harvestable time and a larger overall area has a higher allocation weight when calculating the harvesting effectiveness and allocating agricultural machinery, so that the present invention can take into account both the overall and regional harvesting effectiveness in large-scale farmland harvesting, and is more applicable and practical. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a flow chart of a smart agriculture intelligent monitoring method based on big data in the present invention;

[0053] Figure 2 This is an organizational structure chart of the smart agriculture intelligent monitoring system based on big data in the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] Example: See Figure 1-Figure 2 , the present invention provides a technical solution,

[0056] like Figure 1 As shown, the present invention provides an intelligent monitoring method for smart agriculture based on big data, comprising the following analysis steps:

[0057] Step S100: setting the width of the farmland grid unit, dividing all farmland into farmland grid units, monitoring farmland image information through remote sensing technology, and measuring the filling degree of each farmland grid unit;

[0058] Step S200: obtaining the remote sensing image historical data of each time period during the crop growth process of each farmland grid unit through remote sensing technology, recording the time point of remote sensing image historical data acquisition, synchronously obtaining the crop final harvest time data in the remote sensing image historical data, calculating and obtaining the crop maturity data of each farmland grid unit in the remote sensing image historical data to construct a crop growth status prediction model; Step S300: predicting the expected maturity period of the crops in each farmland grid unit, obtaining the meteorological parameter forecast information of the future time period, and analyzing the harvest deadline of the crops in each farmland grid unit;

[0059] Step S400: using the external navigation interface to monitor and summarize the position data and traversable road information of all agricultural machinery within the management scope in real time, and analyzing the time required for each agricultural machinery to reach each farmland grid unit;

[0060] Step S500: Calculate the harvesting effect of each agricultural machine assigned to each farmland grid unit at each time node, and use dynamic programming method to analyze the maximum total harvesting effect strategy of all farmlands in the supervision area.

[0061] Step S100 includes the following contents:

[0062] Set the width of the farmland grid unit a, where the farmland grid unit is in the shape of a square with a side length of a, and densely pave all farmland areas so that all farmland areas are covered by the farmland grid units;

[0063] Acquire remote sensing image data of farmland area. For irregular areas at the edge of farmland area, according to the formula: , calculate the filling degree of the farmland grid cells covering the area;

[0064] Among them, r is the filling degree of the farmland grid unit covering the area, is the number of pixels in the farmland area in the remote sensing image covering the farmland grid unit in this area, a is the width of the farmland grid unit, is the number of pixels contained in the remote sensing image per unit area;

[0065] In specific implementation, the side length of the farmland grid unit can be set according to the accuracy of the remote sensing technology used and the crop planting habits, ensuring that the number of remote sensing image pixels contained in a single farmland grid unit is in the range of 100-500. In some irregularly shaped farmland plots, farmland grid units are used to densely cover the plots, and then the filling degree of the farmland area in each unit is calculated.

[0066] Step S200 includes the following contents:

[0067] Extract the historical data of remote sensing images during the crop growth process in each farmland grid unit, obtain the reflectance of each band reflectance spectrum, and calculate the crop maturity in each farmland grid unit in the historical data of remote sensing images at different time points. For any farmland grid unit x, according to the formula:

[0068] ;

[0069] in, is the farmland grid unit x crop maturity, is the number of pixels contained in the farmland area in the farmland grid unit x, i is the pixel number contained in the farmland area in the farmland grid unit x, G is the digital amplification gain, is the near-infrared band reflectivity of pixel i, is the red light band reflectivity of pixel i, is the blue light band reflectivity of pixel i, and They refer to the atmospheric scattering correction coefficients for the red and blue light bands, respectively, and L is the ground reflection correction coefficient;

[0070] In specific implementation, the reflectivity of the near-infrared band, the reflectivity of the red band, and the reflectivity of the blue band can be obtained through satellite remote sensing multispectral images, or through measurement by an unmanned aerial vehicle carrying a multispectral sensor. In the above calculation formula, the gain factor G is generally taken as 2.5, and the atmospheric correction coefficient is and It is used to eliminate the scattering interference of the atmosphere on the red and blue light bands, and its value is generally taken as 6 or 7.5. The surface reflection correction coefficient L is used to reduce the noise interference caused by surface reflection, and its value is generally taken as 1.

[0071] For different crop types, the interval between the remote sensing data collection time point and the final harvest time point and the crop maturity are used to fit the crop growth state curve to obtain the crop growth state prediction model, which is as follows:

[0072] ;

[0073] in, is the predicted crop maturity of farmland grid unit x, A and B are the prediction model parameters, e is the natural logarithm, k is the growth rate coefficient of the current type of crop, and t is the time difference between the predicted time point and the final harvest of the crop;

[0074] In specific implementation, for crops such as rice and wheat, which gradually change from green to withered yellow as they grow, the chlorophyll content of crops has a single decreasing trend during the growth process, and the reflectance spectrum of farmland changes more significantly. Therefore, it is more accurate to use remote sensing images for maturity assessment fitting, and an exponential model is used for maturity prediction. The parameter t in the model decreases over time, so the maturity value decreases over time. Rice and wheat are usually judged to be mature and can be harvested when the maturity drops to 0.2-0.4. Since the actual harvesting time is chosen to be a period of time after maturity to allow the grains to be initially dried in the field, the subsequent maturity thresholds can be synchronously corrected and lowered.

[0075] Step S300 includes the following contents:

[0076] Crop maturity threshold ranges are set according to crop types, and for any farmland grid unit, the crop maturity at the current time point is calculated, and the crop growth state prediction model is used to calculate the estimated time difference from the crop to maturity and harvesting, and then the estimated crop maturity at a future time point is analyzed;

[0077] Calculate the earliest time point in the current farmland grid unit when the crop maturity is expected to be included in the maturity threshold range, and set this time point as the initial maturity time point of the farmland grid unit; calculate the latest time point in the current farmland grid unit when the crop maturity is expected to be included in the maturity threshold range, and set this time point as the cut-off maturity time point of the farmland grid unit; set the time from the initial maturity time point to the cut-off maturity time point as the cut-off harvesting deadline T of the current farmland grid unit x , denoted as ;in, is the left threshold of the harvest deadline for farmland grid unit x, indicating the initial maturity time point of farmland grid unit x. The left threshold of the harvest deadline for farmland grid unit x, indicating the deadline for maturity of farmland grid unit x;

[0078] Obtain the forecast information of meteorological parameters within the harvest deadline of all monitored farmland areas, screen the parameters that affect the harvest of crops grown in each farmland grid unit, and set the threshold range for interference with harvesting;

[0079] For any farmland grid unit, if there is a time point within the harvest deadline where the value of the selected parameter is included in the interference harvest threshold range, the harvest deadline of the current farmland grid unit is corrected to the time point from the initial maturity time point to the time point where the parameter value is included in the interference harvest threshold range;

[0080] In specific implementation, taking rice and wheat as examples, a certain amount of precipitation needs to be maintained during the filling period, and after actual maturity, the demand for water gradually decreases. Excessive water can cause grain diseases, mildew, and premature germination in the field. Therefore, by obtaining climate parameters during the harvest period, damage prevention can be carried out to avoid losses in the final harvest due to abnormal changes in field water volume.

[0081] Step S500 includes the following contents:

[0082] Obtain the harvest deadline data for each monitored farmland grid unit, and divide all farmland grid units according to the harvest deadline left threshold Sorting, then setting the harvesting time window, selecting the sorted farmland grid units with the harvesting time window, setting the farmland grid units in the same harvesting time window as the same harvesting batch, and then dividing the geographically adjacent farmland grid units in the same harvesting batch into the same harvesting area;

[0083] When performing harvesting strategy analysis, the harvesting time window of each harvesting area is obtained. When the time point reaches any time window, the agricultural machinery allocation strategy analysis is performed on all harvesting areas within the time window. For agricultural machinery that is currently harvesting, the harvesting effect calculation is performed when the time point reaches the estimated time point for completing the harvesting operation.

[0084] The harvesting effect calculation and total harvesting effect maximum strategy analysis method of different agricultural machines assigned to each harvesting area at each time node in step S500 are as follows:

[0085] Calculate the harvesting results of different agricultural machines assigned to each harvesting area at each time node. For any agricultural machine m and any harvesting area p, according to the formula:

[0086] ;

[0087] ;

[0088] ;

[0089] in, is the harvesting performance of agricultural machine m assigned to harvesting area p, is the traffic loss of agricultural machinery m traveling to the nearest farmland grid unit in the harvesting area p, To avoid constant parameters with denominators equal to zero, e is the natural logarithm and α is the time scale scaling factor. is the time difference between the current time point and the earliest time point of the right threshold of the harvest deadline for the farmland grid unit in the harvest area p, is the area of ​​harvesting area a, j is the farmland grid unit number in harvesting area p, is the number of farmland grid units in the harvesting area p, a is the side length of the farmland grid unit, T is the time taken by the agricultural machine m to harvest one farmland grid unit, in days, is the filling degree of farmland grid unit j, is the agricultural machinery m transportation loss evaluation parameter, is the travel time of the agricultural machine m to the nearest farmland grid unit in the harvesting area p, in hours, The fuel consumption of the agricultural machine m when traveling to the nearest farmland grid unit in the harvesting area p;

[0090] For the above calculation formula, the following calculation example is given: Assuming that the side length of a farmland grid unit is 10 meters, the harvesting time of a farmland grid unit is 0.5 hours, and a total of 5 farmland grid units are designed in the harvesting area, with filling degrees of 80%, 100%, 100%, 100%, and 60% respectively. The traffic loss assessment parameters are It takes 1.5 hours for the agricultural machine to reach the nearest farmland grid unit in the harvesting area, and the fuel consumption is 5 liters. , the unit is day, the time scale scaling factor α=-0.1, , it can be calculated that the harvesting area is 440 square meters, the traffic loss is 2.9, and the harvesting efficiency of the agricultural machinery assigned to the harvesting area is 136.5;

[0091] Then, the harvesting results of all harvesting areas are added together to obtain the total harvesting results of the farmland in the supervision area, and the dynamic programming method is used to analyze the strategy for maximizing the total harvesting results.

[0092] like Figure 2 As shown, the present invention also provides a smart agricultural intelligent monitoring system based on big data, the system comprising: an agricultural data monitoring module, a crop growth prediction module, and an agricultural machinery harvesting allocation module;

[0093] The agricultural data monitoring module uses remote sensing technology to monitor the image information of all farmlands and crops planted in the supervision area, grid-segment the farmlands, and perform crop maturity analysis and calculation on the crops; the crop growth prediction module is used to construct a crop growth status prediction model, and predict the expected crop maturity of farmland crops at future time points, and analyze the harvest deadline for each farmland grid unit; the agricultural machinery harvesting allocation module calculates the harvesting results of each agricultural machinery assigned to each harvesting area, and analyzes the agricultural machinery allocation strategy that maximizes the total harvesting results of all farmlands in the supervision area.

[0094] The agricultural data monitoring module includes: remote sensing monitoring unit, farmland area segmentation unit, and crop monitoring unit;

[0095] The remote sensing monitoring unit is used to obtain remote sensing image data of the farmland area; the farmland area segmentation unit is used to perform grid segmentation on the farmland area; and the crop monitoring unit is used to monitor the growth status of crops in the supervision area and calculate the crop maturity data.

[0096] The crop growth prediction module includes: model building unit, crop maturity prediction unit, and harvest deadline analysis unit;

[0097] The model building unit is used to build a crop growth status prediction model; the crop maturity prediction unit is used to calculate and analyze the expected maturity of the crops; and the harvest deadline analysis unit is used to correct the harvest deadline of the grown crops according to future weather parameters of each farmland grid unit.

[0098] The agricultural machinery harvesting allocation module includes: a harvesting area division unit, a harvesting effect calculation unit, and an agricultural machinery allocation unit;

[0099] The harvesting area division unit divides the farmland in the supervision area into different harvesting areas according to the expected maturity of the crops in each farmland grid unit; the harvesting effect calculation unit is used to calculate the harvesting effect of different agricultural machinery allocated to each harvesting area; the agricultural machinery allocation unit is used to analyze the maximum total harvesting effect strategy of all farmlands in the supervision area and allocate agricultural machinery.

[0100] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A smart monitoring method for smart agriculture based on big data, characterized in that , the method comprises the following analysis steps: Step S100: setting the width of the farmland grid unit, dividing all farmland into farmland grid units, monitoring farmland image information through remote sensing technology, and measuring the filling degree of each farmland grid unit; Step S200: obtaining the remote sensing image historical data of each time period during the crop growth process of each farmland grid unit through remote sensing technology, recording the time point of remote sensing image historical data acquisition, synchronously obtaining the final crop harvest time data in the remote sensing image historical data, calculating and obtaining the crop maturity data of each farmland grid unit in the remote sensing image historical data to construct a crop growth status prediction model; Step S300: predicting the expected maturity period of crops in each farmland grid unit, obtaining meteorological parameter forecast information for the future time period, and analyzing the harvest deadline of crops in each farmland grid unit; Step S400: using the external navigation interface to monitor and summarize the position data and traversable road information of all agricultural machinery within the management scope in real time, and analyzing the time required for each agricultural machinery to reach each farmland grid unit; Step S500: Calculate the harvesting effect of each agricultural machine assigned to each farmland grid unit at each time node, and use dynamic programming method to analyze the maximum total harvesting effect strategy of all farmlands in the supervision area; Wherein, step S500 includes the following contents: Obtain the harvest deadline data of each monitored farmland grid unit, and divide all farmland grid units according to the harvest deadline left threshold t x，1 Sorting, then setting the harvesting time window, selecting the sorted farmland grid units with the harvesting time window, setting the farmland grid units in the same harvesting time window as the same harvesting batch, and then dividing the geographically adjacent farmland grid units in the same harvesting batch into the same harvesting area; When performing harvesting strategy analysis, the harvesting time window of each harvesting area is obtained. When the time point reaches any time window, the agricultural machinery allocation strategy analysis is performed on all harvesting areas within the time window. For agricultural machinery that is currently harvesting, the harvesting effect calculation is performed when the time point reaches the estimated time point for completing the harvesting operation. The calculation method of harvesting effect of different agricultural machinery assigned to each harvesting area at each time node and the analysis method of the maximum total harvesting effect strategy are as follows: Calculate the harvesting results of different agricultural machines assigned to each harvesting area at each time node. For any agricultural machine m and any harvesting area p, according to the formula: IN tra =k1×t tra +k2×W F ; Among them, W m，p is the harvesting performance of the agricultural machine m assigned to the harvesting area p, W tra is the traffic loss of the agricultural machine m traveling to the nearest farmland grid unit in the harvesting area p, ε is a constant parameter to avoid the denominator being 0, e is the natural logarithm, α is the time scale scaling factor, t gap is the time difference between the current time point and the earliest time point of the right threshold of the harvest deadline for the farmland grid unit in the harvest area p, S p is the area of ​​harvesting region a, j is the farmland grid unit number in harvesting region p, n j is the number of farmland grid units in the harvesting area p, a is the side length of the farmland grid unit, T is the time taken by the agricultural machine m to harvest one farmland grid unit, in days, r j is the filling degree of farmland grid unit j, k1 and k2 are the evaluation parameters of agricultural machinery m’s transportation loss, and t tra is the travel time of the agricultural machine m to the nearest farmland grid unit in the harvesting area p, in hours, W F The fuel consumption of the agricultural machine m when traveling to the nearest farmland grid unit in the harvesting area p; Then, the harvesting results of all harvesting areas are added together to obtain the total harvesting results of the farmland in the supervision area, and the dynamic programming method is used to analyze the strategy for maximizing the total harvesting results.

2. According to the intelligent monitoring method of smart agriculture based on big data described in claim 1, it is characterized in that: The step S100 includes the following contents: Set the width of the farmland grid unit a, where the farmland grid unit is in the shape of a square with a side length of a, and densely pave all farmland areas so that all farmland areas are covered by the farmland grid units; Acquire remote sensing image data of farmland area. For irregular areas at the edge of farmland area, according to the formula: Calculate the fill degree of the farmland grid cells covering the area; Among them, r is the filling degree of the farmland grid unit covering the area, n f is the number of pixels in the farmland area in the remote sensing image covering the farmland grid unit in the area, a is the width of the farmland grid unit, and n is u It is the number of pixels contained in the remote sensing image per unit area.

3. According to the intelligent monitoring method of smart agriculture based on big data described in claim 1, it is characterized in that: The step S200 includes the following contents: Extract the historical data of remote sensing images during the crop growth process in each farmland grid unit, obtain the reflectance of each band reflectance spectrum, and calculate the crop maturity in each farmland grid unit in the historical data of remote sensing images at different time points. For any farmland grid unit x, according to the formula: Among them, M x is the crop maturity of farmland grid unit x, n f，x is the number of pixels in the farmland area in the farmland grid unit x, i is the pixel number in the farmland area in the farmland grid unit x, G is the digital amplification gain, NIR i is the near-infrared band reflectivity of pixel i, RED i is the red light band reflectivity of pixel i, BLUE i is the blue light band reflectance of pixel i, C1 and C2 refer to the atmospheric scattering correction coefficients of the red and blue light bands respectively, and L is the ground reflection correction coefficient; For different crop types, the interval between the remote sensing data collection time point and the final harvest time point and the crop maturity are used to fit the crop growth state curve to obtain the crop growth state prediction model, which is as follows: M pre，x =A×e k×t +B; Among them, M pre，x is the predicted crop maturity of farmland grid unit x, A and B are the prediction model parameters, e is the natural logarithm, k is the growth rate coefficient of the current type of crop, and t is the time difference between the predicted time point and the final harvest of the crop.

4. According to the intelligent monitoring method of smart agriculture based on big data described in claim 1, it is characterized in that: The step S300 includes the following contents: Crop maturity threshold ranges are set according to crop types, and for any farmland grid unit, the crop maturity at the current time point is calculated, and the crop growth state prediction model is used to calculate the estimated time difference from the crop to maturity and harvesting, and then the estimated crop maturity at a future time point is analyzed; Calculate the earliest time point among the time points at which the crop maturity in the current farmland grid unit is expected to be included in the maturity threshold range, and set this time point as the initial maturity time point of the farmland grid unit; calculate the latest time point among the time points at which the crop maturity in the current farmland grid unit is expected to be included in the maturity threshold range, and set this time point as the end maturity time point of the farmland grid unit; Set the time from the initial maturity point to the final maturity point as the farmland grid unit x the final harvest deadline T x , denoted as T x [t x，1 , t x，2 ]; where t x，1 is the left threshold of the harvest deadline for farmland grid unit x, indicating the initial maturity time point of farmland grid unit x, t x，2 The left threshold of the harvest deadline for farmland grid unit x, indicating the deadline for maturity of farmland grid unit x; Obtain the forecast information of meteorological parameters within the harvest deadline of all monitored farmland areas, select the parameters that affect the harvest of crops grown in each farmland grid unit, and set the threshold range for interference with harvesting; For any farmland grid unit, if the screened parameter value at any time point within the harvest deadline is included in the interference harvest threshold range, the current farmland grid unit harvest deadline will be corrected to the time from the initial maturity time point to the time point when the parameter value is included in the interference harvest threshold range.

5. A smart agriculture intelligent monitoring system based on big data using a smart agriculture intelligent monitoring method based on big data according to any one of claims 1 to 4, characterized in that ,The system includes: an agricultural data monitoring module, a crop growth prediction module, and an agricultural machinery harvesting ,allocation module; The agricultural data monitoring module uses remote sensing technology to monitor the image information of all farmlands and crops planted in the supervision area, grid-segment the farmlands, and perform crop maturity analysis and calculation on the crops; the crop growth prediction module is used to construct a crop growth status prediction model, and predict the expected crop maturity of farmland crops at future time points, and analyze the harvest deadline for each farmland grid unit; the agricultural machinery harvesting allocation module calculates the harvesting results of each agricultural machinery assigned to each harvesting area, and analyzes the agricultural machinery allocation strategy that maximizes the total harvesting results of all farmlands in the supervision area.

6. The intelligent monitoring system for smart agriculture based on big data according to claim 5 is characterized in that ,The agricultural data monitoring module includes: a remote sensing monitoring unit, a farmland area segmentation unit, and a crop monitoring unit; The remote sensing monitoring unit is used to obtain remote sensing image data of the farmland area; the farmland area segmentation unit is used to perform grid segmentation on the farmland area; and the crop monitoring unit is used to monitor the growth status of crops in the supervision area and calculate the crop maturity data.

7. The intelligent monitoring system for smart agriculture based on big data according to claim 5 is characterized in that ,The crop growth prediction module includes: a model building unit, a crop maturity prediction unit, and a harvest deadline analysis unit; The model building unit is used to build a crop growth status prediction model; the crop maturity prediction unit is used to calculate and analyze the expected maturity of the crops; and the harvest deadline analysis unit is used to correct the harvest deadline of the grown crops according to future weather parameters of each farmland grid unit.

8. The intelligent monitoring system for smart agriculture based on big data according to claim 5 is characterized in that ,The agricultural machinery harvesting allocation module includes: a harvesting area division unit, a harvesting effectiveness calculation unit, and an agricultural machinery allocation unit; The harvesting area division unit divides the farmland in the supervision area into different harvesting areas according to the expected maturity of the crops in each farmland grid unit; the harvesting effect calculation unit is used to calculate the harvesting effect of different agricultural machinery allocated to each harvesting area; the agricultural machinery allocation unit is used to analyze the maximum total harvesting effect strategy of all farmlands in the supervision area and allocate agricultural machinery.

Images