Agricultural information sharing management method based on multi-source data fusion

Abstract

The present invention relates to the field of information sharing and management technology. It provides an agricultural information sharing and management method based on multi-source data fusion, spatially calibrates multi-source data, and constructs an agricultural health spatial dataset. It mines the correlation between microbial communities and soil health through spatial correlation network analysis and constructs a spatial correlation model. It optimizes the allocation of agricultural resources. It also generates a personalized agricultural resource allocation plan for each region through a spatial optimization algorithm. After the agricultural resource allocation plan is implemented, a correction plan is automatically generated based on spatial feedback from microbial communities and soil health, and an agricultural health assessment report is generated. The present invention establishes a closed-loop feedback system through an adaptive optimization mechanism, dynamically adjusts management measures based on real-time monitoring data, and ensures that the management strategy is always in an optimal state.

Description

Technical Field

[0001] The present invention relates to the technical field of information sharing management, and in particular to an agricultural information sharing management method based on multi-source data fusion. Background Art

[0002] As global agricultural development enters a new stage of precision, intelligence, and sustainability, the application of information technology in agriculture is becoming increasingly widespread. In recent years, the development of agricultural information technology has shown a diversified trend, and the application potential of multi-source data in agricultural production has been widely recognized. Agricultural information sharing and management based on multi-source data provides important support for the rational use of agricultural resources and the improvement of agricultural production efficiency. Currently, multi-source data fusion technology provides accurate decision-making basis for farmland management, pest and disease control, crop yield prediction, etc. by integrating spatial data, temporal data, and attribute data. In addition, dynamic monitoring technology of soil health and microbial communities has gradually become an important research direction in agricultural health management.

[0003] The development of these technologies provides important solutions for addressing issues such as resource waste, environmental pollution, and low production efficiency in agricultural production. However, existing multi-source data fusion and sharing technologies still face bottlenecks such as strong data heterogeneity, inaccurate spatial analysis, and a lack of efficient data sharing mechanisms, making them difficult to meet the complex needs of refined agricultural management. Furthermore, resource optimization solutions lack the ability to tailor them to microbial communities and soil health, resulting in poor applicability. Summary of the Invention

[0004] The embodiments of the present invention provide an agricultural information sharing and management method based on multi-source data fusion, thereby at least to a certain extent solving the problems of strong heterogeneity of multi-source data and poor resource allocation effect.

[0005] Other features and advantages of the present invention will become apparent from the following detailed description, or may be learned in part by practice of the present invention.

[0006] According to one aspect of the present invention, an agricultural information sharing and management method based on multi-source data fusion is provided, comprising: collecting and preprocessing multi-source data, spatially calibrating the multi-source data, and constructing an agricultural health spatial dataset; based on the 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 and allocating agricultural resources according to the spatial correlation model; and generating a personalized agricultural resource allocation plan for each region through a spatial optimization algorithm, combining microbial community health data and soil environmental characteristics; after the implementation of the agricultural resource allocation plan, automatically generating a correction plan based on spatial feedback from microbial communities and soil health; and generating an agricultural health assessment report by integrating all collected data and the optimized agricultural resource allocation plan.

[0007] In the present invention, based on the above-mentioned scheme, the multi-source data is spatially calibrated, including: obtaining geographic information data of the agricultural area, using GIS software to connect the collected various data with the geographic coordinate system; and spatially calibrating different data sources to have a unified geographic coordinate system.

[0008] In the present invention, based on the above-mentioned solution, the remote sensing image data in the multi-source data is preprocessed, including radiation correction, geometric correction and atmospheric correction.

[0009] In the present invention, based on the aforementioned scheme, the correlation between microbial communities and soil health is mined through spatial correlation network analysis, including: using spatial statistical methods to calculate the spatial correlation between microbial communities and soil health; converting the spatial correlation into a spatial network, wherein each agricultural unit is regarded as a node, and the edge weights between nodes represent the spatial correlation between them; using a community detection algorithm to calculate the modularity Q and identify areas with strong correlation in the spatial network.

[0010] In the present invention, based on the above solution, the spatial correlation , including: when When , it indicates that there is positive autocorrelation, that is, the health status of adjacent regions is similar; when When , it indicates that there is negative autocorrelation, that is, the health status of adjacent regions is quite different; when , indicating no autocorrelation.

[0011] In the present invention, based on the aforementioned scheme, the construction of the multidimensional spatial correlation model includes: modeling the interaction of spatial data based on the spatial correlation and the modularity Q: taking the spatial correlation as the spatial autocorrelation term and the modularity Q as the network structure strength term to construct a multidimensional spatial correlation model; using the cross-validation method to evaluate the multidimensional spatial correlation model, by dividing the data into a training set and a validation set, and performing training and validation on multiple subsets to reduce the risk of model overfitting.

[0012] In the present invention, based on the aforementioned scheme, agricultural resources are optimized and allocated according to the spatial correlation model, including: collecting resource demand data of agricultural areas and constructing resource demand characteristics for each agricultural unit; modeling resource demand according to crop planting conditions, and obtaining a unified resource demand model through data integration; integrating microbial community health data and spatial correlation model output into the resource demand model; adjusting water source demand and fertilizer demand according to the health status of the microbial community; and for each agricultural unit, adjusting the selection of crop types according to the soil health index.

[0013] In the present invention, based on the above scheme, the water source demand is adjusted according to the health status of the microbial community, and the expression is:

[0014] ;

[0015] in, For the region water demand, For basic water needs, For the region The microbial health index, is the regulating factor, which represents the effect of microbial health status on water demand;

[0016] The fertilizer requirement is adjusted as follows:

[0017] ;

[0018] in, For the region Fertilizer requirements, For basic fertilizer requirements, is a regulating factor that represents the effect of microbial health status on fertilizer demand.

[0019] In the present invention, based on the aforementioned scheme, the spatial optimization algorithm is combined with microbial community health data and soil environmental characteristics, including: defining an objective function based on integrated resource demand data and a spatial correlation model; the objective function uses weighted calculations to ensure that resource waste is minimized while maximizing crop yield, soil health, and microbial community health; using a particle swarm optimization algorithm or a genetic algorithm to optimize resource allocation, and gradually finding the optimal solution by simulating population evolution.

[0020] In the present invention, based on the aforementioned scheme, the correction scheme is automatically generated according to the spatial feedback of microbial communities and soil health, including: using spatial correlation models and real-time collected data to analyze the health status of microbial communities and soil health; after monitoring the changes in the status of microbial communities and soil health, adjusting agricultural management measures through an adaptive optimization mechanism; the adaptive optimization mechanism uses historical data, real-time data and the results of spatial correlation analysis to automatically determine the adaptability of current management measures and make necessary adjustments; based on the adjustments of the adaptive optimization mechanism, a correction scheme is automatically generated.

[0021] In the technical solution of the present invention, the problems of inconsistent spatial distribution and large precision differences between different data sources are solved through multi-source data collection and preprocessing technology, and a unified agricultural health spatial data set is constructed, providing a reliable data basis for accurate analysis of the agricultural ecological environment. Secondly, the present invention innovatively introduces a spatial correlation network analysis method, using spatial statistics and network analysis technology to deeply explore the complex correlation between microbial communities and soil health, and by constructing a multidimensional spatial correlation model, it realizes the accurate modeling of multi-factor interactions in agricultural ecosystems, which can reveal the spatial interactions between agricultural units and their influence paths, and provide a scientific basis for the optimal allocation of resources.

[0022] In addition, the present invention comprehensively considers microbial health, soil environmental characteristics and crop needs, and dynamically adjusts water sources, fertilizers and crop planting patterns, which not only improves the efficiency of agricultural resource utilization but also ensures the health and stability of the ecosystem.

[0023] Unlike traditional agricultural management methods, this invention establishes a closed-loop feedback system through an adaptive optimization mechanism, dynamically adjusts management measures based on real-time monitoring data, ensures that management strategies are always in the optimal state, and realizes the visualization and quantification of agricultural ecological health by generating agricultural health assessment reports, providing important support for long-term planning and scientific decision-making.

[0024] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings are incorporated into and constitute a part of this specification, illustrate embodiments consistent with the present invention, and together with the description, serve to explain the principles of the present invention. Obviously, the drawings described below are only some embodiments of the present invention, and it is clear that those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0026] Figure 1 The flowchart of the agricultural information sharing and management method based on multi-source data fusion in one embodiment of the present invention is schematically shown.

[0027] Figure 2 The flowchart of constructing a spatial correlation model in one embodiment of the present invention is schematically shown. DETAILED DESCRIPTION

[0028] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0029] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present invention. However, it will be appreciated by those skilled in the art that the technical solutions of the present invention can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring various aspects of the present invention.

[0030] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0031] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, while others may be combined or partially combined. Therefore, the actual execution order may vary depending on the actual situation.

[0032] The implementation details of the technical solution of the present invention are described in detail below:

[0033] Figure 1FIG2 shows a flow chart of an agricultural information sharing and management method based on multi-source data fusion according to an embodiment of the present invention. Figure 1 As shown, the agricultural information sharing and management method based on multi-source data fusion includes at least steps S1 to S5, which are described in detail as follows:

[0034] S1: Collect and preprocess multi-source data, perform spatial calibration on the multi-source data, and construct an agricultural health spatial dataset.

[0035] S1.1: In agricultural production areas, collect multi-source data through sensor networks, remote sensing technology, and Internet of Things devices.

[0036] It also includes the configuration of a variety of sensors, including soil moisture sensors, temperature and humidity sensors, pH sensors, plant growth monitoring cameras, etc. In addition, the use of microbial community sampling tools to collect soil samples and analyze indicators such as microbial species, quantity and activity

[0037] The multi-source data collected include soil moisture, temperature, pH value, vegetation index (NDVI), crop growth status, and microbial community information.

[0038] Among them, it is necessary to ensure that the data covers the time span and spatial scope of the agricultural area. The data should cover multiple seasons and conduct multi-point sampling among different plots of farmland to improve the representativeness and comprehensiveness of the data.

[0039] It should be noted that a high-density time-synchronized sensor deployment scheme is used when collecting data to ensure accurate alignment of timestamps for various types of data, solve the time mismatch problem of different data sources in the traditional agricultural data collection process, provide high-temporal resolution data, and provide a reliable basis for subsequent spatial calibration and analysis.

[0040] S1.2: Preprocess the collected data, especially the collected remote sensing image data, including radiometric correction, geometric correction, and atmospheric correction, to ensure the consistency of different data sources.

[0041] Specifically, geographic information system (GIS) technology is used to spatially match ground-collected data with remote sensing data to achieve spatial calibration of the data.

[0042] For data from different sources, standardized methods are used for data preprocessing to ensure that they have uniform spatial resolution and standards for subsequent analysis.

[0043] The better approach is to combine the calibration of geographic information systems and multi-source data, adopt a multi-level spatial alignment method, and set different spatial matching accuracies according to the distribution characteristics of different data sources, so that spatial calibration can adapt to the data heterogeneity in complex agricultural environments and improve calibration accuracy.

[0044] Specifically, obtain geographic information data of agricultural areas, use GIS software (such as ArcGIS, QGIS) to connect the collected data with the geographic coordinate system; perform spatial calibration on different data sources to make them have a unified geographic coordinate system to ensure data accuracy.

[0045] Furthermore, the construction of the agricultural health spatial dataset uses a multidimensional spatial mapping algorithm to uniformly map data of different dimensions into a spatial framework to ensure the compatibility and comparability of the data.

[0046] It should be noted that through data fusion, the spatial consistency of various types of data can be ensured, and basic data support can be provided for subsequent agricultural health analysis and optimization decisions.

[0047] S2: Based on the agricultural health spatial dataset, the correlation between microbial communities and soil health was explored through spatial correlation network analysis, and a spatial correlation model was constructed.

[0048] First, soil health parameters (such as moisture, temperature, pH value, etc.) and microbial community data (such as microbial species, population density, activity index, etc.) are integrated to ensure data consistency and integrity.

[0049] S2.1: Use spatial statistical methods to calculate the spatial correlation between microbial communities and soil health.

[0050] The degree of correlation between soil and microbial communities in different regions was quantified by the spatial autocorrelation coefficient (such as Moran's I).

[0051] Preferably, spatial autocorrelation coefficients (such as Moran's I) are used to quantify the spatial correlation between microbial communities and soil health.

[0052] Among them, Moran's I is used to measure the similarity between a spatial unit (such as an agricultural area) and its neighboring units. The specific calculation formula is:

[0053] ;

[0054] in, is the spatial autocorrelation coefficient, is the number of regions or units, is the sum of all spatial weights, For unit and unit The spatial weight between and Unit and unit Microbial community or soil health data values, is the mean of all unit data.

[0055] It can be seen that this formula measures whether the health status (microbial community or soil health) between different agricultural units shows spatial clustering; when When , it indicates that there is positive autocorrelation, that is, the health status of adjacent regions is similar; when When , it indicates that there is negative autocorrelation, that is, the health status of adjacent regions is quite different; when , indicating no autocorrelation.

[0056] The spatial correlation was converted into a spatial network, with each agricultural unit regarded as a node and the edge weights between nodes representing the spatial correlation between them, that is, the spatial dependence between microbial communities and soil health.

[0057] The weight of the edge is weighted according to the I value.

[0058] For each node, the correlation within the neighborhood was calculated and a spatial correlation network was constructed so that the relationship between network nodes could reflect the spatial dependence of microbial communities and soil health.

[0059] S2.2: Use community detection algorithms to identify areas of strong connectivity in spatial networks to determine which soil health states and microbial communities are spatially closely linked.

[0060] Preferably, a community detection algorithm is used to analyze the constructed spatial correlation network. In this invention, the Louvain algorithm is used to identify regions with strong internal connections in the spatial network by maximizing modularity. Modularity is defined as:

[0061] ;

[0062] in, is the modularity, which indicates the quality of network partitioning, is the number of edges in the network, is the adjacency matrix element, representing the node and nodes Is it connected? and Node and nodes The degree (i.e., the number of adjacencies), and For nodes and nodes The community to which they belong, is the indicator function, when the node and nodes If they belong to the same community, the value is 1; otherwise, it is 0.

[0063] when Greater than the preset threshold , it is considered to have a strong correlation.

[0064] The formula partitions the network by maximizing modularity, identifying regions with strong associations—those where microbial communities are spatially closely linked to soil health.

[0065] Optionally, based on the identified community structure, the characteristics of each community can be further analyzed to identify key factors that influence the health of the microbial community. For example, regression analysis or machine learning algorithms can be used to analyze the impact of factors such as soil temperature, moisture, and pH on the health of the microbial community.

[0066] S2.3: Based on the extracted spatial correlation patterns, construct a multidimensional spatial correlation model to predict future agricultural health status.

[0067] Preferably, after extracting the spatial correlation patterns between microbial communities and soil health (S2.1) and network structure analysis (S2.2), the interactions of spatial data are modeled based on I value and modularity Q.

[0068] The I value was used as the spatial autocorrelation term and the modularity Q was used as the network structure strength term to construct a multidimensional regression model.

[0069] The model is used to predict agricultural health status and incorporates spatial structure and interaction factors to improve the accuracy of the model:

[0070] ;

[0071] in, is the predicted value of agricultural health status, are model parameters, are the relevant characteristics of soil and microbial communities (such as humidity, temperature, pH value, microbial population density, etc.), and is the weight coefficient of Moran's I value I and modularity Q, is the interaction weight between features, is the error term, is the number of relevant characteristics of soil and microbial communities.

[0072] It should be noted that I, as the spatial autocorrelation coefficient, quantifies the spatial clustering of microbial communities and soil health in S2.1. It can help the model capture the local dependence of health status and provide a quantitative indicator of spatial dependence for the regression model;

[0073] As a strength indicator of the network structure, Q quantifies the closeness and connectivity between agricultural regions in S2.2, which can help the model identify clustering effects between different agricultural regions and thus optimize the spatial management of agricultural health.

[0074] In this regression model, I and modularity Q serve as additional spatial dependencies, reflecting the spatial dependence between agricultural areas and the tightness of the network structure, enabling the model to take into account both spatial autocorrelation and network structure, which helps to reveal the complex relationship between soil health and microbial communities and avoids the limitations of traditional regression models.

[0075] Optionally, use cross-validation to evaluate the model. This method reduces the risk of overfitting by splitting the data into training and validation sets, and then training and validating on multiple subsets. Based on the difference between the predicted results and the actual data, adjust the model parameters to optimize the model's accuracy.

[0076] The evaluation indicators of cross-validation can be mean square error (MSE) or mean absolute error (MAE).

[0077] S3: Based on the spatial correlation model, agricultural resources (such as water sources, fertilizers, crop types, etc.) are optimized and allocated; and through spatial optimization algorithms, combined with microbial community health data and soil environmental characteristics, personalized agricultural resource allocation plans are generated for each region.

[0078] S3.1: Integrate regional resource demand data with microbial community and soil health data to adjust resource demand and ensure accurate allocation of agricultural resources.

[0079] First, resource demand data of agricultural areas, such as water sources, fertilizers, and crop types, are collected to construct resource demand characteristics for each agricultural unit (such as farmland blocks, regions, etc.).

[0080] Resource requirements can be modeled based on crop planting requirements, soil conditions, climate conditions, etc., and a unified resource demand model can be obtained through data integration.

[0081] Integrate microbial community health data and spatial correlation outputs into resource demand models. For example, water and fertilizer requirements can be adjusted by:

[0082] The health of the microbial community directly affects the soil's water retention capacity, so areas with a higher microbial health index may require less water input, expressed as:

[0083] ;

[0084] in, For the region water demand, For basic water needs, For the region The microbial health index, is a regulating factor that represents the impact of microbial health status on water demand.

[0085] The health of the microbial community affects the cycling of nutrients in the soil. A healthy microbial community may reduce the need for fertilizer. The following exponential model can be used to adjust fertilizer requirements:

[0086] ;

[0087] in, For the region Fertilizer requirements, For basic fertilizer requirements, is a regulating factor that represents the effect of microbial health status on fertilizer demand.

[0088] Soil health influences crop planting patterns through parameters such as soil temperature, moisture, and pH. For each agricultural unit, crop selection is adjusted based on the soil health index. For example, when the soil health index is high, crops with higher soil requirements are selected. The calculation method can be referenced above and will not be further explained here.

[0089] S3.2: Use spatial optimization algorithms to spatially correlate resource requirements, soil health, and microbial communities.

[0090] Based on the aforementioned integrated resource demand data and spatial correlation model, the objective function is defined.

[0091] The objective function is calculated using a weighted approach and must be set to minimize resource waste while maximizing crop yield, soil health, and microbial community health.

[0092] Use particle swarm optimization algorithm or genetic algorithm to optimize resource allocation and gradually find the optimal solution by simulating group evolution.

[0093] At this point, the position of the particle or individual in the solution space represents the resource allocation of each agricultural unit, and the objective function is used to guide the optimization process.

[0094] S3.3: Generate a personalized resource allocation plan for each agricultural region based on the output of the optimization algorithm, and evaluate and adjust it based on actual data.

[0095] After processing by the optimization algorithm, a personalized resource allocation plan is generated for each region. This plan takes into account factors such as microbial communities, soil health, and climate conditions to provide the optimal allocation of water, fertilizer, and crop types.

[0096] S4: After the agricultural resource allocation plan is implemented, a correction plan is automatically generated based on the spatial feedback of microbial communities and soil health.

[0097] Ideally, spatial correlation models and real-time data collection can be used to analyze microbial communities and soil health. For example, soil health indices and microbial activity indices can be calculated to assess the health of the current agricultural unit and identify healthy and problematic areas.

[0098] Based on these spatial feedback data, problems that may arise in the resource allocation process, such as soil being too dry or excessive fertilizer, can be discovered in a timely manner.

[0099] After monitoring changes in the status of microbial communities and soil health, agricultural management measures are adjusted through adaptive optimization mechanisms.

[0100] The adaptive optimization mechanism uses historical data, real-time data and the results of spatial correlation analysis to automatically determine the adaptability of current management measures and make necessary adjustments. For example:

[0101] Automatically increase irrigation when soil moisture is too low in certain areas and microbial community health indicators show reduced activity, and adjust irrigation frequency and intensity based on soil type;

[0102] If an area has an excess or deficiency of fertilizer, and the soil pH or nutrient levels fluctuate abnormally, adjust the fertilizer application rate to maintain the appropriate nutrient level in the soil.

[0103] Based on the adjustment of the adaptive optimization mechanism, correction plans are automatically generated, including optimization plans for agricultural management measures such as irrigation, fertilization, and crop types.

[0104] The revised plans are transmitted to agricultural production units in real time and synchronized with the agricultural management platform. Through the agricultural management platform or automated system, farmers or relevant managers can quickly implement these plans and continuously track their effects.

[0105] After the implementation of the plan, the effectiveness of the corrective measures will be continuously tracked, and agricultural management measures will be continuously adjusted through feedback from re-collected soil and microbial data to form a closed-loop optimization.

[0106] Each round of adjustments is based on the latest monitoring data to ensure the adaptability and efficiency of agricultural management measures at different time points and in different regions.

[0107] Optionally, microbial communities and soil health may also change with seasonal changes, climate fluctuations, crop growth cycles, and other factors.

[0108] Therefore, the revised plan not only needs to respond quickly to short-term changes, but also continuously optimize agricultural resource allocation and management measures through long-term monitoring and data accumulation to ensure the sustainable development of agricultural production.

[0109] S5: Generate an agricultural health assessment report by integrating all collected data and the optimized agricultural resource allocation plan.

[0110] The report includes information on soil health, crop growth, microbial health, and the effectiveness of various agricultural management measures. Furthermore, it quantifies the environmental impact of agricultural production (such as carbon emissions, resource consumption, and water footprint), providing farmers and managers with data support for future agricultural health optimization decisions.

[0111] In the technical solution of the present invention, the problems of inconsistent spatial distribution and large precision differences between different data sources are solved through multi-source data collection and preprocessing technology, and a unified agricultural health spatial data set is constructed, providing a reliable data basis for accurate analysis of the agricultural ecological environment. Secondly, the present invention innovatively introduces a spatial correlation network analysis method, using spatial statistics and network analysis technology to deeply explore the complex correlation between microbial communities and soil health, and by constructing a multidimensional spatial correlation model, it realizes the accurate modeling of multi-factor interactions in agricultural ecosystems, which can reveal the spatial interactions between agricultural units and their influence paths, and provide a scientific basis for the optimal allocation of resources.

[0112] In addition, the present invention comprehensively considers microbial health, soil environmental characteristics and crop needs, and dynamically adjusts water sources, fertilizers and crop planting patterns, which not only improves the efficiency of agricultural resource utilization but also ensures the health and stability of the ecosystem.

[0113] Unlike traditional agricultural management methods, this invention establishes a closed-loop feedback system through an adaptive optimization mechanism, dynamically adjusts management measures based on real-time monitoring data, ensures that management strategies are always in the optimal state, and realizes the visualization and quantification of agricultural ecological health by generating agricultural health assessment reports, providing important support for long-term planning and scientific decision-making.

[0114] It should be noted that the computer-readable medium described in the embodiments of the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. Computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present invention, a computer-readable signal medium may include a data signal transmitted in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, or any suitable combination thereof.

[0115] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0116] The units involved in the embodiments of the present invention may be implemented in software or hardware, and the units described may also be provided in a processor. In some cases, the names of these units do not limit the units themselves.

[0117] According to one aspect of the present invention, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described above.

[0118] As another aspect, the present invention further provides a computer-readable medium, which may be included in the electronic device described in the above embodiments, or may exist independently and not incorporated into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, enable the electronic device to implement the agricultural information sharing and management method based on multi-source data fusion described in the above embodiments.

[0119] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0120] Through the description of the above embodiments, it will be readily understood by those skilled in the art that the exemplary embodiments described herein can be implemented via software or via a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored on a non-volatile storage medium (such as a CD-ROM, USB flash drive, or mobile hard drive) or on a network and includes instructions for causing a computing device (such as a personal computer, server, touch terminal, or network device) to execute the methods according to the embodiments of the present invention.

[0121] Other embodiments of the present invention will readily occur to those skilled in the art after considering the specification and practicing the embodiments disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein.

[0122] It should be understood that the present invention is not limited to the exact construction described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. The agricultural information sharing and management method based on multi-source data fusion is characterized by: include: Collecting and preprocessing multi-source data, spatially calibrating the multi-source data, and constructing an agricultural health spatial dataset; Based on the agricultural health spatial dataset, the association between microbial communities and soil health was explored through spatial correlation network analysis, and a spatial correlation model was constructed. Optimize the allocation of agricultural resources based on the spatial correlation model; and generate personalized agricultural resource allocation plans for each region through spatial optimization algorithms combined with microbial community health data and soil environmental characteristics; After the agricultural resource allocation plan is implemented, a correction plan is automatically generated based on the spatial feedback of microbial communities and soil health; Generate an agricultural health assessment report by integrating all collected data and optimized agricultural resource allocation plans; The spatial correlation network analysis is used to explore the relationship between microbial communities and soil health, including: Using spatial statistical methods to calculate the spatial correlation between microbial communities and soil health ; The spatial correlation is converted into a spatial network, each agricultural unit is regarded as a node, and the edge weights between nodes represent the spatial correlation between them; Using community detection algorithms, we calculate modularity Q and identify regions with strong connections in the spatial network. The spatial correlation ,include: when When , it indicates that there is positive autocorrelation, that is, the health status of adjacent regions is similar; when When , it indicates that there is negative autocorrelation, that is, the health status of adjacent regions is quite different; when When , it means there is no autocorrelation; The construction of the spatial correlation model includes: Based on the spatial correlation And the modularity Q models the interaction of spatial data: The spatial correlation As a spatial autocorrelation term, the modularity Q is used as a network structure strength term to construct a multidimensional spatial correlation model; The multidimensional spatial correlation model is evaluated using a cross-validation method, by dividing the data into a training set and a validation set, and training and validating on multiple subsets to reduce the risk of model overfitting; According to the spatial correlation model, agricultural resources are optimized and allocated, including: Collect resource demand data for agricultural regions and construct resource demand characteristics for each agricultural unit; Resource demand is modeled based on crop planting conditions, and a unified resource demand model is obtained through data integration; Integrate microbial community health data and spatial connectivity model outputs into the resource demand model: Adjust water and fertilizer requirements based on the health of the microbial community; For each agricultural unit, the choice of crop types is adjusted according to the soil health index; The water source demand is adjusted according to the health status of the microbial community, and the expression is: ； in, For the region water demand, For basic water needs, For the region The microbial health index, is the regulating factor, which represents the effect of microbial health status on water demand; The fertilizer requirement is adjusted as follows: ； in, For the region Fertilizer requirements, For basic fertilizer requirements, is a regulating factor that represents the effect of microbial health status on fertilizer demand.

2. The agricultural information sharing and management method based on multi-source data fusion according to claim 1 is characterized in that: Performing spatial calibration on the multi-source data includes: Obtain geographic information data of agricultural areas and use GIS software to connect various types of collected data with the geographic coordinate system; Spatial calibration is performed on different data sources to make them have a unified geographic coordinate system.

3. The agricultural information sharing and management method based on multi-source data fusion according to claim 1 is characterized in that: Preprocessing the remote sensing image data in the multi-source data includes: Radiation correction, geometric correction and atmospheric correction.

4. The agricultural information sharing and management method based on multi-source data fusion according to claim 1 is characterized in that: The spatial optimization algorithm combines microbial community health data and soil environmental characteristics, including: Define the objective function based on the integrated resource demand data and spatial correlation model; The objective function is calculated using a weighted approach and is set to minimize resource waste while maximizing crop yield, soil health, and microbial community health. Use particle swarm optimization algorithm or genetic algorithm to optimize resource allocation and gradually find the optimal solution by simulating group evolution.

5. The agricultural information sharing and management method based on multi-source data fusion according to claim 1 is characterized in that: The proposed method automatically generates correction schemes based on spatial feedback of microbial communities and soil health, including: Analyze microbial communities and soil health using spatial correlation models and real-time data collection; After monitoring changes in the status of microbial communities and soil health, agricultural management measures can be adjusted through adaptive optimization mechanisms; The adaptive optimization mechanism uses historical data, real-time data and the results of spatial correlation analysis to automatically determine the adaptability of current management measures and make necessary adjustments; Based on the adjustment of the adaptive optimization mechanism, a correction plan is automatically generated.

Images