Agricultural data intelligent deployment and management system and method based on artificial intelligence

Abstract

The invention discloses an agricultural data intelligent deployment and management system and method based on artificial intelligence, and relates to the technical field of agricultural deployment management. The agricultural data intelligent deployment and management system based on artificial intelligence comprises a deployment conflict monitoring module, an alignment monitoring module and a deployment deviation monitoring module. According to the method, agricultural data transmission conflict analysis is carried out to judge whether concurrent conflict-loss degree analysis is carried out or not, after agricultural data transmission conflict analysis is qualified, agricultural data alignment monitoring is carried out based on an agricultural data transmission conflict analysis result, and whether first-level agricultural data alignment optimization is carried out or not is judged; after the agricultural data alignment monitoring is qualified, whether agricultural data allocation deviation evaluation is carried out is judged based on the agricultural data alignment monitoring result, the effect of improving the accuracy of the agricultural data intelligent allocation and management process is achieved, and the problem that the accuracy is low when agricultural data intelligent allocation and management are carried out in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of agricultural allocation and management technology, and in particular to an intelligent agricultural data allocation and management system and method based on artificial intelligence. Background Technology

[0002] To achieve efficient integration and reliable utilization of multi-source data in agricultural production (such as soil moisture, crop growth images, meteorological information, and agricultural machinery operation records), intelligent allocation and management of agricultural data is required.

[0003] Existing methods first involve comprehensive three-dimensional perception and aggregation of data across the entire area. Through various channels such as agricultural sensors deployed in the fields, drone remote sensing, satellite imagery, and agricultural machinery operation records, the system collects agricultural status data in real time, including soil moisture, nutrient content, meteorological information, crop growth images, and pest and disease conditions, forming the foundation for a "digital twin" of agricultural production. Next comes the core data fusion and intelligent diagnosis stage. The collected multi-source heterogeneous data is transmitted to the cloud or edge computing platform. Data cleaning, alignment, and fusion technologies are used to eliminate noise and inconsistencies, forming a unified, high-quality dataset. Subsequently, AI (Artificial Intelligence) models (such as machine learning and deep learning algorithms) begin to play a key role: by analyzing historical and real-time datasets, the models can accurately analyze the current state of farmland. For example, they can identify specific areas under water stress or predict the risk of a disease outbreak within the next week and quantify its potential impact on the final yield. Next comes the scientific intelligent decision-making and allocation stage. Based on the analyzed farmland needs and preset optimization goals (such as maximizing yield, minimizing resource consumption, or optimizing quality), the system automatically generates the optimal agricultural operation plan through operations research algorithms and a preset rule base. Finally, the precise execution and feedback stage begins. The generated allocation instructions (such as scheduling plans) are automatically sent to the corresponding intelligent execution terminals, such as intelligent irrigation systems, autonomous tractors, or drone-based plant protection systems. These devices perform precise tasks based on AI instructions. At the same time, the execution process itself generates new data (such as the actual operation trajectory of agricultural machinery and the completion of irrigation volume), which is fed back to the system in real time.

[0004] For example, the Chinese invention patent with announcement number CN120031323B discloses an agricultural information sharing and management method based on multi-source data fusion, which includes: spatially labeling multi-source data and constructing an agricultural health spatial dataset; mining the correlation between microbial communities and soil health through spatial correlation network analysis and constructing a spatial correlation model; optimizing the allocation of agricultural resources; and generating personalized agricultural resource allocation plans for each region through spatial optimization algorithms; and automatically generating a correction plan and an agricultural health assessment report based on spatial feedback from microbial communities and soil health after the implementation of the agricultural resource allocation plan.

[0005] The above-mentioned technology has at least the following technical problems: When agricultural status data is transmitted and allocated based on existing wireless transmission methods (such as LoRa and NB-IoT), transmission conflicts and delays caused by the special environment of remote farmland may significantly damage data quality, leading to a chain reaction of accuracy deviations. For example, crop growth images captured by drone remote sensing may experience partial frame loss due to concurrent transmission conflicts of multiple NB-IoT devices. Remote farmland is usually far from urban core communication base stations, with weak signal coverage, making the transmission delay problem between satellite imagery and field sensor data more prominent. Due to transmission delays (such as data transmission delays in remote farmland), data from different sources cannot be aligned in the time dimension, resulting in inaccurate farmland status analysis by the model based on agricultural status data. This leads to a mismatch between the real-time agricultural status perceived by the system and the actual situation, ultimately causing allocation deviations when instructions generated based on the erroneous status are automatically sent to the corresponding intelligent execution terminals for intelligent allocation. Existing systems lack an adaptive feedback correction mechanism for allocation execution deviations, preventing subsequent AI models from correcting parameters based on real-time execution results. This causes errors to accumulate and amplify during the selection process, resulting in low accuracy in intelligent allocation and management of agricultural data. Summary of the Invention

[0006] To address the low accuracy problem in existing technologies for intelligent allocation and management of agricultural data, this invention provides an artificial intelligence-based intelligent allocation and management system and method for agricultural data. The technical solution is as follows: On the one hand, an AI-based intelligent allocation and management system for agricultural data is provided, including: an allocation conflict monitoring module, an alignment monitoring module, and an allocation deviation monitoring module. The allocation conflict monitoring module performs agricultural data transmission conflict analysis during the intelligent execution terminal allocation process based on agricultural data. It outputs agricultural data transmission conflict analysis results to assess the situation of agricultural sensor data transmission conflicts and satellite image transmission loss. Based on the agricultural data transmission conflict analysis results, it determines whether to conduct concurrent conflict-loss analysis to measure the degree of interference between agricultural sensor data transmission conflicts and satellite image transmission loss on the intelligent allocation and management of agricultural data. The alignment monitoring module, after the agricultural data transmission conflict analysis is deemed satisfactory, uses the agricultural data transmitted by the allocation conflict monitoring module to... The data transmission conflict analysis results are used to monitor agricultural data alignment, outputting agricultural data alignment monitoring results to evaluate the compliance of agricultural data alignment in the time dimension. Based on the agricultural data alignment monitoring results, it is determined whether to perform primary and secondary agricultural data alignment optimization. Primary agricultural data alignment optimization is used to ensure the accuracy of matching between the operation of the intelligent execution terminal and the actual needs of the farmland. Secondary agricultural data alignment optimization is used to ensure that the data alignment deviation meets the alignment quality standards based on the primary agricultural data alignment optimization. The allocation deviation monitoring module is used to determine whether to conduct agricultural data allocation deviation assessment based on the agricultural data alignment monitoring results transmitted by the alignment monitoring module after the agricultural data alignment monitoring is qualified, in order to assess the allocation deviation of the agricultural intelligent execution terminal.

[0007] On the other hand, an AI-based intelligent allocation and management method for agricultural data is provided. This method is applied to an AI-based intelligent allocation and management system for agricultural data, including: During the allocation of intelligent execution terminals based on agricultural data, agricultural data transmission conflict analysis is performed to output agricultural data transmission conflict analysis results for evaluating the situation of agricultural sensor data transmission conflicts and satellite image transmission loss; based on the agricultural data transmission conflict analysis results, it is determined whether to perform concurrent conflict-loss degree analysis to measure the interference degree of agricultural sensor data transmission conflicts and satellite image transmission loss on the intelligent allocation and management of agricultural data; after the agricultural data transmission conflict analysis is qualified, based on the agricultural data transmission conflict analysis results transmitted by the allocation conflict monitoring module, agricultural data alignment monitoring is performed to output agricultural data alignment monitoring results for evaluating the qualification of agricultural data time dimension alignment; based on the agricultural data alignment monitoring results, it is determined whether to perform primary and secondary agricultural data alignment optimization; after the agricultural data alignment monitoring is qualified, based on the agricultural data alignment monitoring results transmitted by the alignment monitoring module, it is determined whether to perform agricultural data allocation deviation assessment to evaluate the allocation deviation of agricultural intelligent execution terminals.

[0008] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: 1. By conducting agricultural data transmission conflict analysis and outputting the results, and determining whether to perform concurrent conflict-loss analysis based on these results, it helps to screen high-quality agricultural data from the transmission source, preemptively eliminating "invalid and distorted data" caused by channel conflicts and image frame drops. This prevents low-quality data from entering subsequent analysis stages and causing cascading errors. After the agricultural data transmission conflict analysis is deemed satisfactory, agricultural data alignment monitoring is performed based on the results, outputting the agricultural data alignment monitoring results. Based on these results, it is determined whether to perform primary and secondary agricultural data alignment optimization, which helps to achieve... This approach addresses the issue of temporal misalignment in multi-source agricultural data by employing a multi-tiered optimization strategy. First-level optimization quickly avoids immediate execution errors caused by time discrepancies (such as mismatched irrigation timing), while second-level optimization ensures precise data alignment, providing AI models with consistent temporal analysis samples. After agricultural data alignment monitoring is deemed satisfactory, the system determines whether to conduct an agricultural data allocation deviation assessment based on the acquired monitoring results. This helps to accurately capture the discrepancies between AI allocation instructions and actual terminal operations, promptly identifying potential deviations at the execution end. Ultimately, this improves the accuracy of intelligent agricultural data allocation and management, resolving the low accuracy issue present in existing technologies for intelligent agricultural data allocation and management.

[0009] 2. By performing agricultural sensor data transmission conflict analysis to obtain the quantification value of concurrent agricultural data conflicts, and triggering concurrent conflict-loss level analysis when the quantification value exceeds a preset concurrent conflict quantification value, it helps to achieve "precise hierarchical triggering" of transmission conflicts. This avoids the "ambiguity of qualitative judgment of conflicts" in existing technologies, and only initiates in-depth analysis for conflicts exceeding a safety threshold, reducing redundant calculations. Similarly, by performing agricultural image data loss analysis to obtain the quantification value of agricultural data loss, and triggering concurrent conflict-loss level analysis when the quantification value exceeds a preset agricultural data loss quantification value, it helps to achieve precise hierarchical triggering of transmission conflicts. Quantitative management of data loss risks avoids excessive triggering of optimization processes due to the loss of a small number of non-critical frames, balancing data quality and processing efficiency. Through correlation analysis of agricultural sensor data transmission conflict analysis and agricultural image data loss analysis, compared with the isolated mode of existing technologies that monitor sensor conflicts or image loss separately and ignore the synergistic interference of the two, it can more comprehensively identify the superimposed effects of transmission risks (such as sensor conflicts causing data delays, superimposed with image loss, further amplifying data time misalignment). It can achieve a systematic assessment of transmission layer interference, avoid risk omissions caused by single monitoring, and thus ensure the basic data quality of subsequent data alignment and AI allocation decision-making.

[0010] 3. By performing concurrent conflict control when the concurrent conflict interference level value obtained from concurrent conflict-loss level analysis is greater than the agricultural data loss interference level value, it helps to achieve precise control logic that prioritizes the resolution of core interference. This avoids the situation where critical risks (such as the loss of a large amount of sensor data caused by high concurrent conflicts) are not addressed in a "spreading the load" manner, and quickly reduces transmission problems that have a greater impact on allocation. By performing agricultural data alignment monitoring after the concurrent conflict-loss level analysis is qualified, compared with the process defect of "starting data alignment before the transmission conflict is completely resolved" in the existing technology, it can avoid the data after alignment being distorted again due to continuous transmission conflicts (such as the agricultural sensor data that has just been aligned being delayed due to new conflicts). This ensures that the input data in the data alignment process is stable and reliable, reduces the repetitive operation of alignment optimization, and thus improves the success rate and stability of subsequent data alignment, reducing the risk of cumulative error throughout the process.

[0011] 4. By triggering agricultural data allocation deviation assessment when the average agricultural data alignment deviation value obtained from agricultural data alignment monitoring is within the preset agricultural data alignment deviation range, and conversely performing first-level agricultural data alignment optimization, it helps to achieve "on-demand activation" of alignment optimization. This avoids the redundant operation of "forcibly executing multi-level optimization regardless of the deviation size" in existing technologies. Data with acceptable deviations is directly promoted to allocation assessment, improving the efficiency of the entire process. By stopping the execution of first-level agricultural data alignment optimization and performing agricultural data alignment qualification verification when the average agricultural data alignment deviation value obtained after first-level agricultural data alignment optimization is within the preset agricultural data alignment deviation range, it helps to ensure the continuity and stability of data alignment quality, prevent alignment deviation residues from entering the allocation stage, and thus improve the accuracy of AI models in generating allocation instructions based on alignment data. This reduces operational errors of intelligent execution terminals caused by alignment deviations (such as mismatched irrigation amounts and deviations in plant protection timing). Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of the structure of the intelligent allocation and management system for agricultural data based on artificial intelligence provided in an embodiment of the present invention; Figure 2 This is an overview diagram of the intelligent allocation and management system for agricultural data based on artificial intelligence provided in the embodiments of the present invention; Figure 3This is a schematic diagram illustrating the concurrent conflict-loss level analysis of the intelligent allocation and management system for agricultural data based on artificial intelligence provided in an embodiment of the present invention; Figure 4 This is a flowchart of an artificial intelligence-based intelligent allocation and management method for agricultural data provided in an embodiment of the present invention. Detailed Implementation

[0014] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0015] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0016] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0017] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0018] This invention provides an intelligent agricultural data allocation and management system based on artificial intelligence. For example... Figure 1 The schematic diagram of the AI-based intelligent agricultural data allocation and management system shown includes: an allocation conflict monitoring module, an alignment monitoring module, and an allocation deviation monitoring module. The allocation conflict monitoring module performs agricultural data transmission conflict analysis during the allocation of intelligent execution terminals based on agricultural data. It outputs agricultural data transmission conflict analysis results to assess the situation of agricultural sensor data transmission conflicts and satellite image transmission loss. Based on the agricultural data transmission conflict analysis results, it determines whether to conduct concurrent conflict-loss analysis to measure the interference degree of agricultural sensor data transmission conflicts and satellite image transmission loss on the intelligent allocation and management of agricultural data. By performing allocation conflict monitoring, it helps to identify and quantify the transmission risks of agricultural data (such as sensor data packet loss caused by LoRa channel collisions and satellite image frame loss caused by NB-IoT concurrency) from the transmission source, providing stable and reliable basic data for subsequent data alignment.

[0019] The alignment monitoring module is used to monitor agricultural data alignment after the agricultural data transmission conflict analysis is deemed satisfactory. Based on the conflict analysis results of the agricultural data transmission from the allocation conflict monitoring module, it outputs agricultural data alignment monitoring results to evaluate the time dimension alignment of agricultural data. Based on the agricultural data alignment monitoring results, it determines whether to perform primary and secondary agricultural data alignment optimization. Primary agricultural data alignment optimization is used to avoid execution errors caused by persistent time misalignment, thereby ensuring the accuracy of matching between the operation of the intelligent execution terminal and the actual needs of farmland. Secondary agricultural data alignment optimization is used to further correct the time misalignment problem of agricultural data based on the primary agricultural data alignment optimization, ensuring that the data alignment deviation meets the alignment quality standards. By performing alignment monitoring, it is helpful to solve the time misalignment problem of multi-source agricultural data in a hierarchical manner. Primary agricultural data alignment optimization can quickly avoid the risk of immediate execution, while secondary agricultural data alignment optimization can achieve high-precision alignment. This provides a time-consistent analysis sample for accurately judging farmland needs (such as water stress).

[0020] The allocation deviation monitoring module is used to determine whether to conduct an agricultural data allocation deviation assessment based on the agricultural data alignment monitoring results transmitted by the alignment monitoring module after the agricultural data alignment monitoring is qualified, so as to assess the allocation deviation of the agricultural intelligent execution terminal. By conducting allocation deviation monitoring, it is helpful to achieve accurate verification between AI allocation instructions and actual terminal operations, and timely capture deviation problems at the execution end.

[0021] Prior to the design of the AI-based intelligent allocation and management system and method for agricultural data provided in this application, a database is established to store various types of preset data. The database includes, but is not limited to, preset concurrent conflict quantification values ​​and preset agricultural data loss quantification values. The various values ​​are directly set by technicians. This database adopts a cloud-based distributed relational database (such as MySQL Cluster or PostgreSQL) and is the central hub for setting data throughout the entire system operation. Its core is used to store various quantification thresholds, configuration parameters, and association rules preset by technicians, providing judgment criteria and operational basis for the three major modules: allocation conflict monitoring module, alignment monitoring module, and allocation deviation monitoring module.

[0022] like Figure 2 The diagram shown is an overview of the intelligent allocation and management system for agricultural data based on artificial intelligence provided in an embodiment of the present invention; Figure 2It can be seen that: by performing agricultural data transmission conflict analysis, the quantitative values ​​of concurrent agricultural data conflict and agricultural data loss are obtained respectively. When the quantitative value of concurrent agricultural data conflict is greater than the preset quantitative value of concurrent agricultural data conflict, and the quantitative value of agricultural data loss is greater than the preset quantitative value of agricultural data loss, the concurrent conflict-loss degree analysis is triggered. Otherwise, agricultural data alignment monitoring is triggered and the average agricultural data alignment deviation value is obtained. When the average agricultural data alignment deviation value is not within the preset agricultural data alignment deviation range, first-level agricultural data alignment optimization is performed. Otherwise, agricultural data allocation deviation assessment is triggered and the agricultural data allocation deviation value is obtained. When the monitored agricultural data allocation deviation value is greater than the preset agricultural data allocation deviation value, allocation optimization and deviation verification are performed. Otherwise, after performing a preset number of agricultural data allocation deviation assessments, allocation instructions with an average agricultural data allocation deviation value not greater than the preset agricultural data allocation deviation value are marked as qualified allocation instructions and stored in the preset agricultural allocation center.

[0023] In this embodiment, the interaction and interconnection of the allocation conflict monitoring module, alignment monitoring module, and allocation deviation monitoring module help to achieve a closed-loop quality control system across the entire chain, from transmission risk control to data timing correction and deviation verification. The allocation conflict monitoring module establishes a "data entry threshold" for the chain, ensuring that the input data is transmitted without distortion. The alignment monitoring module addresses the issue of data timing consistency based on the entry threshold, ensuring the reliability of the analysis samples. The allocation deviation monitoring module connects decision-making and execution, ensuring that instructions are accurately implemented. The three modules work in a progressive manner, with each module providing qualified input for the next, avoiding the defects of isolated operation and risk superposition in traditional technologies. This helps to ensure the accuracy of AI models in analyzing farmland conditions (such as water stress identification and disease prediction) and the matching degree between intelligent execution terminals (irrigation, plant protection, agricultural machinery) and actual farmland needs, thereby improving the overall accuracy of the intelligent allocation and management of agricultural data based on artificial intelligence.

[0024] Furthermore, agricultural data transmission conflict analysis includes agricultural sensor data transmission conflict analysis, which measures the conflict situation of concurrent transmission of agricultural sensors, and agricultural image data loss analysis, which measures the loss situation during satellite image transmission.

[0025] Specifically, the process of agricultural sensor data transmission conflict analysis is as follows: The concurrent transmission conflict of agricultural sensor data is quantified based on the total number of signal collisions corresponding to the agricultural sensor data, obtaining a concurrent conflict quantification value. This quantification value is represented by the total number of signal collisions monitored by a counter when field sensors simultaneously send agricultural sensor data to the same allocated resource block within a preset field area. A judgment is made based on this quantification value. If the quantification value is greater than the preset quantification value, the corresponding quantification value is marked as the concurrent conflict value to be analyzed, triggering concurrent conflict-loss analysis; otherwise, the corresponding agricultural sensor data is marked as qualified agricultural sensor data, triggering agricultural data alignment monitoring. The preset quantification value is represented by the average value of the concurrent conflict quantification values ​​over a historical time period.

[0026] Specifically, the process of agricultural image data loss analysis is as follows: The agricultural image data loss is quantified based on the number of lost satellite image frames, obtaining a quantitative value for agricultural data loss; the number of lost satellite image frames within a preset field area is monitored using a multi-channel spectrum analyzer, and the proportion of these lost frames to the total number of frames is represented as the quantitative value for agricultural data loss; a judgment is made based on the quantitative value for agricultural data loss; if the quantitative value for agricultural data loss is greater than the preset quantitative value for agricultural data loss, the corresponding quantitative value for agricultural data loss is marked as the agricultural data loss value to be analyzed, triggering concurrent conflict-loss degree analysis; otherwise, the corresponding agricultural image data is marked as qualified agricultural image data, triggering agricultural data alignment monitoring; wherein, the preset quantitative value for agricultural data loss is represented by the average value of the quantitative values ​​for agricultural data loss over a historical time period.

[0027] In this embodiment, by simultaneously performing agricultural sensor data transmission conflict analysis and agricultural image data loss analysis, it is helpful to achieve a "full-dimensional and comprehensive" assessment of risks in the agricultural data transmission layer, thereby accurately identifying composite risks in the transmission layer and laying a solid foundation for data alignment and AI allocation decisions. By triggering concurrent conflict-loss degree analysis when the quantification value of agricultural data concurrency conflict exceeds the preset quantification value of concurrent conflict and the quantification value of agricultural data loss exceeds the preset quantification value of agricultural data loss, it is helpful to achieve precise hierarchical triggering of in-depth analysis of transmission risks, improve the accuracy of transmission risk assessment, and provide a clear basis for subsequent concurrent conflict control and data quality repair.

[0028] like Figure 3 The diagram shown illustrates the concurrent conflict-loss level analysis of the artificial intelligence-based intelligent allocation and management system for agricultural data provided in this embodiment of the invention; Figure 3It can be seen that by performing concurrent conflict-loss analysis, the concurrent conflict interference level and the agricultural data loss interference level of agricultural data are obtained. When the concurrent conflict interference level of agricultural data is greater than the agricultural data loss interference level, concurrent conflict control is performed; otherwise, satellite image loss control is performed.

[0029] Further, the specific process of concurrent conflict-loss analysis is as follows: The agricultural data to be analyzed is input into the concurrent conflict-loss table, and the concurrent conflict-loss value is output. The agricultural data to be analyzed includes concurrent conflict values ​​and lost values. The concurrent conflict-loss value includes concurrent conflict interference values ​​and lost interference values. Based on the concurrent conflict-loss value, the impact of concurrent transmission conflict of agricultural sensors and lost satellite imagery on the qualified interference of agricultural data transmission is determined: If the concurrent conflict interference value is greater than the lost interference value, concurrent conflict control is performed in the next adjacent preset agricultural transmission window to alleviate channel contention pressure; otherwise, satellite imagery loss control is performed in the next adjacent preset agricultural transmission window to reduce the probability of transmission loss. Concurrent conflict control is used to alleviate channel contention pressure and reduce anomalies such as interruption of agricultural sensor data transmission due to concurrent conflicts. Satellite imagery loss control is used to reduce the amount of data transmitted in a single round of satellite imagery transmission, thereby reducing the probability of transmission loss. The preset agricultural transmission window represents the preset time period corresponding to the agricultural data transmission conflict analysis.

[0030] The specific process of concurrent conflict control is as follows: The concurrent conflict interference level value of agricultural data and the channel bandwidth corresponding to the agricultural data monitored by the spectrum analyzer are input into the preset concurrent conflict control list. The preset coding rate control ratio value corresponding to the agricultural data is read. Within the preset range corresponding to the coding rate, the amplitude corresponding to the preset coding rate control ratio value is used as the adjustment step size. Based on the initial coding rate of the agricultural data, a decreasing operation is performed. This helps to gradually reduce the amount of transmitted data while ensuring that the effective information of the data is not lost, thereby improving the transmission efficiency of agricultural sensor data and reducing concurrent conflicts caused by excessive data volume. Each time a decreasing operation is performed, if the newly acquired concurrent conflict quantification value of agricultural data is not greater than the preset concurrent conflict quantification value, concurrent conflict control is stopped. If the acquired concurrent conflict quantification value of agricultural data is still greater than the preset concurrent conflict quantification value after performing a preset number of concurrent conflict control operations, a concurrent conflict control warning is sent. Agricultural data includes agricultural sensor data (such as soil moisture content, air temperature and humidity, etc.) and agricultural image data (such as the resolution of crop leaf close-up images, agricultural machinery operation trajectory, etc.).

[0031] Satellite imagery loss control means that within a preset range corresponding to the data frame, a data frame control operation is performed. The data frame control operation uses the amplitude corresponding to a preset data frame control ratio as the adjustment step size. Based on the initial data frame of agricultural data, a decreasing operation is performed, triggering a data frame control operation detection. This helps to eliminate redundant data frames and retain core data frames, thereby improving the transmission stability of agricultural imagery data and reducing transmission conflicts and data loss caused by redundant frames. Data frame control operation detection means that after each data frame control operation, the agricultural data loss quantization value is reacquired. If the reacquired agricultural data loss quantization value is not greater than the preset agricultural data loss quantization value, satellite imagery loss control stops. If, after a preset number of satellite imagery loss control operations, the acquired agricultural data loss quantization value is still greater than the preset agricultural data loss quantization value, a concurrent conflict control warning is sent. The preset data frame control ratio is read by inputting the agricultural data loss quantization value and the channel bandwidth corresponding to the agricultural imagery data into a preset loss control list.

[0032] It should be added that, in the embodiments of this application, relevant data such as a concurrency conflict-loss level table, a preset concurrency conflict control list, a preset loss control list, a preset clock frequency optimization table, a preset secondary clock frequency optimization table, and a preset timeout optimization table, retrieved from the database, are presented. These data contain mapping relationships with dynamic characteristics. Such mapping relationships have high flexibility, enabling both one-to-one mapping between single parameters and many-to-one mapping between multiple parameters and single parameters.

[0033] Specifically, the following information is input into a machine learning model (e.g., a decision tree model to represent the importance of features): agricultural data to be analyzed within a historical time period collected by pre-defined personnel; combinations of agricultural data concurrency conflict interference levels and corresponding channel bandwidths for agricultural sensor data; combinations of agricultural data loss quantification values ​​and corresponding channel bandwidths for agricultural image data; combinations of agricultural data alignment deviation values ​​and corresponding synchronization clock pulse counts; combinations of alignment qualification verification values ​​and corresponding synchronization clock pulse counts for agricultural data; and combinations of average agricultural data allocation deviation values ​​and corresponding sliding window sizes for agricultural retransmission requests. Using the model's feature splitting function, corresponding weights or data can be obtained, such as concurrency conflict-loss levels, preset coding rate adjustment ratios, preset data frame adjustment ratios, preset clock frequency adjustment ratios, preset secondary clock frequency adjustment ratios, and preset timeout adjustment ratios. The historical time period data is then correlated and matched with its corresponding weights or data to generate a concurrency conflict-loss level table, a preset concurrency conflict control list, a preset loss control list, a preset clock frequency optimization table, a preset secondary clock frequency optimization table, and a preset timeout optimization table.

[0034] Subsequently, by inputting information such as the real-time acquired agricultural data to be analyzed, the combination of agricultural data concurrent conflict interference level value and the channel bandwidth corresponding to agricultural sensor data, the combination of agricultural data loss quantization value and the channel bandwidth corresponding to agricultural image data, the combination of agricultural data alignment deviation value and the corresponding synchronization clock pulse count, and the combination of the alignment qualification verification value to be analyzed and the synchronization clock pulse count corresponding to agricultural data into the corresponding concurrent conflict-loss level table, preset concurrent conflict control list, preset loss control list, preset clock frequency optimization table, preset secondary clock frequency optimization table, and preset timeout time optimization table, etc., according to the preset mapping relationship, the system outputs data such as concurrent conflict-loss level value, preset coding rate control ratio value, preset data frame control ratio value, preset clock frequency adjustment ratio, preset secondary clock frequency adjustment ratio, and preset timeout time adjustment ratio, which are limited to the range of 0-1.

[0035] In this embodiment, concurrent conflict-loss level analysis is performed to obtain the concurrent conflict-loss level value. When the concurrent conflict interference level value of agricultural data is greater than the agricultural data loss interference level value, concurrent conflict control is performed. This helps to achieve precise control by prioritizing the resolution of core transmission risks. Prioritizing conflict control can quickly reduce the sensor data packet loss rate, avoid the destruction of subsequent farmland moisture analysis due to the distortion of a large amount of sensor data, and ensure that risks with greater impact on allocation are eliminated first, thereby improving the efficiency and pertinence of solving transmission layer problems. When the concurrent conflict interference level value of agricultural data is not greater than the agricultural data loss interference level value, satellite image loss control is performed. This helps to achieve precise restoration of the core value of the image. Prioritizing image control can restore key growth information, ensure that the AI ​​model can judge disease risks based on complete images, and avoid allocation decision deviations due to the lack of core image information.

[0036] Furthermore, the specific process of agricultural data alignment monitoring is as follows: Based on the number of successful agricultural data alignments, the alignment status of qualified agricultural data in the time dimension is quantified, and an agricultural data alignment monitoring value is output. The agricultural data alignment monitoring value is represented by the proportion of successful alignments monitored by the counter during the agricultural data alignment process to the total number of alignments. Based on the agricultural data alignment monitoring value and a preset agricultural data alignment monitoring value, the degree of alignment deviation in the time dimension of qualified agricultural data is quantified, and an agricultural data alignment deviation value is output. The preset agricultural data alignment monitoring value is represented by the average of agricultural data alignment monitoring values ​​over a historical time period. The agricultural data alignment deviation value is determined when the agricultural data alignment monitoring value is greater than the preset agricultural data alignment monitoring value. The difference between the agricultural data alignment monitoring value and the preset agricultural data alignment monitoring value is used to represent the data alignment deviation. The average agricultural data alignment deviation value is then used for judgment: if the average agricultural data alignment deviation value is within the preset agricultural data alignment deviation range, an agricultural data allocation deviation assessment is triggered; otherwise, a first-level agricultural data alignment optimization is performed in the next adjacent preset alignment monitoring window. The preset agricultural data alignment deviation range is pre-set by preset personnel. The average agricultural data alignment deviation value represents the average of the agricultural data alignment deviation values ​​obtained after a preset number of agricultural data alignment monitoring sessions. The preset alignment monitoring window represents the preset time period corresponding to the agricultural data alignment monitoring. Qualified agricultural data includes qualified agricultural sensor data and qualified agricultural image data.

[0037] Specifically, the process of primary agricultural data alignment optimization is as follows: The agricultural data alignment deviation value, along with the corresponding synchronization clock pulse count monitored by a counter, is input into the preset clock frequency optimization table for agricultural data. The preset clock frequency adjustment ratio for agricultural data is then queried. Within the preset range of clock frequencies, the amplitude corresponding to the queried preset clock frequency adjustment ratio is used as the adjustment step size for each increment, increasing the adjustment based on the initial clock frequency of the agricultural data. This helps to achieve a smooth transition in clock synchronization during primary agricultural data alignment optimization, gradually reducing the clock deviation of sensors and satellite receiving equipment, and ensuring a steady improvement in the synchronization of data acquisition timestamps. After each increment operation, the average value is reacquired. Agricultural data alignment deviation value; if the average agricultural data alignment deviation value is within the preset agricultural data alignment deviation range, stop executing Level 1 agricultural data alignment optimization and perform agricultural data alignment qualification verification; if after executing Level 1 agricultural data alignment optimization a preset number of times, the obtained agricultural data alignment deviation value is still not within the preset agricultural data alignment deviation range, trigger Level 1 agricultural data alignment optimization warning level; Level 1 agricultural data alignment optimization warning level means that agricultural data alignment deviation values ​​that are still not within the preset agricultural data alignment deviation range after executing Level 1 agricultural data alignment optimization a preset number of times will be input into a preset machine learning model (such as a random forest model), outputting a Level 1 agricultural data alignment optimization warning level and sending it to preset personnel.

[0038] Specifically, by randomly dividing the agricultural data alignment deviation values ​​that are outside the preset agricultural data alignment deviation range in historical time periods and the set first-level agricultural data alignment optimization warning level into a training set, and inputting them into a preset machine learning model (such as a random forest model) for training, a training model is obtained. The newly acquired agricultural data alignment deviation values ​​that are outside the preset agricultural data alignment deviation range are then used to train the model, and the first-level agricultural data alignment optimization warning level is output.

[0039] It should be added that the specific process of agricultural data alignment qualification verification is as follows: Based on the agricultural data alignment monitoring values ​​at the initial and final states of the first-level agricultural data alignment optimization, the degree of first-level agricultural data alignment optimization is quantified, and an agricultural data alignment qualification verification value is output. The agricultural data alignment qualification verification value is represented by the difference between the agricultural data alignment monitoring values ​​at the initial and final states of the first-level agricultural data alignment optimization. A judgment is made based on the agricultural data alignment qualification verification value: if the agricultural data alignment qualification verification value is greater than 0, the corresponding agricultural data alignment qualification verification value is marked as the alignment qualification verification value to be analyzed, and a second alignment qualification judgment is triggered; otherwise, an alignment maintenance prompt is sent to preset personnel. The second alignment qualification judgment is as follows: if the alignment qualification verification value to be analyzed is greater than the preset agricultural data alignment qualification verification value, an agricultural data allocation deviation assessment is performed; otherwise, a second-level agricultural data alignment optimization is triggered. The preset agricultural data alignment qualification verification value is represented by the average value of the alignment qualification verification values ​​to be analyzed over a historical time period. The specific process of the second-level agricultural data alignment optimization is as follows: the alignment qualification verification value to be analyzed and the corresponding agricultural data... The system inputs a synchronous clock pulse count to the preset secondary clock frequency optimization table for agricultural data, and queries the preset secondary clock frequency adjustment ratio for agricultural data. It then determines whether the clock frequency at the end of the primary agricultural data alignment optimization is within the corresponding preset range. If so, within the preset clock frequency range, it uses the amplitude corresponding to the preset secondary clock frequency adjustment ratio as the adjustment step size, and performs an incremental operation based on the clock frequency at the end of the primary agricultural data alignment optimization. This helps to achieve precise fine-tuning of clock synchronization in the secondary agricultural data alignment optimization, thereby improving the accuracy of the secondary agricultural data alignment optimization. Otherwise, it sends a secondary agricultural data alignment optimization alarm. Next, it checks whether the verification alignment data meets the verification alignment conditions. If it does, it stops executing the secondary agricultural data alignment optimization; otherwise, it sends a secondary agricultural data alignment optimization alarm. The verification alignment data includes the agricultural data alignment deviation value and the agricultural data alignment pass verification value re-acquired after performing a preset number of incremental operations. The verification alignment condition indicates that the re-acquired agricultural data alignment deviation value is within the preset agricultural data alignment deviation range, and the agricultural data alignment pass verification value is greater than the preset agricultural data alignment pass verification value. The preset agricultural data alignment deviation range is preset by preset personnel.

[0040] In this embodiment, the average agricultural data alignment deviation value is obtained through agricultural data alignment monitoring. If the average agricultural data alignment deviation value is not within the preset agricultural data alignment deviation range, first-level agricultural data alignment optimization is performed. This helps to achieve real-time time misalignment correction, quickly pull the data alignment deviation back to the "acceptable basic range", provide a stable starting point for subsequent higher-precision optimization, and prevent misaligned data from entering the AI ​​model analysis stage, thereby reducing the initial error in farmland status judgment.

[0041] By verifying the average agricultural data alignment deviation value obtained after primary agricultural data alignment optimization within the preset agricultural data alignment deviation range, an agricultural data alignment qualification verification value is obtained. When the agricultural data alignment qualification verification value is greater than 0 and the alignment qualification verification value to be analyzed is not greater than the preset agricultural data alignment qualification verification value, secondary agricultural data alignment optimization is triggered. This helps to achieve a precise upgrade from qualified to stable compliance. Secondary agricultural data alignment optimization then ensures the long-term stability of data alignment, preventing short-term qualification from masking long-term misalignment risks. Through the interconnection and mutual support of agricultural data alignment monitoring, primary agricultural data alignment optimization, and secondary agricultural data alignment optimization, a hierarchical and progressive data time-series correction closed loop can be achieved, thereby reducing the analysis error caused by the mixing of data from different time points and providing a reliable sample with time-series consistency for subsequent intelligent allocation decisions.

[0042] Furthermore, the specific process for assessing agricultural data allocation deviation is as follows: Obtain the agricultural data allocation deviation value used to assess the allocation deviation of the agricultural intelligent execution terminal; monitor the operation duration corresponding to the allocation instruction generated by the agricultural data and the actual operation duration of the intelligent execution terminal through a timer, and use the difference between the two as the agricultural data allocation deviation value; based on the agricultural data allocation deviation value, make a judgment: if the agricultural data allocation deviation value is greater than the preset agricultural data allocation deviation value, perform allocation optimization and deviation verification in the next adjacent preset allocation deviation window period; otherwise, after performing a preset number of agricultural data allocation deviation assessments, based on... The average agricultural data allocation deviation value is used for judgment. The preset agricultural data allocation deviation value is represented by the average value of agricultural data allocation deviation values ​​over a historical period. If the average agricultural data allocation deviation value is greater than the preset agricultural data allocation deviation value, allocation optimization and deviation verification are performed. Otherwise, the corresponding allocation instruction is marked as a qualified allocation instruction and stored in the preset agricultural allocation center. The preset allocation deviation window period represents the preset time period corresponding to the agricultural data allocation deviation assessment. The average agricultural data allocation deviation value represents the average value of agricultural data allocation deviation values ​​obtained after performing a preset number of agricultural data allocation deviation assessments.

[0043] It should be noted that allocation optimization and deviation verification are used to reduce the processing time of instruction parsing and task scheduling within the intelligent execution terminal. The specific process is as follows: The average agricultural data allocation deviation value and the sliding window size corresponding to agricultural retransmission requests monitored by a protocol analyzer (such as Wireshark, Tcpdump, Sniffer, etc.) are input into a preset timeout optimization table. The preset timeout adjustment ratio of agricultural data retransmission requests is read. Within the preset range of the timeout, the magnitude corresponding to the preset timeout adjustment ratio is used as the adjustment step size. Based on the initial retransmission request timeout time of agricultural data, a decreasing operation is performed. This helps to achieve accurate optimization of the transmission timeout time, reduce data transmission latency, and avoid invalid retransmissions. This improves the real-time transmission of agricultural data, ensures that the allocation deviation assessment can obtain the latest execution data in a timely manner, avoids inaccurate deviation judgment due to data lag, and ultimately guarantees allocation optimization. The system ensures timely delivery. After each decrement operation, if the newly acquired average agricultural data allocation deviation is not greater than the preset agricultural data allocation deviation, the system will stop optimizing and verifying the allocation. The agricultural data allocation deviation acquired in the next adjacent preset allocation time period will be marked as the allocation optimization value to be verified. If, after a preset number of allocation optimization and deviation verification operations, the average agricultural data allocation deviation is still greater than the preset agricultural data allocation deviation, an allocation optimization and deviation verification warning will be sent. The preset allocation time period represents the preset time period corresponding to the agricultural data allocation deviation assessment. Based on the allocation optimization value to be verified: if the allocation optimization value to be verified is still greater than the preset agricultural data allocation deviation, a smart execution terminal maintenance prompt will be sent; otherwise, the corresponding allocation instruction will be marked as a qualified allocation instruction and stored in the preset agricultural allocation center. This helps to trace and review high-deviation instructions, thereby improving the agricultural allocation center's ability to control instruction quality.

[0044] like Figure 4 The diagram shows a flowchart of an artificial intelligence-based intelligent allocation and management method for agricultural data provided in an embodiment of this invention. This method, applied to an artificial intelligence-based intelligent allocation and management system for agricultural data, includes: Dispatch Conflict Monitoring: During the dispatch of intelligent execution terminals based on agricultural data, agricultural data transmission conflict analysis is performed to output agricultural data transmission conflict analysis results for evaluating the situation of agricultural sensor data transmission conflicts and satellite image transmission loss. Based on the agricultural data transmission conflict analysis results, it is determined whether to conduct concurrent conflict-loss degree analysis to measure the degree of interference of agricultural sensor data transmission conflicts and satellite image transmission loss on the intelligent dispatch and management of agricultural data.

[0045] Alignment monitoring: After the agricultural data transmission conflict analysis is qualified, agricultural data alignment monitoring is carried out based on the agricultural data transmission conflict analysis results transmitted by the allocation conflict monitoring module. The agricultural data alignment monitoring results are output to evaluate the qualification of agricultural data time dimension alignment. Based on the agricultural data alignment monitoring results, it is determined whether to carry out primary agricultural data alignment optimization and secondary agricultural data alignment optimization.

[0046] Allocation Deviation Monitoring: After the agricultural data alignment monitoring is qualified, the agricultural data alignment monitoring results transmitted by the alignment monitoring module determine whether to conduct an agricultural data allocation deviation assessment in order to assess the allocation deviation of the agricultural intelligent execution terminal.

[0047] In this embodiment, agricultural data allocation deviation values ​​are obtained by conducting agricultural data allocation deviation assessment. When the agricultural data allocation deviation value exceeds a preset agricultural data allocation deviation value, allocation optimization and deviation verification are performed. This helps to achieve a dual guarantee of timely deviation correction and optimization effect verification, ensuring that optimization measures are truly effective rather than blindly adjusted. Through the interaction between agricultural data allocation deviation assessment, allocation optimization, and deviation verification, it helps to achieve closed-loop management from deviation discovery to deviation resolution and effect confirmation. Furthermore, the verified deviation data can be fed back to the AI ​​model to correct model parameters (such as adjusting the correlation algorithm between flight speed and spray volume), improving the initial accuracy of subsequent allocation commands.

[0048] In summary, this application's embodiments, by performing agricultural data transmission conflict analysis to output the analysis results, and determining whether to conduct concurrent conflict-loss analysis based on these results, help to screen high-quality agricultural data from the transmission source, preemptively eliminating "invalid and distorted data" caused by channel conflicts and image frame drops, and preventing low-quality data from entering subsequent analysis stages and causing cascading errors. After the agricultural data transmission conflict analysis is deemed satisfactory, agricultural data alignment monitoring is performed based on the analysis results to output the monitoring results. Based on these results, it is determined whether to perform primary and secondary agricultural data alignment optimization, which is beneficial for... To address the issue of time misalignment in multi-source agricultural data, a multi-level optimization approach is implemented. This approach quickly avoids immediate execution errors caused by time deviations (such as mismatched irrigation timing) through primary optimization, while secondary optimization ensures precise data alignment. This provides AI models with consistent analysis samples in the time dimension. After agricultural data alignment monitoring is deemed satisfactory, the approach determines whether to conduct an agricultural data allocation deviation assessment based on the acquired agricultural data alignment monitoring results. This helps to accurately capture the differences between AI allocation instructions and actual terminal operations, promptly identify potential deviations at the execution end, and thus improve the accuracy of intelligent allocation and management of agricultural data. This addresses the problem of low accuracy in existing technologies for intelligent allocation and management of agricultural data.

[0049] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. An intelligent agricultural data allocation and management system based on artificial intelligence, characterized in that, include: The module includes a conflict monitoring module, an alignment monitoring module, and a deviation monitoring module. The allocation conflict monitoring module is used to perform agricultural data transmission conflict analysis during the allocation of intelligent execution terminals based on agricultural data, so as to output agricultural data transmission conflict analysis results for evaluating the agricultural sensor data transmission conflict situation and satellite image transmission loss situation. Based on the agricultural data transmission conflict analysis results, it is determined whether to perform concurrent conflict-loss degree analysis to measure the degree of interference of agricultural sensor data transmission conflict and satellite image transmission loss on the intelligent allocation and management of agricultural data. The alignment monitoring module is used to monitor agricultural data alignment based on the agricultural data transmission conflict analysis results transmitted by the allocation conflict monitoring module after the agricultural data transmission conflict analysis is qualified. It outputs agricultural data alignment monitoring results to evaluate the qualification of agricultural data alignment in the time dimension. Based on the agricultural data alignment monitoring results, it determines whether to perform primary and secondary agricultural data alignment optimization. The primary agricultural data alignment optimization is used to ensure the accuracy of matching between the operation of the intelligent execution terminal and the actual needs of the farmland. The secondary agricultural data alignment optimization is used to ensure that the data alignment deviation meets the alignment quality standards on the basis of the primary agricultural data alignment optimization. The allocation deviation monitoring module is used to determine whether to conduct an agricultural data allocation deviation assessment based on the agricultural data alignment monitoring results transmitted by the alignment monitoring module after the agricultural data alignment monitoring is qualified, so as to assess the allocation deviation of the agricultural intelligent execution terminal.

2. The intelligent allocation and management system for agricultural data based on artificial intelligence according to claim 1, characterized in that, The agricultural data transmission conflict analysis includes agricultural sensor data transmission conflict analysis, which measures the concurrent transmission conflict of agricultural sensors, and agricultural image data loss analysis, which measures the loss of data during satellite image transmission. The specific process of the agricultural sensor data transmission conflict analysis is as follows: The concurrent transmission conflict of agricultural sensor data is quantified based on the total number of signal collisions corresponding to agricultural sensor data, and the concurrent conflict quantification value of agricultural data is obtained. If the concurrent conflict quantification value of agricultural data is greater than the preset concurrent conflict quantification value, the corresponding agricultural data concurrent conflict quantification value will be marked as the concurrent conflict value of agricultural data to be analyzed, triggering concurrent conflict-loss degree analysis; otherwise, the corresponding agricultural sensor data will be marked as qualified agricultural sensor data, triggering agricultural data alignment monitoring. The specific process of the agricultural image data loss analysis is as follows: The agricultural image data loss situation is quantified based on the number of missing frames in satellite imagery, and the agricultural data loss quantification value is obtained. If the agricultural data loss quantification value is greater than the preset agricultural data loss quantification value, the corresponding agricultural data loss quantification value will be marked as the agricultural data loss value to be analyzed, triggering concurrent conflict-loss degree analysis; otherwise, the corresponding agricultural image data will be marked as qualified agricultural image data, triggering agricultural data alignment monitoring.

3. The intelligent allocation and management system for agricultural data based on artificial intelligence according to claim 2, characterized in that, The specific process of the concurrent conflict-loss level analysis is as follows: Input the agricultural data to be analyzed into the concurrency conflict-loss level table, and output the concurrency conflict-loss level value; The agricultural data to be analyzed includes concurrent conflict values ​​and missing values ​​of the agricultural data to be analyzed; The concurrent conflict-loss level value includes the agricultural data concurrent conflict interference level value and the agricultural data loss interference level value; The impact of concurrent collision-loss levels on agricultural sensor concurrent transmission collision levels and satellite image loss levels on the acceptable interference of agricultural data transmission is determined based on concurrent collision-loss levels: If the concurrent conflict interference level of agricultural data is greater than the agricultural data loss interference level, concurrent conflict control will be performed in the next adjacent preset agricultural transmission window to alleviate channel contention pressure; otherwise, satellite image loss control will be performed in the next adjacent preset agricultural transmission window to reduce the probability of transmission loss.

4. The intelligent allocation and management system for agricultural data based on artificial intelligence according to claim 3, characterized in that, The specific process of concurrent conflict control is as follows: The concurrent conflict interference level of agricultural data and the channel bandwidth corresponding to agricultural sensor data are input into the preset concurrent conflict control list. The preset coding rate control ratio value corresponding to agricultural data is read. Within the preset range corresponding to the coding rate, the amplitude corresponding to the preset coding rate control ratio value is used as the adjustment step size. Based on the initial coding rate of agricultural data, a decreasing operation is performed. Each time a decreasing operation is performed, if the newly acquired concurrent conflict quantization value of agricultural data is not greater than the preset concurrent conflict quantization value, the concurrent conflict control is stopped. If the acquired concurrent conflict quantization value of agricultural data is still greater than the preset concurrent conflict quantization value after performing a preset number of concurrent conflict control operations, a concurrent conflict control warning is sent. The agricultural data includes agricultural sensor data and agricultural image data; The satellite image loss control means that within a preset range corresponding to the data frame, a data frame control operation is performed; The data frame control operation means that the amplitude corresponding to the preset data frame control ratio value is used as the adjustment step size, and the initial data frame of agricultural data is used to perform a decrement operation and trigger the data frame control operation detection. The data frame control operation detection means that after each data frame control operation, the agricultural data loss quantization value is reacquired. If the reacquired agricultural data loss quantization value is not greater than the preset agricultural data loss quantization value, the satellite image loss control is stopped. If the agricultural data loss quantization value obtained after performing a preset number of satellite image loss control operations is still greater than the preset agricultural data loss value, a concurrent conflict control warning is sent. The preset data frame control ratio is read by inputting the agricultural data loss quantification value and the channel bandwidth corresponding to the agricultural image data into the preset loss control list.

5. The intelligent allocation and management system for agricultural data based on artificial intelligence according to claim 4, characterized in that, The specific process of agricultural data alignment monitoring is as follows: Based on the number of successful agricultural data alignments, a quantitative measure is taken to assess the alignment of qualified agricultural data over time, and an agricultural data alignment monitoring value is output. Based on agricultural data alignment monitoring values ​​and preset agricultural data alignment monitoring values, a quantification is performed to measure the degree of alignment deviation in the time dimension of qualified agricultural data, and the agricultural data alignment deviation value is output. The average agricultural data alignment deviation value is statistically analyzed and judged: if the average agricultural data alignment deviation value is within the preset agricultural data alignment deviation range, an agricultural data allocation deviation assessment is triggered; otherwise, a first-level agricultural data alignment optimization is performed in the next adjacent preset alignment monitoring window. The qualified agricultural data includes qualified agricultural sensor data and qualified agricultural image data.

6. The intelligent allocation and management system for agricultural data based on artificial intelligence according to claim 5, characterized in that, The specific process of the first-level agricultural data alignment optimization is as follows: Input the agricultural data alignment deviation value and the corresponding synchronization clock pulse count into the preset clock frequency optimization table of agricultural data, and query the preset clock frequency adjustment ratio of agricultural data. Within the preset range of clock frequency, the amplitude corresponding to the preset clock frequency adjustment ratio obtained from the query is used as the adjustment step size for each adjustment, and the adjustment is incrementally made based on the initial clock frequency of the agricultural data. After each increment operation is completed, the average agricultural data alignment deviation value is reacquired. If the average agricultural data alignment deviation is within the preset agricultural data alignment deviation range, stop the first-level agricultural data alignment optimization and perform agricultural data alignment qualification verification. If the agricultural data alignment deviation value obtained after performing a preset number of first-level agricultural data alignment optimizations is still not within the preset agricultural data alignment deviation range, a first-level agricultural data alignment optimization warning level will be triggered. The Level 1 Agricultural Data Alignment Optimization Warning Classification indicates that agricultural data alignment deviation values ​​that are still outside the preset agricultural data alignment deviation range after performing Level 1 agricultural data alignment optimization a preset number of times are input into a preset machine learning model, outputting the Level 1 Agricultural Data Alignment Optimization Warning Classification and sending it to preset personnel.

7. The intelligent agricultural data allocation and management system based on artificial intelligence according to claim 6, characterized in that, The specific process for verifying the alignment of agricultural data is as follows; The degree of optimization of primary agricultural data alignment is quantified based on the monitoring values ​​of agricultural data alignment at the initial state and the final state of primary agricultural data alignment optimization, and the qualified verification value of agricultural data alignment is output. Judgment is made based on the alignment of agricultural data with qualified verification values: If the agricultural data alignment verification value is greater than 0, the corresponding agricultural data alignment verification value is marked as the alignment verification value to be analyzed and a second alignment verification is triggered; otherwise, an alignment inspection prompt is sent to the preset personnel. The secondary alignment qualification judgment is as follows: if the alignment qualification verification value to be analyzed is greater than the preset agricultural data alignment qualification verification value, an agricultural data allocation deviation assessment is performed; otherwise, a secondary agricultural data alignment optimization is triggered. The specific process of the secondary agricultural data alignment and optimization is as follows: Input the alignment qualification verification value to be analyzed and the corresponding synchronous clock pulse count of the agricultural data into the preset secondary clock frequency optimization table of the agricultural data, and query the preset secondary clock frequency adjustment ratio of the agricultural data. Determine whether the clock frequency of the final state of the first-level agricultural data alignment optimization is within the corresponding preset range. If it is, then within the preset range of clock frequency, use the amplitude corresponding to the preset second-level clock frequency adjustment ratio as the adjustment step size, and perform an incremental operation based on the clock frequency of the final state of the first-level agricultural data alignment optimization. Otherwise, send a second-level agricultural data alignment optimization alarm. Determine whether the validated aligned data meets the validation alignment conditions; If the conditions are met, stop the secondary agricultural data alignment optimization; otherwise, send a secondary agricultural data alignment optimization alert. The verification alignment data includes agricultural data alignment deviation values ​​and agricultural data alignment pass verification values ​​that are re-acquired after performing an incremental operation of a preset number of times. The verification alignment condition indicates that the reacquired agricultural data alignment deviation value is within the preset agricultural data alignment deviation range, and the agricultural data alignment qualification verification value is greater than the preset agricultural data alignment qualification verification value.

8. The intelligent allocation and management system for agricultural data based on artificial intelligence according to claim 7, characterized in that, The specific process for assessing the deviation in agricultural data allocation is as follows: Obtain agricultural data allocation deviation values ​​to assess the allocation deviation of agricultural intelligent execution terminals; The agricultural data allocation deviation value is represented by the result of a difference calculation between the operation time corresponding to the allocation instruction generated by the agricultural data and the actual operation time of the intelligent execution terminal. Judgment is based on the agricultural data allocation deviation value: if the agricultural data allocation deviation value is greater than the preset agricultural data allocation deviation value, allocation optimization and deviation verification are carried out in the next adjacent preset allocation deviation window period; otherwise, after evaluating the agricultural data allocation deviation a preset number of times, a judgment is made based on the obtained average agricultural data allocation deviation value. If the average agricultural data allocation deviation is greater than the preset agricultural data allocation deviation, allocation optimization and deviation verification are performed; otherwise, the corresponding allocation instruction is marked as a qualified allocation instruction and stored in the preset agricultural allocation center.

9. The intelligent allocation and management system for agricultural data based on artificial intelligence according to claim 8, characterized in that, The allocation optimization and deviation verification are used to reduce the processing time of instruction parsing and task scheduling within the intelligent execution terminal. The specific process is as follows: Input the average agricultural data allocation deviation value and the sliding window size corresponding to the agricultural retransmission request into the preset timeout optimization table, and read the preset timeout adjustment ratio of the agricultural data retransmission request. Within the preset timeout period, the adjustment step size is based on the magnitude corresponding to the preset timeout period adjustment ratio, and a decreasing operation is performed on the basis of the initial retransmission request timeout period for agricultural data. Each time a decrementing operation is performed, if the average agricultural data allocation deviation value that is re-acquired is not greater than the preset agricultural data allocation deviation value, the agricultural data allocation deviation obtained in the next adjacent preset allocation time period after allocation optimization and deviation verification will be marked as the allocation optimization value to be verified. If, after performing a preset number of allocation optimizations and deviation checks, the average agricultural data allocation deviation value is still greater than the preset agricultural data allocation deviation value, an allocation optimization and deviation check warning will be sent. The judgment is based on the optimization value to be verified: if the optimization value to be verified is still greater than the preset agricultural data allocation deviation value, a maintenance prompt is sent to the intelligent execution terminal; otherwise, the corresponding allocation instruction is marked as a qualified allocation instruction and stored in the preset agricultural allocation center.

10. An artificial intelligence-based intelligent allocation and management method for agricultural data, applied to the artificial intelligence-based intelligent allocation and management system for agricultural data as described in any one of claims 1-9, characterized in that, include: In the process of intelligent execution terminal allocation based on agricultural data, agricultural data transmission conflict analysis is performed to output agricultural data transmission conflict analysis results for evaluating the agricultural sensor data transmission conflict situation and satellite image transmission loss situation. Based on the agricultural data transmission conflict analysis results, it is determined whether to perform concurrent conflict-loss degree analysis to measure the degree of interference of agricultural sensor data transmission conflict and satellite image transmission loss on intelligent allocation and management of agricultural data. After the agricultural data transmission conflict analysis is qualified, agricultural data alignment monitoring is carried out based on the agricultural data transmission conflict analysis results transmitted by the allocation conflict monitoring module. The agricultural data alignment monitoring results are output to evaluate the qualification of agricultural data time dimension alignment. Based on the agricultural data alignment monitoring results, it is determined whether to carry out first-level agricultural data alignment optimization and second-level agricultural data alignment optimization. After the agricultural data alignment monitoring is qualified, the agricultural data alignment monitoring results transmitted by the alignment monitoring module determine whether to conduct an agricultural data allocation deviation assessment in order to assess the allocation deviation of the agricultural intelligent execution terminal.

Images