Smart agricultural planting environment data processing method and system based on multi-dimensional collaboration

Abstract

The invention belongs to the field of planting environment management, relates to a data analysis technology, is used for solving the problem that the prior art cannot combine multi-source heterogeneous data to perform integration analysis, and particularly relates to a multi-dimensional collaboration-based intelligent agricultural planting environment data processing method and system, which comprises a monitoring subsystem, a management subsystem and a database. The monitoring subsystem comprises a region segmentation module, a remote sensing monitoring module and a soil monitoring module which are in communication connection in sequence; the region segmentation module is used for carrying out region segmentation processing on an agricultural planting region; the agricultural planting region is segmented into a plurality of monitoring regions, and segmentation modes comprise rectangular block segmentation, annular segmentation and random segmentation; according to the application, a data coverage blind area is effectively avoided through a diversified segmentation mode of the region segmentation module, the remote sensing monitoring module sensitively captures growth state changes by utilizing vegetation spectral response characteristics, and the soil monitoring module quantifies a regional nutrition state through multipoint data aggregation and reduces local abnormal interference.

Description

Technical Field

[0001] This invention belongs to the field of planting environment management and involves data analysis technology, specifically a smart agricultural planting environment data processing method and system based on multi-dimensional collaboration. Background Technology

[0002] The core of smart agriculture planting environment data processing methods lies in breaking down data silos. By integrating and collaboratively analyzing data from different sources, types, and spatiotemporal scales, more accurate perception, intelligent decision-making, and autonomous control of the agricultural environment can be achieved.

[0003] The invention patent with announcement number CN119443623A discloses a system and method for timely adjustment of agricultural planting methods based on big data analysis. This system and method adjusts and controls agricultural planting methods in a timely manner according to the actual growth status of crops, thereby promoting rapid crop growth and improving agricultural planting results. However, this system cannot integrate and analyze multi-source heterogeneous data, and it cannot optimize planting management from a spatial planning perspective when there are deviations in the monitoring results of different dimensions.

[0004] To address the aforementioned technical problems, this application proposes a solution. Summary of the Invention

[0005] The purpose of this invention is to provide a smart agricultural planting environment data processing method and system based on multi-dimensional collaboration, which solves the problem that existing technologies cannot integrate and analyze multi-source heterogeneous data; The technical problem to be solved by this invention is: how to provide a smart agricultural planting environment data processing method and system that can integrate and analyze multi-source heterogeneous data based on multi-dimensional collaboration.

[0006] The objective of this invention can be achieved through the following technical solutions: A smart agricultural planting environment data processing system based on multi-dimensional collaboration includes a monitoring subsystem, a management subsystem, and a database; The monitoring subsystem includes a region segmentation module, a remote sensing monitoring module, and a soil monitoring module that are connected in sequence via communication. The region segmentation module is used to perform region segmentation processing on agricultural planting areas: dividing the agricultural planting areas into several monitoring areas, and the segmentation methods include rectangular segmentation, ring segmentation and random segmentation; The remote sensing monitoring module is used to collect and analyze remote sensing data of the monitoring area: generate a monitoring period and divide the monitoring period into several monitoring periods. At the end of the monitoring period, remote sensing images of agricultural planting areas are collected. The normalized vegetation index of the monitoring area is calculated by the difference between the red light and near-infrared band reflectance in the remote sensing images of the monitoring area. The monitoring area is marked as a normal growth area or an abnormal growth area by the normalized vegetation index. The soil monitoring module is used to monitor and analyze the soil nutrient status of the monitoring area: at the end of the monitoring period, the nutrient abnormality coefficient of the monitoring area is obtained, and the monitoring area is marked as a nutrient-normal area or a nutrient-abnormal area by the nutrient abnormality coefficient. The management subsystem includes a decision analysis module and a global management module; The decision analysis module is used to analyze management decisions in agricultural planting areas; The global management module is used to perform global statistical analysis on environmental data in agricultural planting areas.

[0007] Furthermore, the segmentation method is randomly selected; rectangular segmentation divides the agricultural planting area into several rectangular monitoring areas, and the process of ring segmentation includes: drawing several rays with the agricultural planting area as the center point, and the included angle between any adjacent rays is equal, and marking the area formed by the rays and the edge line of the agricultural planting area as the monitoring area; random segmentation randomly divides the agricultural planting area into several monitoring areas; the number and area values ​​of the monitoring areas obtained by different segmentation methods are equal.

[0008] Furthermore, the specific process of marking the monitoring area as a normal growth area or an abnormal growth area includes: obtaining the normalized vegetation threshold from the database, comparing the normalized vegetation index with the normalized vegetation threshold: if the normalized vegetation index is less than the normalized vegetation threshold, it is determined that the growth status of crops in the monitoring area does not meet the requirements during the monitoring period, and the corresponding monitoring area is marked as an abnormal growth area; if the normalized vegetation index is greater than or equal to the normalized vegetation threshold, it is determined that the growth status of crops in the monitoring area meets the requirements during the monitoring period, and the corresponding monitoring area is marked as a normal growth area.

[0009] Furthermore, the process of obtaining the nutritional abnormality coefficient in the monitoring area includes: setting up several monitoring points in the monitoring area, obtaining the content values ​​of nutritional parameters at the monitoring points, summing the content values ​​of the same nutritional parameter at all monitoring points in the monitoring area and taking the average value to obtain the evaluation value, comparing the evaluation value of the nutritional parameter with its preset content range: marking nutritional parameters whose content values ​​are within the corresponding content range as normal parameters; marking nutritional parameters whose content values ​​are outside the corresponding content range as abnormal parameters; and marking the ratio of the number of abnormal parameters to the total content of nutritional parameters as the nutritional abnormality coefficient.

[0010] Furthermore, the specific process of the decision analysis module in analyzing management decisions for agricultural planting areas includes: if the monitoring area is marked as a nutrient abnormality area, a nutrient supplementation signal is generated and sent to the mobile terminal of the management personnel; if the monitoring area is simultaneously marked as a nutrient normality area and a growth normality area, it is determined that the soil nutrient and growth status of the monitoring area meet the requirements and no action is taken; if the monitoring area is simultaneously marked as a nutrient normality area and a growth abnormality area, it is determined that the crop nutrient absorption capacity in the monitoring area is abnormal, a crop diagnosis signal is generated and sent to the mobile terminal of the management personnel.

[0011] Furthermore, the specific process of the global management module to perform global statistical analysis on environmental data of agricultural planting areas includes: at the end of the monitoring period, obtaining the number of times the monitoring area was marked as a nutrient-abnormal area and marking it as the out-of-standard value of the monitoring area; calculating the variance of the out-of-standard values ​​of all monitoring areas to obtain the supplementary balance coefficient of the monitoring period; and using the supplementary balance coefficient to determine whether the nutrient balance status of the agricultural planting area meets the requirements during the monitoring period.

[0012] Furthermore, the specific process for determining whether the nutritional balance status of agricultural planting areas meets the requirements during the monitoring period includes: obtaining the supplementary balance threshold from the database, comparing the supplementary balance coefficient with the supplementary balance threshold; if the supplementary balance coefficient is less than the supplementary balance threshold, it is determined that the nutritional balance status of agricultural planting areas meets the requirements during the monitoring period; if the supplementary balance coefficient is greater than or equal to the supplementary balance threshold, it is determined that the nutritional balance status of agricultural planting areas does not meet the requirements during the monitoring period, generating a re-segmentation signal and sending the re-segmentation signal to the region segmentation module. After receiving the re-segmentation signal, the region segmentation module re-segments the agricultural planting areas, and at the beginning of the next monitoring period, remote sensing data is collected and nutritional status is analyzed based on the re-segmented monitoring areas.

[0013] A smart agriculture planting environment data processing method and system based on multi-dimensional collaboration includes the following steps: Step 1: Divide the agricultural planting area into several monitoring zones; Step 2: Mark the monitoring area as either a normal growth area or an abnormal growth area; Step 3: Mark the monitoring area as either a nutritionally normal area or a nutritionally abnormal area; Step 4: Analyze the management decisions for agricultural planting areas; Step 5: Determine whether the nutritional balance of the agricultural planting area meets the requirements during the monitoring period.

[0014] The present invention has the following beneficial effects: 1. The diverse segmentation methods of the regional segmentation module effectively avoid data coverage blind spots. The remote sensing monitoring module uses the spectral response characteristics of vegetation to sensitively capture changes in growth status. The soil monitoring module quantifies the regional nutrient status and reduces local anomaly interference through multi-point data aggregation. The decision analysis module and global management module provide collaborative decision-making capabilities from local to global perspectives. As a result, the system effectively integrates multi-source heterogeneous data, breaks down data silos, and optimizes planting management from a spatial planning perspective when monitoring results in different dimensions deviate. This achieves precise perception and intelligent control of the agricultural environment, solving the technical problems of insufficient integration of multi-source heterogeneous data and lack of spatial optimization when monitoring deviations occur. 2. By centrally storing standardized normalized vegetation thresholds in a database, the remote sensing monitoring module calculates the normalized vegetation index of the monitored area at the end of the monitoring period. The system automatically compares this index with the thresholds in the database, strictly determines the growth status and marks the area based on the comparison results, thus ensuring that the marking process is entirely based on quantitative data and avoids interference from human factors. This mechanism allows the thresholds to be dynamically updated based on historical data or industry standards, ensuring the authority and adaptability of the comparison benchmark. At the same time, the rigid comparison rules of the thresholds strengthen the consistency of the system in multi-dimensional collaborative analysis, ultimately supporting the management subsystem to generate more accurate decision signals. 3. By setting up multiple monitoring points within the monitoring area for multi-point sampling, the spatial variation characteristics of soil nutrients are comprehensively captured; after obtaining the nutrient parameter content values ​​of each monitoring point, the average value is calculated to obtain the evaluation value, reducing random errors; the evaluation value is compared with the preset range to mark normal and abnormal parameters; finally, the ratio of the number of abnormal parameters to the total content of nutrient parameters is calculated as the nutrient abnormality coefficient, which standardizes the characterization of the severity of nutrient imbalance and provides a reliable basis for multi-dimensional collaborative analysis. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0016] Figure 1 This is an overall system block diagram of the present invention; Figure 2 This is a system block diagram of Embodiment 1 of the present invention; Figure 3 This is a system block diagram of Embodiment 2 of the present invention; Figure 4 This is a flowchart of the method in Embodiment 3 of the present invention. Detailed Implementation

[0017] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] In traditional smart agriculture planting environment data processing, the lack of a multi-source heterogeneous data integration mechanism prevents the effective fusion of data from different sources, types, and spatiotemporal scales. When monitoring results from different dimensions deviate, the system lacks the ability to optimize planting management from a spatial planning perspective, resulting in limited environmental perception accuracy, insufficient intelligence in the decision-making process, and reduced autonomy of the control mechanism, directly affecting the systematic nature and reliability of agricultural environmental data processing.

[0019] For example, in an orchard setting in hilly terrain, remote sensing images collected by the remote sensing monitoring module show anomalies in the Normalized Difference Vegetation Index (NDI) of a specific monitoring area, which is marked as an area of ​​abnormal growth. However, the nutrient anomaly coefficient obtained by the soil monitoring module indicates that the same area is marked as a nutrient-normal area. Because the system cannot integrate remote sensing data and soil monitoring information for collaborative analysis, it cannot determine whether the anomaly is caused by crop diseases or topographic shading factors. This prevents targeted adjustments to spatial planting management strategies, hindering the optimization of irrigation plans or fertilization layouts, and consequently affecting the consistency and adaptability of overall planting management.

[0020] If these problems are not addressed, data silos will continue to hinder the effective integration of environmental data, systematically constrain the accuracy of environmental perception, and potentially lead to directional biases in the decision-making and analysis process. Consequently, agricultural environmental regulation will fail to meet actual needs. In the long run, this will result in an imbalance in resource allocation mechanisms, a weakening of the ability to regulate crop growth, and a systemic decline in the overall effectiveness of planting management.

[0021] like Figure 1 As shown, the smart agricultural planting environment data processing system based on multi-dimensional collaboration includes a monitoring subsystem, a management subsystem, and a database.

[0022] Example 1: As Figure 2 As shown, the monitoring subsystem includes a region segmentation module, a remote sensing monitoring module, and a soil monitoring module that are connected in sequence via communication.

[0023] The region segmentation module is used to segment agricultural planting areas into several monitoring areas. Segmentation methods include rectangular segmentation, circular segmentation, and random segmentation, with the method selected randomly. Rectangular segmentation divides the agricultural planting area into several rectangular monitoring areas. Circular segmentation involves drawing several rays centered on the agricultural planting area, ensuring that the angles between any adjacent rays are equal. The area formed by the rays and the edge of the agricultural planting area is marked as the monitoring area. Random segmentation randomly divides the agricultural planting area into several monitoring areas. The number and area of ​​monitoring areas obtained by different segmentation methods are equal.

[0024] In practical applications, random selection of segmentation methods refers to a mechanism where the system dynamically selects region division strategies. This can be achieved using a pseudo-random number generator combined with a preset list of segmentation methods. The aim is to avoid the limitations of fixed segmentation strategies in adapting to specific terrains, ensuring that the region division process is not influenced by human preferences, thus providing an unbiased foundation for multi-dimensional data fusion. Specifically, rectangular block segmentation refers to dividing agricultural planting areas into regular grid-like regions. This can be implemented using a grid-based algorithm based on geographic information systems, aiming to achieve uniform spatial coverage and facilitate pixel-level processing of remote sensing images and systematic deployment of soil monitoring points. Ring segmentation refers to generating radial regions based on a center point. This can be implemented using an angle-division algorithm in a polar coordinate system, aiming to analyze the environmental gradient change patterns centered on irrigation sources or management cores. Random segmentation refers to generating irregularly shaped monitoring areas. This can be implemented using a Voronoi diagram algorithm combined with random seed point generation, aiming to simulate natural variation patterns and effectively capture local anomalies in complex terrains. Specifically, the fact that the number and area values ​​of monitoring areas obtained by different segmentation methods are equal means that no matter what segmentation method is used, the system forces the total number of areas and the area of ​​a single area to be consistent. This can be achieved by dynamically adjusting the segmentation parameters. The purpose is to eliminate the interference of the segmentation method itself on the comparability of data, so that multi-dimensional data can be cross-validated on a unified spatial scale.

[0025] This application's solution achieves spatial alignment of multi-dimensional data through a collaborative design of a random selection mechanism for segmentation and standardized regional specifications. During region segmentation, the system first activates the corresponding segmentation algorithm based on the randomly selected segmentation strategy. When rectangular segmentation is selected, the system generates a regular rectangular grid; when ring segmentation is selected, the system divides the area radially at equal angles with the geometric center of the planting area as the origin; when random segmentation is selected, the system generates irregular regions. Regardless of the segmentation method used, the system dynamically adjusts the segmentation parameters to ensure that the total number of generated monitoring regions and the area of ​​each individual region are strictly consistent. This design allows vegetation index data acquired by the remote sensing monitoring module and nutrient status data acquired by the soil monitoring module to be compared and analyzed on perfectly matched spatial units, thereby eliminating data bias caused by inconsistent regional specifications and providing an accurate spatial reference benchmark for the decision analysis module.

[0026] The remote sensing monitoring module is used to collect and analyze remote sensing data in the monitoring area: it generates a monitoring period and divides it into several monitoring periods. At the end of each monitoring period, it collects remote sensing images of agricultural planting areas. It calculates the normalized vegetation index (NVI) of the monitoring area by analyzing the difference in reflectance between red and near-infrared bands in the remote sensing images of the monitoring area. It obtains the NVI threshold from the database and compares the NVI with the NVI threshold: if the NVI is less than the NVI threshold, it is determined that the growth status of crops in the monitoring area during the monitoring period does not meet the requirements, and the corresponding monitoring area is marked as an abnormal growth area; if the NVI is greater than or equal to the NVI threshold, it is determined that the growth status of crops in the monitoring area during the monitoring period meets the requirements, and the corresponding monitoring area is marked as a normal growth area.

[0027] The normalized vegetation threshold (NVT) is a preset benchmark value used to assess vegetation growth status. It can be achieved using a dynamic average value derived from historical monitoring data or a fixed threshold specified by industry standards. The aim is to provide an objective and authoritative comparison standard, avoiding arbitrariness in threshold selection and ensuring that the threshold is adaptively adjusted according to actual planting conditions. Comparing the normalized vegetation index (NVI) with the NVT threshold involves performing an objective judgment through numerical quantification. This can be achieved automatically using embedded software algorithms to eliminate subjective bias and ensure that growth status assessment strictly relies on measurable vegetation index data. In the judgment logic, when the NVI is less than the NVT threshold, it is marked as an abnormal growth area. This rule can be understood as a precise mechanism for capturing the correlation between low vegetation index and hindered growth, aiming to identify abnormal growth areas promptly and avoid missed judgments. Conversely, when the NVI is greater than or equal to the NVT threshold, it is marked as a normal growth area. This setting can be understood as a reasonable definition of the healthy growth boundary, aiming to prevent excessive intervention and unify the marking standard through rigid comparison rules.

[0028] In practical applications, the normalized vegetation thresholds stored in the database can be dynamically updated based on the historical growth data of specific crop types. When the remote sensing monitoring module obtains the normalized vegetation index of a certain monitoring area, the system automatically compares it with the threshold in the database. If the index value is lower than the threshold, it is marked as an area with abnormal growth; otherwise, it is marked as an area with normal growth. This process is automatically executed by the decision analysis module without human intervention.

[0029] The soil monitoring module is used to monitor and analyze the soil nutrient status of the monitoring area. Several monitoring points are set up within the monitoring area to obtain the content values ​​of nutrient parameters at these points. The average value of the content values ​​of the same nutrient parameter at all monitoring points within the monitoring area is summed to obtain an evaluation value. The evaluation value of the nutrient parameter is compared with its preset content range: nutrient parameters with content values ​​within the corresponding range are marked as normal parameters; nutrient parameters with content values ​​outside the corresponding range are marked as abnormal parameters. The ratio of the number of abnormal parameters to the total content of nutrient parameters is marked as the nutrient anomaly coefficient. A nutrient anomaly threshold is obtained from the database, and the nutrient anomaly coefficient is compared with the nutrient anomaly threshold: if the nutrient anomaly coefficient is less than the nutrient anomaly threshold, the soil nutrient status of the monitoring area during the monitoring period is determined to meet the requirements, and the corresponding monitoring area is marked as a nutrient-normal area; if the nutrient anomaly coefficient is greater than or equal to the nutrient anomaly threshold, the soil nutrient status of the monitoring area during the monitoring period is determined to not meet the requirements, and the corresponding monitoring area is marked as a nutrient-abnormal area.

[0030] Among them, monitoring points refer to sampling locations distributed within the monitoring area. They can be set up in a grid-like or random distribution to ensure data coverage of the entire area and avoid the randomness of single-point measurements; the content values ​​of nutrient parameters refer to the concentrations of key elements such as nitrogen, phosphorus, and potassium in the soil, which can be obtained through soil sensors or laboratory analysis methods, serving as the basis of raw data; the assessment value refers to the regional average nutrient level, which can be calculated by arithmetic mean or weighted average, effectively eliminating local abnormal fluctuations; the preset content range refers to the threshold range of nutrient parameters set according to agricultural science, which can be dynamically adjusted based on crop type and soil type, used to objectively determine nutrient status; the nutrient anomaly coefficient is an indicator that quantifies the degree of nutrient imbalance, which can be expressed as a ratio to represent the proportion of anomalies, thus standardizing the coefficient.

[0031] Nutrient-abnormal areas refer to regions marked after soil nutrient status monitoring and analysis of the monitored area using a soil monitoring module. These areas can be determined based on comparisons of nutrient parameter values ​​with preset ranges, aiming to quickly identify areas with insufficient soil nutrients. Nutrient replenishment signals are instruction signals indicating the need for soil nutrient replenishment. These can be delivered via SMS, mobile application push notifications, or email, ensuring timely notification and targeted intervention by management personnel. Mobile terminals refer to mobile communication devices used by management personnel, including smartphones, tablets, or wearable devices, providing convenient real-time notification channels. Normal growth areas refer to regions marked after remote sensing data collection and analysis of the monitored area using a remote sensing monitoring module. These areas can be determined based on comparisons of the normalized vegetation index (NVI) and the normalized vegetation threshold, aiming to objectively assess crop growth status. Abnormal crop nutrient absorption capacity indicates that the system infers nutrient absorption obstacles in the crop itself. This can be determined based on combinations of nutrient-normal but abnormal growth conditions, aiming to accurately distinguish between soil problems and crop-related issues.

[0032] Example 2: Figure 3 As shown, the management subsystem includes a decision analysis module and a global management module.

[0033] The decision analysis module is used to analyze management decisions in agricultural planting areas: if the monitoring area is marked as a nutrient abnormality area, a nutrient supplementation signal is generated and sent to the mobile terminal of the management personnel; if the monitoring area is marked as both a nutrient normality area and a growth normality area, it is determined that the soil nutrient and growth status of the monitoring area meet the requirements and no action is taken; if the monitoring area is marked as both a nutrient normality area and a growth abnormality area, it is determined that the crop nutrient absorption capacity in the monitoring area is abnormal, a crop diagnosis signal is generated and sent to the mobile terminal of the management personnel.

[0034] Among them, the out-of-calibration value refers to the cumulative number of times a monitored area is marked as a nutrient-abnormal area within the monitoring period. It can be implemented using database records or counters. Its purpose is to quantify the frequency of nutrient abnormalities in the area and avoid interference from real-time data fluctuations on the evaluation results. The supplementary balance coefficient refers to the variance of the out-of-calibration values ​​of all monitored areas. It can be implemented using statistical analysis algorithms or variance calculation modules. Its purpose is to characterize the spatial uniformity of the distribution of nutrient abnormalities. The smaller the variance, the more balanced the distribution of abnormalities. The nutrient balance status determination refers to assessing the degree of nutrient balance in the entire agricultural planting area based on the supplementary balance coefficient. It can be implemented using rule engines or dynamic threshold comparison mechanisms. Its purpose is to transform quantitative indicators into actionable decision-making basis and provide data support for regional segmentation optimization.

[0035] The global management module is used to perform global statistical analysis of environmental data in agricultural planting areas. At the end of the monitoring period, it acquires the number of times the monitoring area is marked as a nutrient-abnormal area and marks it as the outlier value of the monitoring area. It calculates the variance of the outlier values ​​of all monitoring areas to obtain the supplementary balance coefficient for the monitoring period. It obtains the supplementary balance threshold from the database and compares the supplementary balance coefficient with the supplementary balance threshold. If the supplementary balance coefficient is less than the supplementary balance threshold, it is determined that the nutrient balance status of the agricultural planting area meets the requirements during the monitoring period. If the supplementary balance coefficient is greater than or equal to the supplementary balance threshold, it is determined that the nutrient balance status of the agricultural planting area does not meet the requirements during the monitoring period. A resegmentation signal is generated and sent to the region segmentation module. After receiving the resegmentation signal, the region segmentation module resegments the agricultural planting area. At the beginning of the next monitoring period, it performs remote sensing data acquisition and nutrient status analysis based on the resegmented monitoring areas.

[0036] Among them, the supplementary balance coefficient is a quantitative indicator that reflects the spatial dispersion of nutrient abnormalities in the monitoring area, calculated through statistical variance. It can be implemented using analysis of variance to accurately capture local spatial differences in nutrient abnormalities and avoid the shortcomings of simple average statistics in representing the uniformity of distribution. The supplementary balance threshold is a preset benchmark value used to determine the nutrient balance status. It can be set using historical data or empirical values ​​stored in the database to provide an objective basis for judgment and ensure the reliability and adaptability of the system's assessment of nutrient distribution status. The re-segmentation signal is a control command generated when the nutrient balance status does not meet the requirements. It can be implemented in the form of digital signals or communication protocols to trigger the optimization operation of the area segmentation module in a timely manner and realize the dynamic adjustment of area division.

[0037] Specifically, the proposed solution obtains the out-of-range values ​​of each monitoring area at the end of the monitoring cycle, calculates the variance of these out-of-range values ​​to obtain a supplementary balance coefficient, which directly characterizes the uniformity of the distribution of nutrient abnormalities. Subsequently, the supplementary balance coefficient is compared with a preset supplementary balance threshold, and the nutrient balance status is determined based on the comparison result: if the coefficient is less than the threshold, it indicates that the distribution is uniform and meets the requirements; if the coefficient is greater than or equal to the threshold, it indicates that the distribution is uneven and does not meet the requirements. At this time, a re-segmentation signal is generated and sent to the region segmentation module. The region segmentation module responds to the signal and re-segments the agricultural planting area, so that data collection and analysis are carried out based on the optimized region in the next monitoring cycle, realizing dynamic optimization of planting management from the perspective of spatial distribution.

[0038] Example 3: Figure 4 As shown, the smart agriculture planting environment data processing method and system based on multi-dimensional collaboration includes the following steps: Step 1: Divide the agricultural planting area into several monitoring zones; Step 2: Mark the monitoring area as either a normal growth area or an abnormal growth area; Step 3: Mark the monitoring area as either a nutritionally normal area or a nutritionally abnormal area; Step 4: Analyze the management decisions for agricultural planting areas; Step 5: Determine whether the nutritional balance of the agricultural planting area meets the requirements during the monitoring period.

[0039] Based on a multi-dimensional collaborative smart agriculture planting environment data processing method and system, during operation, the region segmentation module first performs region segmentation processing on the agricultural planting area, dividing the planting area into several monitoring areas. The segmentation method can choose one of rectangular segmentation, ring segmentation, or random segmentation to adapt to diverse terrain features and ensure that the monitoring areas are representative in spatial distribution, thus providing a structured basis for subsequent multi-dimensional analysis. The remote sensing monitoring module divides the monitoring period into several monitoring time periods within the generated monitoring period, and acquires remote sensing images of the agricultural planting area at the end of each monitoring time period. By calculating the difference in reflectance between red light and near-infrared bands in the remote sensing images, the normalized vegetation index of the monitoring area is obtained, and the monitoring area is marked as a normal growth area or a growth abnormal area based on this index. The soil monitoring module simultaneously acquires the nutrient abnormality coefficient of the monitoring area at the end of the monitoring time period, and marks the monitoring area as a nutrient normal area or a nutrient abnormal area based on this coefficient. The decision analysis module in the management subsystem performs management decision analysis based on the region marking results, while the global management module performs global statistical analysis on the environmental data, thereby transforming the scattered monitoring results into systematic indicators.

[0040] The above description is merely an example and illustration of the structure of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined in the claims, all of which should fall within the protection scope of the present invention.

[0041] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0042] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A smart agricultural planting environment data processing system based on multi-dimensional collaboration, characterized in that: It includes a monitoring subsystem, a management subsystem, and a database; The monitoring subsystem includes a region segmentation module, a remote sensing monitoring module, and a soil monitoring module that are connected in sequence via communication. The region segmentation module is used to perform region segmentation processing on agricultural planting areas: dividing the agricultural planting areas into several monitoring areas, and the segmentation methods include rectangular segmentation, ring segmentation and random segmentation; The remote sensing monitoring module is used to collect and analyze remote sensing data of the monitoring area: generate a monitoring period and divide the monitoring period into several monitoring periods. At the end of the monitoring period, remote sensing images of agricultural planting areas are collected. The normalized vegetation index of the monitoring area is calculated by the difference between the red light and near-infrared band reflectance in the remote sensing images of the monitoring area. The monitoring area is marked as a normal growth area or an abnormal growth area by the normalized vegetation index. The soil monitoring module is used to monitor and analyze the soil nutrient status of the monitoring area: at the end of the monitoring period, the nutrient abnormality coefficient of the monitoring area is obtained, and the monitoring area is marked as a nutrient-normal area or a nutrient-abnormal area by the nutrient abnormality coefficient. The management subsystem includes a decision analysis module and a global management module; The decision analysis module is used to analyze management decisions in agricultural planting areas; The global management module is used to perform global statistical analysis on environmental data in agricultural planting areas.

2. The smart agricultural planting environment data processing system based on multi-dimensional collaboration according to claim 1, characterized in that, The segmentation method is randomly selected; rectangular segmentation divides the agricultural planting area into several rectangular monitoring areas; the process of ring segmentation includes: drawing several rays with the agricultural planting area as the center point, and the included angle between any adjacent rays is equal, and marking the area formed by the rays and the edge line of the agricultural planting area as the monitoring area; random segmentation randomly divides the agricultural planting area into several monitoring areas; the number and area of ​​monitoring areas obtained by different segmentation methods are equal.

3. The smart agricultural planting environment data processing system based on multi-dimensional collaboration according to claim 2, characterized in that, The specific process of marking a monitoring area as a normal growth area or an abnormal growth area includes: obtaining the normalized vegetation threshold from the database, comparing the normalized vegetation index with the normalized vegetation threshold; if the normalized vegetation index is less than the normalized vegetation threshold, it is determined that the growth status of crops in the monitoring area does not meet the requirements during the monitoring period, and the corresponding monitoring area is marked as an abnormal growth area; if the normalized vegetation index is greater than or equal to the normalized vegetation threshold, it is determined that the growth status of crops in the monitoring area meets the requirements during the monitoring period, and the corresponding monitoring area is marked as a normal growth area.

4. The smart agricultural planting environment data processing system based on multi-dimensional collaboration according to claim 3, characterized in that, The process of obtaining the nutritional abnormality coefficient in the monitoring area includes: setting up several monitoring points in the monitoring area, obtaining the content values ​​of nutritional parameters at the monitoring points, summing the content values ​​of the same nutritional parameter at all monitoring points in the monitoring area and taking the average value to obtain the evaluation value, comparing the evaluation value of the nutritional parameter with its preset content range: nutritional parameters whose content values ​​are within the corresponding content range are marked as normal parameters; nutritional parameters whose content values ​​are outside the corresponding content range are marked as abnormal parameters; and the ratio of the number of abnormal parameters to the total content of nutritional parameters is marked as the nutritional abnormality coefficient.

5. The smart agricultural planting environment data processing system based on multi-dimensional collaboration according to claim 4, characterized in that, The specific process of the decision analysis module in analyzing management decisions for agricultural planting areas includes: if the monitoring area is marked as a nutrient abnormality area, a nutrient supplementation signal is generated and sent to the mobile terminal of the management personnel; if the monitoring area is marked as both a nutrient normality area and a growth normality area, it is determined that the soil nutrient and growth status of the monitoring area meet the requirements and no action is taken; if the monitoring area is marked as both a nutrient normality area and a growth abnormality area, it is determined that the crop nutrient absorption capacity in the monitoring area is abnormal, a crop diagnosis signal is generated and sent to the mobile terminal of the management personnel.

6. The smart agricultural planting environment data processing system based on multi-dimensional collaboration according to claim 5, characterized in that, The specific process of the global management module to perform global statistical analysis on environmental data of agricultural planting areas includes: at the end of the monitoring period, obtaining the number of times the monitoring area was marked as a nutrient-abnormal area and marking it as the out-of-standard value of the monitoring area; calculating the variance of the out-of-standard values ​​of all monitoring areas to obtain the supplementary balance coefficient of the monitoring period; and using the supplementary balance coefficient to determine whether the nutrient balance status of the agricultural planting area meets the requirements during the monitoring period.

7. The smart agricultural planting environment data processing system based on multi-dimensional collaboration according to claim 6, characterized in that, The specific process for determining whether the nutritional balance status of agricultural planting areas meets the requirements during the monitoring period includes: obtaining the supplementary balance threshold from the database, comparing the supplementary balance coefficient with the supplementary balance threshold; if the supplementary balance coefficient is less than the supplementary balance threshold, it is determined that the nutritional balance status of agricultural planting areas meets the requirements during the monitoring period; if the supplementary balance coefficient is greater than or equal to the supplementary balance threshold, it is determined that the nutritional balance status of agricultural planting areas does not meet the requirements during the monitoring period, generating a re-segmentation signal and sending the re-segmentation signal to the region segmentation module. After receiving the re-segmentation signal, the region segmentation module re-segments the agricultural planting area, and at the beginning of the next monitoring period, remote sensing data is collected and nutritional status is analyzed based on the re-segmented monitoring area.

8. A smart agriculture planting environment data processing method based on multi-dimensional collaboration, characterized in that, Includes the following steps: Step 1: Divide the agricultural planting area into several monitoring zones; Step 2: Mark the monitoring area as either a normal growth area or an abnormal growth area; Step 3: Mark the monitoring area as either a nutritionally normal area or a nutritionally abnormal area; Step 4: Analyze the management decisions for agricultural planting areas; Step 5: Determine whether the nutritional balance of the agricultural planting area meets the requirements during the monitoring period.

Images