A method and system for agricultural machinery deployment decision-making based on farmland suitability analysis

Abstract

The present invention discloses a method and system for agricultural machinery calling decision-making based on farmland suitability analysis, and the method includes data collection, data preprocessing, farmland clustering processing and agricultural machinery calling decision-making. The present invention belongs to the field of agricultural technology, and specifically refers to a method and system for agricultural machinery calling decision-making based on farmland suitability analysis. This scheme introduces clustering into agricultural machinery calling decision-making, and based on farmland suitability data, dynamically optimizes the shortest path from each farmland to the agricultural machinery service center to ensure that the farmland allocation and the location of the agricultural machinery service center are continuously adjusted and optimized; introduces a state update and waiting mechanism to increase the convergence speed of the generation scheme; improves allocation efficiency and accuracy; designs a new evaluation index based on the silhouette coefficient for evaluating and judging the results of farmland clustering, which can realize rapid evaluation of clustering effects and select the optimal number of clusters; the evaluation index comprehensively reflects the overall clustering effect, ensures the global optimization of the farmland clustering results, and makes the decision of agricultural machinery calling optimal.

Description

Technical Field

[0001] The present invention relates to the field of agricultural technology, and in particular to an agricultural machinery deployment decision method and system based on farmland suitability analysis. Background Art

[0002] Agricultural machinery deployment decision-making methods refer to the use and scheduling of agricultural machinery in agricultural production, which are optimized and decided by various technical means and algorithms; these methods usually combine data analysis, decision support systems and real-time information processing technology, aiming to improve the utilization efficiency of agricultural machinery and the overall benefits of agricultural production. However, general agricultural machinery deployment decision-making methods have the problems of ignoring the suitability of farmland, low resource utilization efficiency, and high service costs, resulting in poor accuracy of farmland allocation and waste of resources; general agricultural machinery deployment decision-making methods have the problems of being unable to accurately evaluate decision-making plans and being unable to achieve global optimization. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an agricultural machinery calling decision method and system based on farmland suitability analysis. In view of the fact that general agricultural machinery calling decision methods ignore farmland suitability, have low resource utilization efficiency, and have high service costs, resulting in poor accuracy of farmland allocation and waste of resources, this scheme introduces clustering into agricultural machinery calling decision-making. Based on farmland suitability data, by dynamically optimizing the shortest path from each farmland to the agricultural machinery service center, it is ensured that the farmland allocation and the location of the agricultural machinery service center are continuously adjusted and optimized to ensure the adaptability of farmland allocation; a state update and waiting mechanism is introduced to ensure the smooth progress of the calling decision scheme and increase the convergence speed of the generated scheme; the allocation efficiency and accuracy are improved; in view of the fact that general agricultural machinery calling decision methods cannot accurately evaluate the decision scheme and the decision scheme cannot achieve global optimization, this scheme designs a new evaluation index based on the silhouette coefficient for evaluating and judging the farmland clustering results, which can realize rapid evaluation of the clustering effect and select the optimal number of clusters; the evaluation index comprehensively reflects the overall clustering effect, ensures the global optimization of the farmland clustering results, and makes the decision of agricultural machinery calling optimal.

[0004] The technical solution adopted by the present invention is as follows: The present invention provides an agricultural machinery call decision method based on farmland suitability analysis, the method comprising the following steps:

[0005] Step S1: data collection;

[0006] Step S2: data preprocessing;

[0007] Step S3: farmland clustering processing;

[0008] Step S4: Agricultural machinery call decision.

[0009] Furthermore, in step S1, the data collection is to collect farmland suitability data; the farmland suitability data includes soil type, climate data, crop demand data and geospatial data; the soil type includes soil type, soil pH value, organic matter content and soil moisture; the climate data includes precipitation, temperature and light duration; the crop demand data includes crop type, growth stage, fertilization and irrigation requirements; the geospatial data includes farmland location, terrain data, farmland area and shape.

[0010] Furthermore, in step S2, the data preprocessing is to perform data cleaning, data conversion and standardization on the collected farmland suitability data; the data cleaning is to perform missing value, duplicate value and outlier processing on the collected farmland suitability data; the data conversion is to convert the farmland suitability data into a vector form; and the standardization is to perform standardization on the farmland suitability data based on the maximum and minimum normalization method.

[0011] Furthermore, in step S3, the farmland clustering process specifically includes the following steps:

[0012] Step S31: Initialization; Initialize the state of each farmland to the inactive state SR(i)=0, and prepare a variable FR(i)=0 for recording the activation order; Generate propagation from each farmland m, and set the initial state to active SR(m)=2;

[0013] Step S32: cluster allocation; dynamically optimize the shortest travel time path Pmn from each farmland m to the agricultural machinery service center n based on the propagation process; allocate the farmland to the corresponding agricultural machinery service center Ki; the propagation process specifically includes:

[0014] Step S321: setting the starting point to the farmland and the end point to the agricultural machinery service center; the agricultural machinery service center is regarded as the center point of the farmland;

[0015] Step S322: propagation; for each activated farmland i, based on the propagation speed and direction, calculate the propagation radius and propagation time to the adjacent farmland j; if the adjacent farmland is in an inactive state, i.e. SR(j)=0, activate farmland j and record the propagation source farmland, i.e. FR(j)=i; if the adjacent farmland is in a waiting state, i.e. SR(j)=1, wait until it is feasible and then continue propagation;

[0016] Step S323: Update the farmland status; if all the neighboring farmlands of farmland i have been activated, update the farmland i status to the completed status, i.e., SR(i)=3; for the farmland that encounters obstacles, keep waiting until the obstacle disappears, and then continue to propagate;

[0017] Step S324: Path backtracking; when the end farmland n is activated, i.e., SR(n) = 2, stop the propagation process; starting from the end farmland n, gradually backtrack to the starting farmland m using the recorded propagation source farmland FR(i) to obtain the optimal path Pmn; record the total length L of the path Pmn;

[0018] Step S33: Update the agricultural machinery service center; calculate the average distance from each farmland to the agricultural machinery service center as the candidate agricultural machinery service center ; Mark all the farmlands within the radius R as adjacent to the candidate agricultural machinery service center; traverse each candidate agricultural machinery service center and calculate the total distance F from all the farmlands in the cluster to the candidate agricultural machinery service center ; Select the candidate agricultural machinery service center with the lowest F value as the new agricultural machinery service center for the next iteration;

[0019] Step S34: Iteration; Re - allocate the farmlands based on the new agricultural machinery service center, and then return to S33 until the agricultural machinery service center no longer changes; Continuously update the position of the agricultural machinery service center; When the agricultural machinery service center no longer changes or the spatial distance between the agricultural machinery service centers in adjacent iterations meets the convergence condition; At this time it is the final position of the agricultural machinery service center;

[0020] Step S35: Global traversal; If n < N, then k = k + 1 and return to step S33; Otherwise, obtain the current farmland clustering result; that is, obtain the allocation of farmlands to agricultural machinery service centers, forming clusters, representing different service areas; N is the number of farmlands;

[0021] Step S36: Evaluation; There is a pre - set evaluation threshold. If the evaluation value of the current farmland clustering result is higher than the evaluation threshold, the farmland clustering is completed; Otherwise, adjust the propagation speed, R, and the initial number of agricultural machinery service centers, and return to step S31; The formula for calculating the evaluation value of the farmland clustering result is as follows:

[0022] ;

[0023] where O is the evaluation value of the current farmland clustering result; is the maximum membership degree of the i - th farmland to all agricultural machinery service centers; , and are the membership degrees of the i - th farmland belonging to the 1st, 2nd, and k - th agricultural machinery service centers respectively; is the second - largest membership degree of the i - th farmland to all agricultural machinery service centers.

[0024] Furthermore, in step S4, the agricultural machinery call decision is based on the final farmland clustering result; Call agricultural machinery for operations on the farmlands belonging to the same cluster.

[0025] The present invention provides an agricultural machinery calling decision system based on farmland suitability analysis, comprising a data acquisition module, a data preprocessing module, a farmland clustering processing module and an agricultural machinery calling decision module;

[0026] The data acquisition module collects farmland suitability data and sends the data to the data preprocessing module;

[0027] The data preprocessing module performs data cleaning, data conversion and data standardization on the collected data, and sends the data to the farmland clustering processing module;

[0028] The farmland clustering processing module dynamically optimizes the shortest path from each farmland to the agricultural machinery service center based on the farmland suitability data, introduces a state update and waiting mechanism, designs a new evaluation index based on the silhouette coefficient, and is used for the evaluation of farmland clustering results, and finally realizes farmland clustering processing; and sends the data to the agricultural machinery call decision module;

[0029] The agricultural machinery calling decision module calls agricultural machinery to perform operations on the farmlands belonging to the same cluster based on the final farmland clustering result.

[0030] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0031] (1) In view of the problems that the general agricultural machinery call decision-making method ignores the suitability of farmland, has low resource utilization efficiency, and has high service costs, resulting in poor accuracy of farmland allocation and resource waste, this scheme introduces clustering into agricultural machinery call decision-making. Based on farmland suitability data, this scheme dynamically optimizes the shortest path from each farmland to the agricultural machinery service center to ensure that the farmland allocation and the location of the agricultural machinery service center are constantly adjusted and optimized to ensure the adaptability of farmland allocation. It also introduces a status update and waiting mechanism to ensure the smooth implementation of the call decision plan and increase the convergence speed of the generated plan. It also improves the allocation efficiency and accuracy.

[0032] (2) In view of the problems that general agricultural machinery deployment decision-making methods cannot accurately evaluate decision-making plans and cannot achieve global optimization, this scheme designs a new evaluation index based on the silhouette coefficient to evaluate and determine the farmland clustering results. It can quickly evaluate the clustering effect and select the optimal number of clusters. The evaluation index comprehensively reflects the overall clustering effect, ensures the global optimization of the farmland clustering results, and makes the decision of agricultural machinery deployment optimal. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A schematic diagram of a flow chart of an agricultural machinery deployment decision method based on farmland suitability analysis provided by the present invention;

[0034] Figure 2 A schematic diagram of an agricultural machinery deployment decision system based on farmland suitability analysis provided by the present invention;

[0035] Figure 3 It is a schematic diagram of the process of step S3.

[0036] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0038] In the description of the present invention, it is necessary to understand that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred system or element must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention.

[0039] Example 1, see Figure 1 The present invention provides an agricultural machinery deployment decision method based on farmland suitability analysis, the method comprising the following steps:

[0040] Step S1: data collection, collecting farmland suitability data;

[0041] Step S2: Data preprocessing, data cleaning, data conversion and data standardization of the collected data;

[0042] Step S3: farmland clustering processing, based on farmland suitability data, dynamically optimize the shortest path from each farmland to the agricultural machinery service center, introduce a state update and waiting mechanism, design a new evaluation index based on the silhouette coefficient, which is used to evaluate the farmland clustering results, and finally realize farmland clustering processing;

[0043] Step S4: Agricultural machinery deployment decision, based on the final farmland clustering result; deploying agricultural machinery to operate on farmlands belonging to the same cluster.

[0044] Example 2, see Figure 1This embodiment is based on the above embodiment. In step S1, the farmland suitability data includes soil type, climate data, crop requirement data and geospatial data; soil type includes soil type, soil pH value, organic matter content and soil moisture; climate data includes precipitation, temperature and sunshine duration; crop requirement data includes crop type, growth stage, fertilization and irrigation requirements; geospatial data includes farmland location, terrain data, farmland area and shape.

[0045] Example 3, see Figure 1 This embodiment is based on the above embodiment. In step S2, data cleaning is to process missing values, duplicate values ​​and outliers of the collected farmland suitability data; data conversion is to convert the farmland suitability data into vector form; and standardization is to standardize the farmland suitability data based on the maximum and minimum normalization method.

[0046] Example 4, see Figure 1 and Figure 3 This embodiment is based on the above embodiment. In step S3, the farmland clustering process specifically includes the following steps:

[0047] Step S31: Initialization; Initialize the state of each farmland to the inactive state SR(i)=0, and prepare a variable FR(i)=0 for recording the activation order; Generate propagation from each farmland m, and set the initial state to active SR(m)=2;

[0048] Step S32: cluster allocation; dynamically optimize the shortest travel time path Pmn from each farmland m to the agricultural machinery service center n based on the propagation process; allocate the farmland to the corresponding agricultural machinery service center Ki; the propagation process specifically includes:

[0049] Step S321: setting the starting point to the farmland and the end point to the agricultural machinery service center; the agricultural machinery service center is regarded as the center point of the farmland;

[0050] Step S322: propagation; for each activated farmland i, based on the propagation speed and direction, calculate the propagation radius and propagation time to the adjacent farmland j; if the adjacent farmland is in an inactive state, i.e. SR(j)=0, activate farmland j and record the propagation source farmland, i.e. FR(j)=i; if the adjacent farmland is in a waiting state, i.e. SR(j)=1, wait until it is feasible and then continue propagation;

[0051] Step S323: Update the farmland status; if all the neighboring farmlands of farmland i have been activated, update the farmland i status to the completed status, i.e., SR(i)=3; for the farmland that encounters obstacles, keep waiting until the obstacle disappears, and then continue to propagate;

[0052] Step S324: Path backtracking; When the end farmland n is activated, i.e., SR(n) = 2, stop the propagation process; Starting from the end farmland n, gradually backtrack to the starting farmland m using the recorded propagation source farmland FR(i) to obtain the optimal path Pmn; Record the total length L of the path Pmn;

[0053] Step S33: Update the agricultural machinery service center; Calculate the average distance from each farmland to the agricultural machinery service center as the candidate agricultural machinery service center ; Mark all the farmlands within the radius R as adjacent to the candidate agricultural machinery service center; Traverse each candidate agricultural machinery service center and calculate the total distance F from all the farmlands in the cluster to the candidate agricultural machinery service center ; Select the candidate agricultural machinery service center with the lowest F value as the new agricultural machinery service center for the next iteration;

[0054] Step S34: Iteration; Reallocate the farmlands based on the new agricultural machinery service center, and then return to S33 until the agricultural machinery service center no longer changes; Continuously update the position of the agricultural machinery service center; When the agricultural machinery service center no longer changes or the spatial distance between the agricultural machinery service centers in adjacent iterations meets the convergence condition; At this time it is the final position of the agricultural machinery service center;

[0055] Step S35: Global traversal; If n < N, then k = k + 1 and return to step S33; Otherwise, obtain the farmland clustering result at this time; That is, obtain the allocation of farmlands to agricultural machinery service centers to form clusters, representing different service areas; N is the number of farmlands;

[0056] Step S36: Evaluation.

[0057] By performing the above operations, for the problems of the general agricultural machinery call decision method, such as ignoring farmland suitability, too low resource utilization efficiency, too high service cost, resulting in poor accuracy of farmland allocation and resource waste, this solution introduces clustering into the agricultural machinery call decision. Based on the farmland suitability data, by dynamically optimizing the shortest path from each farmland to the agricultural machinery service center, it ensures that the farmland allocation and the position of the agricultural machinery service center are continuously adjusted and optimized, ensuring the self - adaptability of farmland allocation; Introduce a state update and waiting mechanism to ensure the smooth progress of the call decision scheme and increase the convergence speed of the generated scheme; Improve the allocation efficiency and accuracy.

[0058] Example Five, refer to Figure 3 , based on the above - mentioned example, in step S36, there is a preset evaluation threshold. If the evaluation value of the farmland clustering result at this time is higher than the evaluation threshold, the farmland clustering is completed; Otherwise, adjust the propagation speed, R, and the initial number of agricultural machinery service centers, and return to step S31; The formula for calculating the evaluation value of the farmland clustering result is as follows:

[0059] ;

[0060] Where, O is the evaluation value of the current farmland clustering result; is the maximum membership degree of the i-th farmland to all agricultural machinery service centers; , and are the membership degrees of the i-th farmland to the first, second, and k-th agricultural machinery service centers respectively; It is the second largest membership degree of the i-th farmland to all agricultural machinery service centers.

[0061] By performing the above operations, in view of the problems that general agricultural machinery call decision methods cannot accurately evaluate decision plans and decision plans cannot achieve global optimization, this scheme designs a new evaluation index based on the silhouette coefficient, which is used to evaluate and determine the farmland clustering results. It can quickly evaluate the clustering effect and select the optimal number of clusters. The evaluation index comprehensively reflects the overall clustering effect, ensures the global optimization of the farmland clustering results, and makes the decision of agricultural machinery call optimal.

[0062] Example 6, see Figure 2 , this embodiment is based on the above embodiment, and the present invention provides an agricultural machinery calling decision system based on farmland suitability analysis, including a data acquisition module, a data preprocessing module, a farmland clustering processing module and an agricultural machinery calling decision module;

[0063] The data acquisition module collects farmland suitability data and sends the data to the data preprocessing module;

[0064] The data preprocessing module performs data cleaning, data conversion and data standardization on the collected data, and sends the data to the farmland clustering processing module;

[0065] The farmland clustering processing module dynamically optimizes the shortest path from each farmland to the agricultural machinery service center based on the farmland suitability data, introduces a state update and waiting mechanism, designs a new evaluation index based on the silhouette coefficient, and is used for the evaluation of farmland clustering results, and finally realizes farmland clustering processing; and sends the data to the agricultural machinery call decision module;

[0066] The agricultural machinery calling decision module calls agricultural machinery to perform operations on the farmlands belonging to the same cluster based on the final farmland clustering result.

[0067] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0068] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0069] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A method for agricultural machinery deployment decision-making based on farmland suitability analysis, characterized by: The method includes the following steps: Step S1: Data collection; Step S2: Data preprocessing; Step S3: Farmland clustering processing. Based on farmland suitability data, dynamically optimize the shortest path from each farmland to the agricultural machinery service center, introduce a state update and waiting mechanism, design a new evaluation index based on the silhouette coefficient for evaluating the farmland clustering results, and finally achieve farmland clustering processing; Step S4: Agricultural machinery call decision; In step S3, the farmland clustering processing specifically includes the following steps: Step S31: Initialization; Initialize the state of each farmland as the unactivated state SR(i)=0, and prepare a variable FR(i)=0 for recording the activation order; Generate propagation from each farmland m, and set the initial state as activated SR(m)=2; Step S32: Clustering assignment; Dynamically optimize the shortest travel time path Pmn from each farmland m to the agricultural machinery service center n based on the propagation process; Assign the farmland to the corresponding agricultural machinery service center Ki; The propagation process specifically includes: Step S321: Set the starting point as the farmland and the ending point as the agricultural machinery service center; The agricultural machinery service center is regarded as the center point of the farmland here; Step S322: Propagation; For each activated farmland i, calculate the propagation radius and propagation time to the adjacent farmland j based on the propagation speed and direction; If the adjacent farmland is in the unactivated state, i.e., SR(j)=0, then activate the farmland j and record the source farmland of the propagation, i.e., FR(j)=i; If the adjacent farmland is in the waiting state, i.e., SR(j)=1, then wait until it is feasible and then continue the propagation; Step S323: Update the farmland state; If all adjacent farmlands of the farmland i have been activated, then update the state of the farmland i to the completed state, i.e., SR(i)=3; For the farmland encountering obstacles, maintain the waiting state until the obstacle state disappears and then continue the propagation; Step S324: Path backtracking; When the end farmland n is activated, i.e., SR(n)=2, stop the propagation process; Starting from the end farmland n, gradually backtrack to the starting farmland m using the recorded source farmland FR(i) of the propagation to obtain the optimal path Pmn; Record the total length L of the path Pmn Step S33: Update the agricultural machinery service center; calculate the average distance from each farmland to the agricultural machinery service center as the candidate agricultural machinery service center ;Will All farmlands within radius R are marked as adjacent candidate agricultural machinery service centers; traverse each candidate agricultural machinery service center and calculate the distance from all farmlands in the cluster to the candidate agricultural machinery service center. The total distance F of the candidate agricultural machinery service center is selected with the lowest F value as the new agricultural machinery service center for the next iteration; Step S34: iteration; reallocate farmland based on the new agricultural machinery service center, and then return to S33 until the agricultural machinery service center no longer changes; continuously update the location of the agricultural machinery service center; when the agricultural machinery service center no longer changes or the spatial distance between the agricultural machinery service centers in adjacent iterations meets the convergence condition; at this time It is the ultimate farm machinery service center location; Step S35: Global traversal; If n<N, then k=k+1 and return to step S33; Otherwise, obtain the farmland clustering result at this time; That is, obtain the farmland assigned to the agricultural machinery service center to form a cluster, representing different service areas; Step S36: Evaluation; There is a preset evaluation threshold. If the evaluation value of the farmland clustering result at this time is higher than the evaluation threshold, then the farmland clustering is completed; Otherwise, adjust the propagation speed, radius R, and the initial number of agricultural machinery service centers, and return to step S31; The formula for calculating the evaluation value of the farmland clustering result is as follows: ； Where O is the evaluation value of the current farmland clustering result; N is the number of farmlands; is the maximum membership degree of the i-th farmland to all agricultural machinery service centers; , and are the membership degrees of the i-th farmland to the first, second, and k-th agricultural machinery service centers respectively; It is the second largest membership degree of the i-th farmland to all agricultural machinery service centers.

2. The agricultural machinery deployment decision method based on farmland suitability analysis according to claim 1 is characterized by: In step S1, the data collection is to collect farmland suitability data; the farmland suitability data includes soil type, climate data, crop demand data and geospatial data; the soil type includes soil type, soil pH value, organic matter content and soil moisture; the climate data includes precipitation, temperature and light duration; the crop demand data includes crop type, growth stage, fertilization and irrigation requirements; the geospatial data includes farmland location, terrain data, farmland area and shape.

3. The agricultural machinery deployment decision method based on farmland suitability analysis according to claim 1 is characterized by: In step S4, the agricultural machinery calling decision is based on the final farmland clustering result; agricultural machinery is called to perform operations on farmlands belonging to the same cluster.

4. The agricultural machinery deployment decision method based on farmland suitability analysis according to claim 1 is characterized by: In step S2, the data preprocessing is to perform data cleaning, data conversion and standardization on the collected farmland suitability data; the data cleaning is to process missing values, duplicate values ​​and outliers on the collected farmland suitability data; the data conversion is to convert the farmland suitability data into a vector form; the standardization is to standardize the farmland suitability data based on the maximum and minimum normalization method.

5. An agricultural machinery calling decision system based on farmland suitability analysis, used to implement an agricultural machinery calling decision method based on farmland suitability analysis as described in any one of claims 1 to 4, characterized in that: It includes data collection module, data preprocessing module, farmland clustering processing module and agricultural machinery calling decision module; The data acquisition module collects farmland suitability data and sends the data to the data preprocessing module; The data preprocessing module performs data cleaning, data conversion and data standardization on the collected data, and sends the data to the farmland clustering processing module; The farmland clustering processing module dynamically optimizes the shortest path from each farmland to the agricultural machinery service center based on farmland suitability data, introduces a state update and waiting mechanism, and designs a new evaluation index based on the silhouette coefficient for evaluating farmland clustering results, thereby finally realizing farmland clustering processing; And send the data to the agricultural machinery calling decision module; The agricultural machinery calling decision module calls agricultural machinery to perform operations on the farmlands belonging to the same cluster based on the final farmland clustering result.

Images