Intelligent agricultural platform based on big data

Abstract

The invention discloses a smart agricultural platform based on big data, and the platform comprises the steps: photographing a farmland image, carrying out the feature analysis of the farmland image, and detecting the growth feature data of grains in the farmland image; the growth trend of the grains is detected, and the growth deviation condition of the grains under the growth trend is analyzed; according to the method, the grain position is detected in real time, the advancing route of the grain harvester is adjusted, and the harvesting process of the grain is completed, the position state of the grain on the advancing route of the grain harvester can be effectively predicted by analyzing the growth deviation condition of the grain under the growth trend, and the growth condition of the grain in a farmland can be extracted and predicted; compared with the prior art, the grain harvesting device has the advantages that a favorable basis is provided for efficient grain harvesting of the harvester, meanwhile, by adjusting the advancing route of the grain harvester, grain loss can be reduced as much as possible when a harvesting opening of the harvester makes contact with grains, the harvesting rate is increased, and the grain harvesting device has the advantages of being high in effective grain harvesting rate and high in grain growth state monitoring capacity.

Description

Technical Field

[0001] The present invention relates to the field of agricultural management technology, and in particular to a smart agriculture platform based on big data. Background Art

[0002] Smart agriculture applies IoT technology to traditional agriculture, using sensors and software to control agricultural production through mobile or computer platforms, making traditional agriculture more intelligent. Smart agriculture enables real-time monitoring of crop growth factors, such as temperature, light, air composition, and soil conditions.

[0003] Existing smart agriculture platforms analyze farmland and crop growth and development, allowing for timely monitoring of grain growth within the fields. During the operation of a grain harvester, if the angle between the grain head and the harvester's direction of travel is significantly different, the harvesting mouth may not be able to crush all the grain in the row, resulting in missed portions. Therefore, it is essential to design a big data-based smart agriculture platform that can achieve a high effective grain harvesting rate and robust grain growth status monitoring capabilities. Summary of the Invention

[0004] The purpose of the present invention is to provide a smart agriculture platform based on big data to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a smart agriculture platform based on big data, comprising:

[0006] photographing farmland images, performing feature analysis on the farmland images, and detecting growth feature data of grains in the farmland images;

[0007] detecting a growth trend of the grain based on the growth characteristic data of the grain, analyzing a deviation of the grain under the growth trend, analyzing a loss caused by the grain harvester contacting the grain at different travel angles based on the deviation, and recording a travel angle corresponding to a minimum grain loss;

[0008] The grain position is detected in real time, the travel route of the grain harvester is adjusted, and the grain harvesting process is completed.

[0009] According to the above technical solution, detecting the growth trend of the grain based on the growth characteristic data of the grain and analyzing the deviation of the growth of the grain under the growth trend includes:

[0010] Get the average growth height data of the grains in the farmland, set the drone at a height above the ground The device flies in a preset direction at a height of times the average growth height to capture images of the farmland, wherein is the preset minimum flight altitude magnification value,

[0011] Establish a spatial rectangular coordinate system with the center of the farmland block as the coordinate origin, the UAV flight direction extending through the coordinate origin as the Y axis, the X axis passing through the coordinate origin on the plane where the farmland block is located and perpendicular to the Y axis as the X axis, and the Z axis passing through the coordinate origin and perpendicular to the X and Y axes as the Z axis, with the coordinate origin as (0, 0). The UAV is used to capture farmland images;

[0012] The coordinates of the grains in the intercepted grain in the rectangular coordinate system are (x1, y1, z1), (x2, y2, z2)...(x n ,y n , z n ), and obtain the distance value between each adjacent grain in turn.

[0013] According to the above technical solution, the detection of the growth trend of the grain based on the growth characteristic data of the grain and the analysis of the deviation of the growth of the grain under the growth trend further include:

[0014] Set four time nodes in chronological order, including:

[0015] a first time node, the first time node being used to record whether an initial position of the grain is shifted after the grain is not affected by the wind;

[0016] a second time node, the second time node being used to monitor the displacement of the grain after the grain is affected by wind;

[0017] a third time node, the third time node being used to predict a possible displacement range of the grains when the grains are affected by wind forces in a direction different from the wind forces at the second time node, under the condition that the grains are affected by the wind forces at the second time node;

[0018] The fourth time node is used to predict the displacement of grains under the influence of wind at the second time node and after being squeezed by the harvesting port of the grain harvester.

[0019] According to the above technical solution, the detection of the growth trend of the grain based on the growth characteristic data of the grain and the analysis of the deviation of the growth of the grain under the growth trend further include:

[0020] Get the first offset coefficient of the grain at the first time node Where z0 is the preset limit value of the height of the grain from the ground, L c is the distance between the grains, i is the sequence value of the grains in the cereal in descending order of z coordinate, 2≤i≤n, and δ is the preset influence coefficient;

[0021] Obtaining first deviation data and second deviation data of the grain in the spatial rectangular coordinate system, wherein the first deviation data is generated when the grain is affected by wind in the current farmland and is offset from its original position, and the second deviation data is generated when the grain is touched by a harvesting port of a grain harvester;

[0022] The first deviation data includes:

[0023] the second offset coefficient of the grain at the second time node;

[0024] a possible value range of a third offset coefficient of the grain at the third time node, the third offset coefficient of the grain being predicted based on the second offset coefficient;

[0025] The second offset data includes:

[0026] a third offset coefficient generated when the target grain is squeezed by the harvesting port at the fourth time node;

[0027] A fourth offset coefficient is generated when the target grain is squeezed by the harvesting port under the influence of the first deviation data at the fourth time node.

[0028] According to the above technical solution, the possible numerical range of the third offset coefficient of the grain at the third time node includes:

[0029] When it is detected that the target grain has the first deviation data, the deviation of the grain caused by the wind from k different directions is predicted, wherein the wind from the k different directions converges at the position of the target grain, and the angle of the wind from each direction is the same. Where r is the angle value of the wind in each direction, the wind direction corresponding to the first deviation coefficient and the second deviation coefficient of the grain are compared to obtain the wind direction difference u;

[0030] Compare the wind direction difference with the difference between the first deviation coefficient and the second offset coefficient, obtain the influence relationship of the wind direction difference u on the offset coefficient according to the size of the wind direction difference, input the influence relationship into the second offset coefficient to obtain the possible numerical range of the third offset coefficient, and the influence relationship includes different linear relationship data between the wind direction difference u and the offset coefficient when it takes different non-special values ​​and the fixed value corresponding to the offset coefficient when it is a special value.

[0031] According to the above technical solution, the fourth offset coefficient generated when the target grain is squeezed by the harvesting port under the influence of the first deviation data at the fourth time node is obtained, includes:

[0032] When the grain harvester reaches the target grain position and detects that the harvesting opening of the grain harvester touches the target grain, a compression model of the target grain being squeezed by the harvesting opening is obtained, wherein the compression model is generated after the target grain is squeezed by the harvesting opening;

[0033] The second deviation data of the target grain being squeezed by the harvesting port under the condition of the first deviation data is entered, and the fourth offset coefficient is obtained by making changes based on the squeezing model within the possible numerical range of the third offset coefficient of the grain.

[0034] According to the above technical solution, a smart agriculture system based on big data includes:

[0035] A data acquisition module, the data acquisition module is used to capture farmland images, perform feature analysis on the farmland images, and detect growth feature data of grains in the farmland images;

[0036] a detection module, the detection module being configured to detect a growth trend of the grain based on the growth characteristic data of the grain, analyze a deviation of the grain growth under the growth trend, analyze a loss caused by the grain harvester contacting the grain at different travel angles based on the deviation, and record a travel angle corresponding to a minimum grain loss;

[0037] The regulating module is used to detect the position of grains in real time, adjust the travel route of the grain harvester, and complete the grain harvesting process.

[0038] According to the above technical solution, the detection module includes:

[0039] The growth trend detection module is used to obtain the average growth height data of the grains in the farmland, and set the drone to The device flies in a preset direction at a height of times the average growth height to capture images of the farmland, wherein is the preset minimum flight altitude magnification value, A spatial rectangular coordinate system is established with the center of the farmland block as the coordinate origin, the flight direction of the drone extending through the coordinate origin as the Y axis, the plane of the farmland block perpendicular to the Y axis through the coordinate origin as the X axis, and the plane of the farmland block perpendicular to the X and Y axes through the coordinate origin as the Z axis. The coordinate origin is (0, 0). The drone is used to shoot farmland images; the coordinates of the grains in the grain in the spatial rectangular coordinate system are (x1, y1, z1), (x2, y2, z2)... (x n ,y n , z n ), and obtain the distance value between each adjacent grain in turn;

[0040] An offset detection module is used to obtain first deviation data and second deviation data of the grain in the spatial rectangular coordinate system, wherein the first deviation data is generated after the grain is deflected by wind in the current farmland, and the second deviation data is generated after the grain is touched by the harvesting port of the grain harvester.

[0041] According to the above technical solution, the offset detection module includes:

[0042] The first offset module is used to sequentially set four time nodes arranged in chronological order, including: the first time node, the first time node is used to record whether the initial position of the grain is offset after the grain is not affected by the wind; the second time node, the second time node is used to monitor the offset of the grain after the grain is affected by the wind; the third time node, the third time node is used to predict the possible offset range of the grain after the grain is affected by the wind at the second time node and the wind direction is different from the wind at the second time node; the fourth time node, the fourth time node is used to predict the offset of the grain after the grain is affected by the wind at the second time node and is squeezed by the harvesting port of the grain harvester. Obtain the first offset coefficient of the grain at the first time node. Where z0 is the preset limit value of the height of the grain from the ground, L c is the distance between the grains, i is the sequence value of the grains in the cereal in descending order of z coordinate, 2≤i≤n, and δ is the preset influence coefficient;

[0043] A second offset module, which is used for the first deviation data, includes:

[0044] the second offset coefficient of the grain at the second time node;

[0045] a possible value range of a third offset coefficient of the grain at the third time node, the third offset coefficient of the grain being predicted based on the second offset coefficient;

[0046] The second offset data includes:

[0047] a third offset coefficient generated when the target grain is squeezed by the harvesting port at the fourth time node;

[0048] A fourth offset coefficient is generated when the target grain is squeezed by the harvesting port under the influence of the first deviation data at the fourth time node.

[0049] According to the above technical solution, the adjustment module includes:

[0050] A setting module is configured to predict the displacement of the grain after it is subjected to wind forces in k different directions when the target grain is detected to have the first deviation data, wherein the wind forces in the k different directions converge at the target grain position and the angle of the wind force in each direction is the same. Where r is the angle value of the wind in each direction, the wind direction corresponding to the first deviation coefficient and the second deviation coefficient of the grain are compared to obtain the wind direction difference u;

[0051] Compare the wind direction difference with the difference between the first deviation coefficient and the second offset coefficient, obtain the influence relationship of the wind direction difference u on the offset coefficient according to the size of the wind direction difference, input the influence relationship into the second offset coefficient to obtain the possible numerical range of the third offset coefficient, and the influence relationship includes different linear relationship data between the wind direction difference u and the offset coefficient when it takes different non-special values ​​and the fixed value corresponding to the offset coefficient when it is a special value.

[0052] A position locking module is used to obtain an extrusion model of the target grain being squeezed by the harvesting port when the grain harvester detects that the harvesting port of the grain harvester touches the target grain when the grain harvester reaches the target grain position. The extrusion model is generated after the target grain is squeezed by the harvesting port; the second deviation data of the target grain being squeezed by the harvesting port under the condition of the first deviation data is entered, and the fourth offset coefficient is obtained by making changes based on the extrusion model within the possible numerical range of the third offset coefficient of the grain.

[0053] Compared with the prior art, the beneficial effects achieved by the present invention are: the present invention detects the growth trend of grains based on the growth characteristic data of grains, analyzes the growth deviation of grains under the growth trend, can effectively predict the position status of grains on the route of the grain harvester, and can extract and predict the growth status of grains in the farmland, providing a favorable basis for the harvester to efficiently harvest grains, and at the same time, by adjusting the route of the grain harvester, so that when the harvesting port of the harvester contacts the grains, the loss of grains can be reduced as much as possible, thereby improving the harvest ratio. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0055] Figure 1 This is a flow chart of a big data-based smart agriculture platform provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0057] See also Figure 1 , which is a flow chart of a smart agriculture platform based on big data provided by an embodiment of the present invention, such as Figure 1 It can be seen that the smart agriculture platform based on big data includes:

[0058] Step S1: photographing a farmland image, performing feature analysis on the farmland image, and detecting growth feature data of grains in the farmland image;

[0059] Step S2: detecting the growth trend of the grain based on the growth characteristic data of the grain, analyzing the deviation of the grain under the growth trend, analyzing the loss caused by the grain harvester contacting the grain at different travel angles based on the deviation, and recording the travel angle corresponding to the minimum grain loss;

[0060] Step S3: Detect the position of grains in real time, adjust the route of the grain harvester, and complete the grain harvesting process. The route of the grain harvester is only appropriately adjusted according to the growth environment of the grains in the current farmland. The preferred embodiment is to move the route of the grain harvester in parallel in the longitudinal direction when the longitudinal route of the farmland can be changed, so that some grains that were cut on the original route can be well harvested into the harvester.

[0061] Embodiments of the present invention detect grain growth trends based on grain growth characteristic data and analyze the deviations in grain growth within these trends. This allows for effective prediction of the grain's position along a grain harvester's path and foresight of the grain's growth within the field, providing a basis for efficient grain harvesting. Furthermore, by adjusting the harvester's path, grain loss can be minimized when the harvester's reaping opening contacts the grain, thereby increasing the yield rate.

[0062] In certain preferred embodiments, detecting the growth trend of the grain based on the growth characteristic data of the grain and analyzing the deviation of the growth of the grain under the growth trend includes:

[0063] Step S201: Obtain the average growth height data of the grains in the farmland, and set the drone to The device flies in a preset direction at a height of times the average growth height to capture images of the farmland, wherein is the preset minimum flight altitude magnification value,

[0064] Step S202: Establish a spatial rectangular coordinate system with the center of the farmland block as the coordinate origin, the UAV's flight direction extending through the coordinate origin as the Y axis, the X axis passing through the coordinate origin in the plane of the farmland block and perpendicular to the Y axis as the X axis, and the Z axis passing through the coordinate origin and perpendicular to the X and Y axes as the Z axis. The coordinate origin is (0, 0). The UAV is used to capture farmland images.

[0065] Step S203: The coordinates of the grains in the space rectangular coordinate system are respectively (x1, y1, z1), (x2, y2, z2) ... (x n ,y n , z n ), and obtain the distance value between each adjacent grain in turn.

[0066] In certain preferred embodiments, detecting the growth trend of the grain based on the growth characteristic data of the grain and analyzing the deviation of the growth of the grain under the growth trend further includes:

[0067] Step S211: sequentially set four time nodes arranged in chronological order, including:

[0068] a first time node, the first time node being used to record whether an initial position of the grain is shifted after the grain is not affected by the wind;

[0069] a second time node, the second time node being used to monitor the displacement of the grain after the grain is affected by wind;

[0070] a third time node, the third time node being used to predict a possible displacement range of the grains when the grains are affected by wind forces in a direction different from the wind forces at the second time node, under the condition that the grains are affected by the wind forces at the second time node;

[0071] The fourth time node is used to predict the displacement of grains under the influence of wind at the second time node and after being squeezed by the harvesting port of the grain harvester.

[0072] In certain preferred embodiments, detecting the growth trend of the grain based on the growth characteristic data of the grain and analyzing the deviation of the growth of the grain under the growth trend further includes:

[0073] Step S221: Obtain the first offset coefficient of the grain at the first time node Where z0 is the preset limit value of the height of the grain from the ground, L c is the distance between the grains, When the grains are densely arranged in the grain, the z-axis difference between adjacent grains is too low to be monitored. By controlling the number of interval grains, the z-axis difference between the interval grains is set to be higher than the minimum limit value z Q , so that the first deviation coefficient of the cereal can be monitored, i is the sequence value of the cereal grains arranged in descending order of z coordinates, 2≤i≤n, and δ is a preset influence coefficient;

[0074] Step S222: Acquire first deviation data and second deviation data of the grain in the spatial rectangular coordinate system, wherein the first deviation data is generated when the grain is affected by wind in the current farmland and is offset from its original position, and the second deviation data is generated when the grain is touched by the harvesting port of the grain harvester;

[0075] During the operation of the grain harvester, the grain harvester uses a harvesting mouth to crush the grains. However, when the angle difference between the deflection direction of the grain head and the traveling direction of the grain harvester is too large, the harvesting mouth cannot crush all the grains in the row, and some grains may be missed.

[0076] Step S223: The first deviation data includes:

[0077] the second offset coefficient of the grain at the second time node;

[0078] a possible value range of a third offset coefficient of the grain at the third time node, the third offset coefficient of the grain being predicted based on the second offset coefficient;

[0079] The wind force in the farmland block will increase the deviation angle of the grain in the deviation direction (when the wind direction in the farmland block is unstable, the deviation angle of the grain in multiple deviation directions will change within a preset time period, making it difficult to monitor with a wind monitor);

[0080] At the second time point, the degree of grain deviation is limited within the constraints of the first deviation data. The degree of grain deviation at the first and second time points can also be used to predict, to a certain extent, the degree of grain deviation at the third time point when the grain is not touched by the harvesting port.

[0081] Step S224: The second offset data includes:

[0082] a third offset coefficient generated when the target grain is squeezed by the harvesting port at the fourth time node;

[0083] A fourth offset coefficient is generated when the target grain is squeezed by the harvesting port under the influence of the first deviation data at the fourth time node.

[0084] In some preferred embodiments, the possible numerical range of the third offset coefficient of the grain at the third time node includes:

[0085] Step S2231: When it is detected that the target grain has the first deviation data, the deviation of the grain caused by winds in k different directions is predicted, wherein the winds in the k different directions converge at the target grain position, and the angles of the winds in each direction are the same. Where r is the angle value of the wind in each direction, the wind direction corresponding to the first deviation coefficient and the second deviation coefficient of the grain are compared to obtain the wind direction difference u;

[0086] Step S2232: Compare the wind direction difference with the difference between the first deviation coefficient and the second offset coefficient, obtain the influence relationship of the wind direction difference u on the offset coefficient according to the size of the wind direction difference, input the influence relationship into the second offset coefficient to obtain the possible numerical range of the third offset coefficient, and the influence relationship includes different linear relationship data between the wind direction difference u and the offset coefficient when it takes different non-special values ​​and the fixed value corresponding to the offset coefficient when it is a special value.

[0087] By comparing the grain deviations at two monitoring time nodes, the first deviation data is made dynamic to predict the possible deviation of grain at the third time node, that is, to predict the second deviation data.

[0088] In some preferred embodiments, the obtaining of a fourth offset coefficient generated when the target grain is squeezed by the harvesting port under the influence of the first deviation data at the fourth time node includes:

[0089] Step S2241: When the grain harvester reaches the target grain position and detects that the harvesting port of the grain harvester touches the target grain, a compression model of the target grain being squeezed by the harvesting port is obtained, where the compression model is generated when the target grain is squeezed by the harvesting port;

[0090] Step S2242: Enter the second deviation data of the target grain being squeezed by the harvesting port under the first deviation data, make changes based on the squeezing model within the possible numerical range of the third offset coefficient of the grain, and obtain the fourth offset coefficient.

[0091] Based on the same concept as the above embodiment, an embodiment of the present invention further provides a smart agriculture system based on big data, including:

[0092] A data acquisition module, the data acquisition module is used to capture farmland images, perform feature analysis on the farmland images, and detect growth feature data of grains in the farmland images;

[0093] a detection module, the detection module being configured to detect a growth trend of the grain based on the growth characteristic data of the grain, analyze a deviation of the grain growth under the growth trend, analyze a loss caused by the grain harvester contacting the grain at different travel angles based on the deviation, and record a travel angle corresponding to a minimum grain loss;

[0094] The regulating module is used to detect the position of grains in real time, adjust the travel route of the grain harvester, and complete the grain harvesting process.

[0095] In this embodiment, the detection module includes:

[0096] The growth trend detection module is used to obtain the average growth height data of the grains in the farmland, and set the drone to The device flies in a preset direction at a height of times the average growth height to capture images of the farmland, wherein is the preset minimum flight altitude magnification value, A spatial rectangular coordinate system is established with the center of the farmland block as the coordinate origin, the flight direction of the drone extending through the coordinate origin as the Y axis, the plane of the farmland block perpendicular to the Y axis through the coordinate origin as the X axis, and the plane of the farmland block perpendicular to the X and Y axes through the coordinate origin as the Z axis. The coordinate origin is (0, 0). The drone is used to shoot farmland images; the coordinates of the grains in the grain in the spatial rectangular coordinate system are (x1, y1, z1), (x2, y2, z2)... (x n ,y n , z n ), and obtain the distance value between each adjacent grain in turn;

[0097] An offset detection module is used to obtain first deviation data and second deviation data of the grain in the spatial rectangular coordinate system, wherein the first deviation data is generated after the grain is deflected by wind in the current farmland, and the second deviation data is generated after the grain is touched by the harvesting port of the grain harvester.

[0098] In this embodiment, the offset detection module includes:

[0099] The first offset module is used to sequentially set four time nodes arranged in chronological order, including: the first time node, the first time node is used to record whether the initial position of the grain is offset after the grain is not affected by the wind; the second time node, the second time node is used to monitor the offset of the grain after the grain is affected by the wind; the third time node, the third time node is used to predict the possible offset range of the grain after the grain is affected by the wind at the second time node and the wind direction is different from the wind at the second time node; the fourth time node, the fourth time node is used to predict the offset of the grain after the grain is affected by the wind at the second time node and is squeezed by the harvesting port of the grain harvester. Obtain the first offset coefficient of the grain at the first time node. Where z0 is the preset limit value of the height of the grain from the ground, L c is the distance between the grains, i is the sequence value of the grains in the cereal in descending order of z coordinate, 2≤i≤n, and δ is the preset influence coefficient;

[0100] A second offset module, which is used for the first deviation data, includes:

[0101] the second offset coefficient of the grain at the second time node;

[0102] a possible value range of a third offset coefficient of the grain at the third time node, the third offset coefficient of the grain being predicted based on the second offset coefficient;

[0103] The second offset data includes:

[0104] a third offset coefficient generated when the target grain is squeezed by the harvesting port at the fourth time node;

[0105] A fourth offset coefficient is generated when the target grain is squeezed by the harvesting port under the influence of the first deviation data at the fourth time node.

[0106] In this embodiment, the adjustment module includes:

[0107] A setting module is configured to predict the displacement of the grain after it is subjected to wind forces in k different directions when the target grain is detected to have the first deviation data, wherein the wind forces in the k different directions converge at the target grain position and the angle of the wind force in each direction is the same. Where r is the angle value of the wind in each direction, the wind direction corresponding to the first deviation coefficient and the second deviation coefficient of the grain are compared to obtain the wind direction difference u;

[0108] Compare the wind direction difference with the difference between the first deviation coefficient and the second offset coefficient, obtain the influence relationship of the wind direction difference u on the offset coefficient according to the size of the wind direction difference, input the influence relationship into the second offset coefficient to obtain the possible numerical range of the third offset coefficient, and the influence relationship includes different linear relationship data between the wind direction difference u and the offset coefficient when it takes different non-special values ​​and the fixed value corresponding to the offset coefficient when it is a special value.

[0109] A position locking module is used to obtain an extrusion model of the target grain being squeezed by the harvesting port when the grain harvester detects that the harvesting port of the grain harvester touches the target grain when the grain harvester reaches the target grain position. The extrusion model is generated after the target grain is squeezed by the harvesting port; the second deviation data of the target grain being squeezed by the harvesting port under the condition of the first deviation data is entered, and the fourth offset coefficient is obtained by making changes based on the extrusion model within the possible numerical range of the third offset coefficient of the grain.

[0110] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0111] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A smart agriculture platform based on big data, characterized by: include: photographing farmland images, performing feature analysis on the farmland images, and detecting growth feature data of grains in the farmland images; detecting a growth trend of the grain based on the growth characteristic data of the grain, analyzing a deviation of the grain under the growth trend, analyzing a loss caused by the grain harvester contacting the grain at different travel angles based on the deviation, and recording a travel angle corresponding to a minimum grain loss; The grain position is detected in real time, the travel route of the grain harvester is adjusted, and the grain harvesting process is completed.

2. The big data-based smart agriculture platform according to claim 1, characterized in that: The detecting the growth trend of the grain based on the growth characteristic data of the grain and analyzing the deviation of the growth of the grain under the growth trend includes: Get the average growth height data of the grains in the farmland, set the drone at a height above the ground The device flies in a preset direction at a height of times the average growth height to capture images of the farmland, wherein is the preset minimum flight altitude magnification value, Establish a spatial rectangular coordinate system with the center of the farmland block as the coordinate origin, the UAV flight direction extending through the coordinate origin as the Y axis, the X axis passing through the coordinate origin on the plane where the farmland block is located and perpendicular to the Y axis as the X axis, and the Z axis passing through the coordinate origin and perpendicular to the X and Y axes as the Z axis, with the coordinate origin as (0, 0). The UAV is used to capture farmland images; The coordinates of the grains in the intercepted grain in the rectangular coordinate system are (x1, y1, z1), (x2, y2, z2)...(x n ,y n , z n ), and obtain the distance value between each adjacent grain in turn.

3. The big data-based smart agriculture platform according to claim 2, characterized in that: The detecting the growth trend of the grain based on the growth characteristic data of the grain and analyzing the deviation of the growth of the grain under the growth trend further includes: Set four time nodes in chronological order, including: a first time node, the first time node being used to record whether an initial position of the grain is shifted after the grain is not affected by the wind; a second time node, the second time node being used to monitor the displacement of the grain after the grain is affected by wind; a third time node, the third time node being used to predict a possible displacement range of the grains when the grains are affected by wind forces in a direction different from the wind forces at the second time node, under the condition that the grains are affected by the wind forces at the second time node; The fourth time node is used to predict the displacement of grains under the influence of wind at the second time node and after being squeezed by the harvesting port of the grain harvester.

4. The big data-based smart agriculture platform according to claim 3, characterized in that: The detecting the growth trend of the grain based on the growth characteristic data of the grain and analyzing the deviation of the growth of the grain under the growth trend further includes: Get the first offset coefficient of the grain at the first time node Where z0 is the preset limit value of the height of the grain from the ground, L c is the distance between the grains, i is the sequence value of the grains in the cereal in descending order of z coordinate, 2≤i≤n, and δ is the preset influence coefficient; Obtaining first deviation data and second deviation data of the grain in the spatial rectangular coordinate system, wherein the first deviation data is generated when the grain is affected by wind in the current farmland and is offset from its original position, and the second deviation data is generated when the grain is touched by a harvesting port of a grain harvester; The first deviation data includes: the second offset coefficient of the grain at the second time node; a possible value range of a third offset coefficient of the grain at the third time node, the third offset coefficient of the grain being predicted based on the second offset coefficient; The second offset data includes: a third offset coefficient generated when the target grain is squeezed by the harvesting port at the fourth time node; A fourth offset coefficient is generated when the target grain is squeezed by the harvesting port under the influence of the first deviation data at the fourth time node.

5. The big data-based smart agriculture platform according to claim 4, characterized in that: The possible numerical range of the third offset coefficient of the grain at the third time node includes: When it is detected that the target grain has the first deviation data, the deviation of the grain caused by the wind from k different directions is predicted, wherein the wind from the k different directions converges at the position of the target grain, and the angle of the wind from each direction is the same. Where r is the angle value of the wind in each direction, the wind direction corresponding to the first deviation coefficient and the second deviation coefficient of the grain are compared to obtain the wind direction difference u; Compare the wind direction difference with the difference between the first deviation coefficient and the second offset coefficient, obtain the influence relationship of the wind direction difference u on the offset coefficient according to the size of the wind direction difference, input the influence relationship into the second offset coefficient to obtain the possible numerical range of the third offset coefficient, and the influence relationship includes different linear relationship data between the wind direction difference u and the offset coefficient when it takes different non-special values ​​and the fixed value corresponding to the offset coefficient when it is a special value.

6. The smart agriculture platform based on big data according to claim 4, characterized in that: The fourth offset coefficient generated when the target grain is squeezed by the harvesting port under the influence of the first deviation data at the fourth time node includes: When the grain harvester reaches the target grain position and detects that the harvesting opening of the grain harvester touches the target grain, a compression model of the target grain being squeezed by the harvesting opening is obtained, wherein the compression model is generated after the target grain is squeezed by the harvesting opening; The second deviation data of the target grain being squeezed by the harvesting port under the condition of the first deviation data is entered, and the fourth offset coefficient is obtained by making changes based on the squeezing model within the possible numerical range of the third offset coefficient of the grain.

7. A smart agriculture system based on big data, characterized by: include: A data acquisition module, the data acquisition module is used to capture farmland images, perform feature analysis on the farmland images, and detect growth feature data of grains in the farmland images; a detection module, the detection module being configured to detect a growth trend of the grain based on the growth characteristic data of the grain, analyze a deviation of the grain growth under the growth trend, analyze a loss caused by the grain harvester contacting the grain at different travel angles based on the deviation, and record a travel angle corresponding to a minimum grain loss; The regulating module is used to detect the position of grains in real time, adjust the travel route of the grain harvester, and complete the grain harvesting process.

8. The big data-based smart agriculture system according to claim 7, characterized in that: The detection module comprises: The growth trend detection module is used to obtain the average growth height data of the grains in the farmland, and set the drone to The device flies in a preset direction at a height of times the average growth height to capture images of the farmland, wherein is the preset minimum flight altitude magnification value, A spatial rectangular coordinate system is established with the center of the farmland block as the coordinate origin, the flight direction of the drone extending through the coordinate origin as the Y axis, the plane of the farmland block perpendicular to the Y axis through the coordinate origin as the X axis, and the plane of the farmland block perpendicular to the X and Y axes through the coordinate origin as the Z axis. The coordinate origin is (0, 0). The drone is used to shoot farmland images; the coordinates of the grains in the grain in the spatial rectangular coordinate system are (x1, y1, z1), (x2, y2, z2)... (x n ,y n , z n ), and obtain the distance value between each adjacent grain in turn; An offset detection module is used to obtain first deviation data and second deviation data of the grain in the spatial rectangular coordinate system, wherein the first deviation data is generated after the grain is deflected by wind in the current farmland, and the second deviation data is generated after the grain is touched by the harvesting port of the grain harvester.

9. The big data-based smart agriculture system according to claim 8, characterized in that: The offset detection module includes: The first offset module is used to sequentially set four time nodes arranged in chronological order, including: a first time node, the first time node is used to record whether the initial position of the grain is offset after the grain is not affected by the wind; a second time node, the second time node is used to monitor the offset of the grain after the grain is affected by the wind; a third time node, the third time node is used to predict the possible offset range of the grain after the grain is affected by the wind at the second time node and the wind is affected by wind in a direction different from the wind at the second time node; a fourth time node, the fourth time node is used to predict the offset of the grain after the grain is affected by the wind at the second time node and is squeezed by the harvesting port of the grain harvester; obtain the first offset coefficient of the grain at the first time node Where z0 is the preset limit value of the height of the grain from the ground, L c is the distance between the grains, i is the sequence value of the grains in the cereal in descending order of z coordinate, 2≤i≤n, and δ is the preset influence coefficient; A second offset module, which is used for the first deviation data, includes: the second offset coefficient of the grain at the second time node; The possible value range of the third offset coefficient of the grain at the third time node, The third shift coefficient is predicted based on the second shift coefficient; The second offset data includes: a third offset coefficient generated when the target grain is squeezed by the harvesting port at the fourth time node; A fourth offset coefficient is generated when the target grain is squeezed by the harvesting port under the influence of the first deviation data at the fourth time node.

10. The big data-based smart agriculture system according to claim 9, characterized in that: The adjustment module includes: A setting module is configured to predict the displacement of the grain after it is subjected to wind forces in k different directions when the target grain is detected to have the first deviation data, wherein the wind forces in the k different directions converge at the target grain position and the angle of the wind force in each direction is the same. Where r is the angle value of the wind in each direction, the wind direction corresponding to the first deviation coefficient and the second deviation coefficient of the grain are compared to obtain the wind direction difference u; Comparing the wind direction difference with the difference between the first deviation coefficient and the second offset coefficient, obtaining an influence relationship of the wind direction difference u on the offset coefficient according to the magnitude of the wind direction difference, inputting the influence relationship into the second offset coefficient to obtain a possible value range of the third offset coefficient, the influence relationship including different linear relationship data between the wind direction difference u and the offset coefficient when the wind direction difference u takes different non-special values, and a fixed value corresponding to the offset coefficient when the wind direction difference u takes a special value; A position locking module is used to obtain an extrusion model of the target grain being squeezed by the harvesting port when the grain harvester detects that the harvesting port of the grain harvester touches the target grain when the grain harvester reaches the target grain position. The extrusion model is generated after the target grain is squeezed by the harvesting port; the second deviation data of the target grain being squeezed by the harvesting port under the condition of the first deviation data is entered, and the fourth offset coefficient is obtained by making changes based on the extrusion model within the possible numerical range of the third offset coefficient of the grain.

Images