Universe space planting data management method and system

Abstract

The invention discloses a global space planting data management method and system, and belongs to the technical field of planting. Planting data in a planting area is collected, a deep learning algorithm is adopted to analyze data in a planting database, an analysis result is determined, and a management report is generated according to the analysis result; comprehensive management and scientific utilization of planting data can be realized, agricultural production decisions are supported, and planting efficiency and benefits are improved.

Description

Technical Field

[0001] The present invention belongs to the field of planting technology, and in particular relates to a global spatial planting data management method and system. Background Art

[0002] Agricultural planting data refers to all kinds of information related to crop planting in the agricultural production process. These data are crucial for agricultural production management, policy formulation, market analysis and scientific research. With the acceleration of my country's agricultural modernization process, the importance of agricultural planting data management has become increasingly prominent. However, the planting data management methods in the existing technology have the following problems: data collection is not comprehensive, and it is difficult to achieve full coverage of the entire space; data processing and analysis methods are single and cannot provide effective support for planting decisions; planting resources are not allocated reasonably, resulting in unstable crop yields and quality. Summary of the invention

[0003] The present invention provides a global spatial planting data management method and system to solve the technical problems existing in the prior art.

[0004] In one aspect, the present invention provides a global spatial planting data management method, comprising:

[0005] For each planting area, the planting data in the planting area is collected using a preset data sampling frequency; wherein the planting data includes environmental parameters, crop growth status and nutrient solution usage;

[0006] Classifying and storing the planting data in the planting area to obtain a planting database consisting of the planting data at different time points;

[0007] Using a deep learning algorithm to analyze data in a planting database, determine analysis results, and generate a management report based on the analysis results;

[0008] The planting database, the analysis results and the management report are associated and presented to farmers through a visual interface.

[0009] Furthermore, for each planting area, the planting data in the planting area is collected using a preset data sampling frequency, including:

[0010] Obtaining a preset data sampling frequency input through human-computer interaction or pre-stored in a database;

[0011] Based on the preset data sampling frequency, the environmental parameters corresponding to the planting area are collected through the Internet of Things sensor to obtain the environmental parameters;

[0012] Based on the preset data sampling frequency, the crop growth images corresponding to the planting area are collected by the Internet of Things sensor to obtain the crop growth status;

[0013] Collect the nutrient solution usage information input by farmers through human-computer interaction;

[0014] The planting data in the planting area is obtained according to the environmental parameters, crop growth status and nutrient solution usage.

[0015] Furthermore, the planting data in the planting area are classified and stored to obtain a planting database consisting of planting data at different time points, including:

[0016] Creating a first storage block, a second storage block, and a third storage block;

[0017] For the same planting area, the environmental parameters are stored in the first storage block in the order of sampling time;

[0018] For the same planting area, the crop growth status is stored in the second storage block in the order of sampling time;

[0019] For the same planting area, the nutrient solution usage is stored in the third storage block;

[0020] A planting database is acquired according to the first storage block, the second storage block and the third storage block.

[0021] Furthermore, a deep learning algorithm is used to analyze the data in the planting database, determine the analysis results, and generate a management report based on the analysis results, including:

[0022] Using a first preset deep learning algorithm to analyze environmental parameters in a planting database to determine a planting environment state;

[0023] A second preset deep learning algorithm is used to analyze the growth status of crops in the planting database to determine the growth cycle of the crops in the planting area;

[0024] A third preset deep learning algorithm is used to jointly analyze the usage of nutrient solution in the planting database, the state of the planting environment, and the growth cycle of the crops in the planting area to determine the growth status of the crops;

[0025] A management report is generated according to the planting environment status, the growth cycle of the crops in the planting area, and the growth status of the crops.

[0026] Furthermore, the first preset deep learning algorithm is set to the BP algorithm, the second preset deep learning algorithm is set to the CNN algorithm, and the third preset deep learning algorithm is set to the BP algorithm.

[0027] Furthermore, the first preset deep learning algorithm, the second preset deep learning algorithm, and the third preset deep learning algorithm are preset in the same manner, and all include:

[0028] Initializing the algorithm parameters of the preset deep learning algorithm multiple times to obtain multiple algorithm parameter codes;

[0029] Using the loss function to evaluate each algorithm parameter encoding to obtain the loss function value corresponding to each algorithm parameter encoding;

[0030] A target algorithm parameter code for information interaction is randomly matched to each algorithm parameter code, and the algorithm parameter code is searched in an unknown area along a sinusoidal search path to obtain the algorithm parameter code after a rough search;

[0031] Performing historical optimal following and current optimal following on the algorithm parameter coding after the rough search, performing restricted search on the algorithm parameter coding after the rough search along the optimal path, and obtaining the algorithm parameter coding after the fine search;

[0032] Perform optimal information interaction on the algorithm parameter encoding after fine search, perform nonlinear search between the current position and the current optimal position, and obtain the algorithm parameter encoding after balanced search;

[0033] Perform random weighted information interaction on the algorithm parameter encoding after the balanced search, search at the global position, and use a greedy algorithm to control the search to obtain the algorithm parameter encoding after the global search;

[0034] Determine whether the end condition is met. If so, determine the final preset deep learning algorithm based on the algorithm parameter encoding after the global search, otherwise return to the rough search step.

[0035] Furthermore, the loss function is set as a supervised loss function.

[0036] Further, judging whether the termination condition is met includes:

[0037] Determine whether the current number of training times is greater than the maximum number of training times. If so, determine that the iteration end condition is met; otherwise, determine that the iteration end condition is not met.

[0038] Furthermore, according to the algorithm parameter encoding after the global search, the final preset deep learning algorithm is determined, including:

[0039] Re-obtain the loss function value corresponding to the algorithm parameter code after the global search, and obtain the algorithm parameter code after the global search with the smallest loss function value to obtain the final algorithm parameter code;

[0040] The final algorithm parameter encoding is applied to the deep learning algorithm to be preset to obtain the final preset deep learning algorithm.

[0041] On the other hand, the present invention provides a global spatial planting data management system, including: a data acquisition module, a data storage module, a data processing module and a data display module;

[0042] The data acquisition module is used to collect planting data in each planting area using a preset data sampling frequency; wherein the planting data includes environmental parameters, crop growth status and nutrient solution usage;

[0043] The data storage module is used to classify and store the planting data in the planting area to obtain a planting database composed of planting data at different time points;

[0044] The data processing module is used to analyze the data in the planting database using a deep learning algorithm, determine the analysis results, and generate a management report based on the analysis results;

[0045] The data display module is used to associate the planting database, the analysis results and the management report, and display them to farmers through a visual interface.

[0046] The present invention provides a global spatial planting data management method and system, which collects planting data in the planting area, uses a deep learning algorithm to analyze the data in the planting database, determines the analysis results, and generates a management report based on the analysis results. It can realize the comprehensive management and scientific use of planting data, support agricultural production decision-making, and improve planting efficiency and benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0048] Figure 1 A flowchart of a global spatial planting data management method provided by the present invention.

[0049] Figure 2 A structural schematic diagram of a global spatial planting data management system provided by the present invention.

[0050] Among them, 1-data acquisition module, 2-data storage module, 3-data processing module, 4-data display module.

[0051] The above drawings have shown clear embodiments of the present invention, which will be described in more detail below. These drawings and text descriptions are not intended to limit the scope of the present invention in any way, but to illustrate the concept of the present invention for those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0052] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0053] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0054] like Figure 1 As shown, the present invention provides a global spatial planting data management method, comprising:

[0055] S1. For each planting area, the planting data in the planting area is collected using a preset data sampling frequency; wherein the planting data includes environmental parameters, crop growth status and nutrient solution usage;

[0056] The preset data sampling frequency can be a frequency input by human-computer interaction or a pre-stored frequency, which can be set according to actual needs. A data sampling frequency can be set for each type of data, or the same data sampling frequency can be set for all data.

[0057] It is worth noting that planting data may include not only environmental parameters, crop growth status and nutrient solution usage, but also other parameters, thereby realizing global spatial planting monitoring and analysis.

[0058] S2, classifying and storing the planting data in the planting area to obtain a planting database consisting of planting data at different time points;

[0059] By classifying and storing the planting data, it is not only easier to transfer the data, but also more convenient for farmers to view the data.

[0060] S3. Analyze the data in the planting database using a deep learning algorithm, determine the analysis results, and generate a management report based on the analysis results;

[0061] After being pre-set, the deep learning algorithm can analyze subsequent data according to pre-set rules, thereby achieving analysis and providing management decisions for farmers.

[0062] S4. Associating the planting database, the analysis results and the management report, and presenting them to farmers through a visual interface.

[0063] The global spatial planting data management method provided by the present invention can provide farmers with clearer planting conditions, allowing farmers to make timely adjustments.

[0064] In the embodiment of the present invention, for each planting area, the planting data in the planting area is collected using a preset data sampling frequency, including:

[0065] Obtaining a preset data sampling frequency input through human-computer interaction or pre-stored in a database;

[0066] Based on the preset data sampling frequency, the environmental parameters corresponding to the planting area are collected through the Internet of Things sensor to obtain the environmental parameters;

[0067] Optionally, environmental parameters may include temperature, humidity, carbon dioxide concentration, toxic gas concentration, oxygen concentration, light intensity and other data related to the environment, so that the environmental data can be analyzed to determine whether the crops are grown in a suitable environment.

[0068] Based on the preset data sampling frequency, the crop growth images corresponding to the planting area are collected by the Internet of Things sensor to obtain the crop growth status;

[0069] As different growth cycles come, the corresponding growth conditions of crops are also different. The growth cycle of crops can be determined by analyzing crop growth images.

[0070] Collect the nutrient solution usage information input by farmers through human-computer interaction;

[0071] The planting data in the planting area is obtained according to the environmental parameters, crop growth status and nutrient solution usage.

[0072] In an embodiment of the present invention, the planting data in the planting area is classified and stored to obtain a planting database consisting of planting data at different time points, including:

[0073] Creating a first storage block, a second storage block, and a third storage block;

[0074] For the same planting area, the environmental parameters are stored in the first storage block in the order of sampling time;

[0075] For the same planting area, the crop growth status is stored in the second storage block in the order of sampling time;

[0076] For the same planting area, the nutrient solution usage is stored in the third storage block;

[0077] A planting database is acquired according to the first storage block, the second storage block and the third storage block.

[0078] By classifying and storing the planting data, it is not only easier to transfer the data, but also more convenient for farmers to view the data.

[0079] In an embodiment of the present invention, a deep learning algorithm is used to analyze the data in the planting database, determine the analysis results, and generate a management report based on the analysis results, including:

[0080] Using a first preset deep learning algorithm to analyze environmental parameters in a planting database to determine a planting environment state;

[0081] In this embodiment, when analyzing the environmental parameters, the unique type code corresponding to the crop should be included, so that it can be analyzed whether the growth environment of the crop is suitable.

[0082] A second preset deep learning algorithm is used to analyze the growth status of crops in the planting database to determine the growth cycle of the crops in the planting area;

[0083] During the data collection process, the position of the sensor remains unchanged, so the approximate height of the crops can be analyzed to determine the growth cycle of the crops in the planting area, so as to subsequently analyze the growth of the crops.

[0084] A third preset deep learning algorithm is used to jointly analyze the usage of nutrient solution in the planting database, the state of the planting environment, and the growth cycle of the crops in the planting area to determine the growth status of the crops;

[0085] The growth conditions of crops can be excellent, good, average, or poor. During the preset process, the staff can set corresponding labels for learning, thereby achieving unmanned monitoring and management.

[0086] A management report is generated according to the planting environment status, the growth cycle of the crops in the planting area, and the growth status of the crops.

[0087] Optionally, suggestions corresponding to different crop growth conditions may be set, and then a management report may be generated according to a preset template based on the planting environment status, the growth cycle of the crops in the planting area, the crop growth conditions, and the suggestions.

[0088] In an embodiment of the present invention, the first preset deep learning algorithm is set to a BP (Back Propagation) algorithm, the second preset deep learning algorithm is set to a CNN (Convolutional Neural Network) algorithm, and the third preset deep learning algorithm is set to a BP algorithm.

[0089] It is worth noting that, in addition to the above algorithms, other algorithms can also be used for analysis to achieve monitoring.

[0090] In the embodiment of the present invention, the first preset deep learning algorithm, the second preset deep learning algorithm and the third preset deep learning algorithm are preset in the same manner and all include:

[0091] A1. Initialize the algorithm parameters of the preset deep learning algorithm multiple times to obtain multiple algorithm parameter codes;

[0092] For the first preset deep learning algorithm, the second preset deep learning algorithm and the third preset deep learning algorithm, each parameter dimension has corresponding upper and lower limits, and can be randomly initialized within the upper and lower limits to obtain an algorithm parameter code, thereby repeatedly obtaining multiple different algorithm parameter codes.

[0093] A2. Use the loss function to evaluate each algorithm parameter encoding to obtain the loss function value corresponding to each algorithm parameter encoding;

[0094] The loss function can be set to a conventional loss function, such as root mean square loss function, mean square loss function, cross entropy loss function, etc., to evaluate the impact of each algorithm parameter encoding on the performance of the deep learning algorithm.

[0095] A3. Randomly match a target algorithm parameter code for information interaction to each algorithm parameter code, and search the unknown area of ​​the algorithm parameter code along the sinusoidal search path to obtain the algorithm parameter code after the rough search;

[0096] For example: The target algorithm parameters are encoded as The algorithm parameters can be encoded along a sinusoidal search path to search the unknown region as:

[0097]

[0098] in, represents the i-th algorithm parameter code in the t-th iteration, i = 1, 2, ..., I, I represents the total number of algorithm parameter codes, Indicates the algorithm parameter encoding after rough search Indicates the algorithm parameter encoding during the t+1th iteration The corresponding increment, Represents the target algorithm parameter encoding, R1 represents the first random number between (0,1), π represents the pi, and R2 represents the second random number between (0,1).

[0099] A4. Perform historical optimal follow-up and current optimal follow-up on the algorithm parameter coding after the rough search, and perform restricted search on the algorithm parameter coding after the rough search along the optimal path to obtain the algorithm parameter coding after the fine search;

[0100] For example: Algorithm parameter encoding after the jth rough search The corresponding historical optimal value is The current optimal encoding is Where, j = 1, 2, ..., I;

[0101] The algorithm parameter encoding after the rough search is restricted to search along the optimal path as follows:

[0102]

[0103] in, Indicates the algorithm parameter encoding after fine search e represents a natural constant, α1 represents the first fusion coefficient, α2 represents the second fusion coefficient, β represents the restricted search control coefficient, d jP The historical optimal value is Encoding with algorithm parameters The Euclidean distance between jG Indicates that the current optimal encoding is Encoding with algorithm parameters The Euclidean distance between .

[0104] A5. Perform optimal information interaction on the algorithm parameter encoding after the fine search, perform nonlinear search between the current position and the current optimal position, and obtain the algorithm parameter encoding after the balanced search;

[0105] For example, based on the current number of searches, the nonlinear search factor can be determined as: γ = 2*R3*(1-t / T); wherein R3 represents a third random number between (0, 1), and T represents a preset maximum number of iterations;

[0106] Based on the nonlinear search factor, a nonlinear search is performed between the current position and the current optimal position:

[0107]

[0108] in, Indicates the algorithm parameter encoding after the nth fine search, Indicates the algorithm parameter encoding after the balance search n=1,2,…,I; R4 represents the fourth random number between (0,1), R5 represents the fifth random number between (0,1), levy represents the Levy flight step length, represents the random algorithm parameter encoding, and Not equal to

[0109] A6. Perform random weighted information interaction on the algorithm parameter encoding after the balanced search, search at the global position, and use a greedy algorithm to control the search to obtain the algorithm parameter encoding after the global search;

[0110] For example, to determine the global search value:

[0111]

[0112] in, represents the algorithm parameter encoding after the mth balance search, Indicates the algorithm parameter encoding after global search R6 represents the sixth random number between (0,1), R7 represents the seventh random number between (0,1), and R8 represents the eighth random number between (0,1). represents the random algorithm parameter code, and Not equal to X STEP Represents the randomly generated algorithm parameter encoding;

[0113] If the loss function value corresponding to the global search value is smaller than the loss function value encoded by the original algorithm parameter, the update is accepted, otherwise the update is rejected.

[0114] A7. Determine whether the end condition is met. If so, determine the final preset deep learning algorithm based on the algorithm parameter encoding after the global search, otherwise return to the rough search step.

[0115] Compared with the prior art, the preset algorithm provided by the embodiment of the present invention has the technical effects of not being easily trapped in local optimality, fast algorithm search speed and high search accuracy, which can make data analysis more effective and provide farmers with more accurate reference.

[0116] In an embodiment of the present invention, the loss function is set to a supervised loss function.

[0117] Exemplarily, the calculation formula of the supervision loss function can be:

[0118]

[0119] Among them, L represents the supervision loss, sum() represents the sum of the set, P represents the prediction result, Y represents the expected label, and γ represents a constant.

[0120] Optionally, in the process of presetting each deep learning algorithm, the training data may correspond to historical data and classification labels determined by experts, thereby achieving data classification. For example, the training data corresponding to the first preset deep learning algorithm may be historical environmental data and corresponding classification labels, and other training data are similar and will not be described in detail.

[0121] In the embodiment of the present invention, judging whether the termination condition is met includes:

[0122] Determine whether the current number of training times is greater than the maximum number of training times. If so, determine that the iteration end condition is met; otherwise, determine that the iteration end condition is not met.

[0123] It is worth noting that the end condition can also be set to other conditions. For example, when the loss function value is less than a preset threshold, it can also be considered that the end condition is met.

[0124] In an embodiment of the present invention, determining a final preset deep learning algorithm according to the algorithm parameter encoding after the global search includes:

[0125] Re-obtain the loss function value corresponding to the algorithm parameter code after the global search, and obtain the algorithm parameter code after the global search with the smallest loss function value to obtain the final algorithm parameter code;

[0126] The final algorithm parameter encoding is applied to the deep learning algorithm to be preset to obtain the final preset deep learning algorithm.

[0127] like Figure 2 As shown, an embodiment of the present invention provides a global spatial planting data management system, including: a data acquisition module 1, a data storage module 2, a data processing module 3 and a data display module 4;

[0128] The data acquisition module 1 is used for collecting planting data in each planting area using a preset data sampling frequency; wherein the planting data includes environmental parameters, crop growth status and nutrient solution usage;

[0129] The data storage module 2 is used to classify and store the planting data in the planting area to obtain a planting database composed of planting data at different time points;

[0130] The data processing module 3 is used to analyze the data in the planting database using a deep learning algorithm, determine the analysis results, and generate a management report based on the analysis results;

[0131] The data display module 4 is used to associate the planting database, the analysis results and the management report, and display them to farmers through a visual interface.

[0132] The global spatial planting data management system described in the embodiment of the present invention can execute the above-mentioned method and technical solution, and its principles and beneficial effects are similar, which will not be repeated here.

[0133] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present invention may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0134] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0135] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0136] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.

[0137] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0138] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A global spatial planting data management method, characterized in that: include: For each planting area, the planting data in the planting area is collected using a preset data sampling frequency; wherein the planting data includes environmental parameters, crop growth status and nutrient solution usage; Classifying and storing the planting data in the planting area to obtain a planting database consisting of the planting data at different time points; Using a deep learning algorithm to analyze data in a planting database, determine analysis results, and generate a management report based on the analysis results; The planting database, the analysis results and the management report are associated and presented to farmers through a visual interface.

2. The global spatial planting data management method according to claim 1, characterized in that: For each planting area, the planting data in the planting area is collected using a preset data sampling frequency, including: Obtaining a preset data sampling frequency input through human-computer interaction or pre-stored in a database; Based on the preset data sampling frequency, the environmental parameters corresponding to the planting area are collected through the Internet of Things sensor to obtain the environmental parameters; Based on the preset data sampling frequency, the crop growth images corresponding to the planting area are collected by the Internet of Things sensor to obtain the crop growth status; Collect the nutrient solution usage information input by farmers through human-computer interaction; The planting data in the planting area is obtained according to the environmental parameters, crop growth status and nutrient solution usage.

3. The global spatial planting data management method according to claim 2, characterized in that: The planting data in the planting area are classified and stored to obtain a planting database consisting of planting data at different time points, including: Creating a first storage block, a second storage block, and a third storage block; For the same planting area, the environmental parameters are stored in the first storage block in the order of sampling time; For the same planting area, the crop growth status is stored in the second storage block in the order of sampling time; For the same planting area, the nutrient solution usage is stored in the third storage block; A planting database is acquired according to the first storage block, the second storage block and the third storage block.

4. The global spatial planting data management method according to claim 2, characterized in that: A deep learning algorithm is used to analyze the data in the planting database, determine the analysis results, and generate a management report based on the analysis results, including: Using a first preset deep learning algorithm to analyze environmental parameters in a planting database to determine a planting environment state; A second preset deep learning algorithm is used to analyze the growth status of crops in the planting database to determine the growth cycle of the crops in the planting area; A third preset deep learning algorithm is used to jointly analyze the usage of nutrient solution in the planting database, the state of the planting environment, and the growth cycle of the crops in the planting area to determine the growth status of the crops; A management report is generated according to the planting environment status, the growth cycle of the crops in the planting area, and the growth status of the crops.

5. The global spatial planting data management method according to claim 4, characterized in that: The first preset deep learning algorithm is set to the BP algorithm, the second preset deep learning algorithm is set to the CNN algorithm, and the third preset deep learning algorithm is set to the BP algorithm.

6. The global spatial planting data management method according to claim 5, characterized in that: The first preset deep learning algorithm, the second preset deep learning algorithm, and the third preset deep learning algorithm are preset in the same manner, and all include: Initializing the algorithm parameters of the preset deep learning algorithm multiple times to obtain multiple algorithm parameter codes; Using the loss function to evaluate each algorithm parameter encoding to obtain the loss function value corresponding to each algorithm parameter encoding; A target algorithm parameter code for information interaction is randomly matched to each algorithm parameter code, and the algorithm parameter code is searched in an unknown area along a sinusoidal search path to obtain the algorithm parameter code after a rough search; Performing historical optimal following and current optimal following on the algorithm parameter coding after the rough search, performing restricted search on the algorithm parameter coding after the rough search along the optimal path, and obtaining the algorithm parameter coding after the fine search; Perform optimal information interaction on the algorithm parameter encoding after fine search, perform nonlinear search between the current position and the current optimal position, and obtain the algorithm parameter encoding after balanced search; Perform random weighted information interaction on the algorithm parameter encoding after the balanced search, search at the global position, and use a greedy algorithm to control the search to obtain the algorithm parameter encoding after the global search; Determine whether the end condition is met. If so, determine the final preset deep learning algorithm based on the algorithm parameter encoding after the global search, otherwise return to the rough search step.

7. The global spatial planting data management method according to claim 6, characterized in that: The loss function is set to be a supervised loss function.

8. The global spatial planting data management method according to claim 7, characterized in that: Determine whether the termination conditions are met, including: Determine whether the current number of training times is greater than the maximum number of training times. If so, determine that the iteration end condition is met; otherwise, determine that the iteration end condition is not met.

9. The global spatial planting data management method according to claim 8, characterized in that: According to the algorithm parameter encoding after the global search, the final preset deep learning algorithm is determined, including: Re-obtain the loss function value corresponding to the algorithm parameter code after the global search, and obtain the algorithm parameter code after the global search with the smallest loss function value to obtain the final algorithm parameter code; The final algorithm parameter encoding is applied to the deep learning algorithm to be preset to obtain the final preset deep learning algorithm.

10. A global spatial planting data management system, characterized in that: include: Data acquisition module, data storage module, data processing module and data display module; The data acquisition module is used to collect planting data in each planting area using a preset data sampling frequency; wherein the planting data includes environmental parameters, crop growth status and nutrient solution usage; The data storage module is used to classify and store the planting data in the planting area to obtain a planting database composed of planting data at different time points; The data processing module is used to analyze the data in the planting database using a deep learning algorithm, determine the analysis results, and generate a management report based on the analysis results; The data display module is used to associate the planting database, the analysis results and the management report, and display them to farmers through a visual interface.

Images