An intelligent agricultural management method and system based on image processing

Abstract

The application provides a kind of wisdom agricultural management method and system based on image processing, comprising, rice-fish symbiotic region is deployed in rice-fish symbiotic region network, and based on rice-fish symbiotic region network, rice, fish and environment are multi-source data collection, obtain rice-fish symbiotic ecological data, data preprocessing is carried out to rice-fish symbiotic ecological data, rice-fish data heterostructure is constructed based on the rice-fish symbiotic ecological data after data preprocessing, rice-fish attention network model is constructed, rice-fish data heterostructure is imported into rice-fish attention network model, cross-domain feature fusion is carried out to rice-fish symbiotic ecological data based on rice-fish attention network model, obtain rice-fish correlation data, then rice-fish causal reasoning is carried out based on rice-fish correlation data, generate rice-fish correlation knowledge graph, establish rice-fish decision model, rice-fish correlation knowledge graph is imported into the rice-fish decision model, and rice-fish regulation and control decision is generated, and the method provides precise and efficient intelligent dynamic regulation and control decision for user.

Description

Technical Field

[0001] The present invention relates to the field of agricultural management technology, and in particular to an intelligent agricultural management method and system based on image processing. Background Art

[0002] As a typical ecological agricultural model, the rice-fish symbiosis system achieves resource circulation and efficiency improvement through the synergy of rice cultivation and aquaculture. However, the traditional rice-fish symbiosis system has limitations when applied to this scenario.

[0003] On the one hand, the data monitoring system of the traditional rice-fish symbiosis system mostly focuses on a single factor and lacks multi-dimensional coordinated perception of rice, fish and the environment. For example, although the fish farming system uses dissolved oxygen sensors to control the feeding machine, it is not linked to the dynamic nitrogen demand of rice during the growth period, resulting in a waste of nitrogen cycle resources. In addition, the data analysis method relies on shallow statistical correlations and simply establishes a linear causal hypothesis between water temperature and fish food intake, while ignoring the chain effect between organisms. As a result, the model is often unable to describe the nonlinear biological interaction process, which in turn affects the generation of subsequent decisions.

[0004] On the other hand, at the decision-making level, the traditional rice-fish symbiosis system relies on a preset rule base and adopts a single-threshold trigger mechanism. It neither considers the synergistic effects of environmental parameters nor is it compatible with the delayed response of biological behavior. For example, under continuous rainy conditions, excessive oxygenation may aggravate heat loss due to water disturbance, causing a sudden drop in water temperature, which in turn inhibits fish activity. This contradictory scenario exposes the fundamental defect of the traditional system's lack of dynamic weight calculation capabilities for multi-dimensional parameters. It can neither quantify the gradient relationship between oxygenation intensity and water temperature changes, nor predict the cross-scale feedback impact of regulatory measures on the symbiotic system, thus leading to rigid decision-making.

[0005] Therefore, the existing traditional rice-fish symbiosis system technology seems to be unable to cope with the complex and changeable rice-fish symbiosis system, and is unable to provide detailed and comprehensive decisions to meet the refined needs of the rice-fish symbiosis system. Summary of the Invention

[0006] In view of the above-mentioned problems, in combination with the first aspect of the present invention, an embodiment of the present invention provides a smart agricultural management method based on image processing, the method comprising:

[0007] Deploying a rice-fish symbiosis area network in a rice-fish symbiosis area, wherein the rice-fish symbiosis area is a rice-fish symbiosis area where rice is grown and fish are cultured simultaneously;

[0008] Based on the rice-fish symbiosis regional network, multi-source data of rice, fish and environment are collected to obtain rice-fish symbiosis ecological data, wherein the rice-fish symbiosis ecological data includes rice data, fish data and environmental data, and data preprocessing is performed on the rice-fish symbiosis ecological data;

[0009] Construct a rice-fish data heterogeneous graph based on the rice-fish symbiotic ecological data after data preprocessing;

[0010] Construct a rice-fish attention network model, import the rice-fish data heterogeneous graph into the rice-fish attention network model, perform cross-domain feature fusion on the rice-fish symbiotic ecological data based on the rice-fish attention network model, and obtain rice-fish correlation data;

[0011] Conduct causal reasoning on rice and fish based on rice-fish association data to generate a rice-fish association knowledge graph;

[0012] A rice-fish decision-making model is established, the rice-fish associated knowledge graph is imported into the rice-fish decision-making model, and a rice-fish regulation decision is generated. Users can dynamically regulate the rice-fish symbiotic area based on the rice-fish regulation decision.

[0013] As a further solution of the present invention, the rice-fish data heterogeneous graph is imported into the rice-fish attention network model, and cross-domain feature fusion of the rice-fish symbiotic ecological data is performed based on the rice-fish attention network model to obtain rice-fish association data, including:

[0014] The preprocessed rice-fish symbiotic ecological data and the rice-fish data heterogeneous graph are imported into the rice-fish attention network model, the feature vectors of the rice-fish symbiotic ecological data are obtained based on the rice-fish attention network model, and the feature vectors of the rice-fish symbiotic ecological data are spatially projected so that the feature vectors of the rice-fish symbiotic ecological data are mapped to the same space;

[0015] The ecological attention weights of the nodes in the rice-fish data heterogeneous graph are obtained, and the rice-fish association is discovered based on the characteristic vectors of the rice-fish symbiotic ecological data based on the ecological attention weights to obtain the rice-fish association data.

[0016] As a further solution of the present invention, the construction of the rice-fish attention network model includes:

[0017] When constructing a rice-fish attention network model, a dynamic meta-learning framework is introduced into the rice-fish attention network model;

[0018] The rice-fish symbiotic area was divided into blocks, and the rice-fish symbiotic area was divided into rectangular sub-areas of equal area, and the historical rice-fish symbiotic ecological data of each rectangular sub-area were obtained;

[0019] The historical rice-fish symbiotic ecological data of different periods in the same rectangular sub-region are used as training positive samples, and the historical rice-fish symbiotic ecological data of the same period in different rectangular sub-regions are randomly combined, and the randomly combined historical rice-fish symbiotic ecological data are used as training negative samples.

[0020] The rice-fish attention network model is trained based on training positive samples and training negative samples.

[0021] As a further solution of the present invention, the rice-fish causal reasoning is performed based on the rice-fish association data and the rice-fish data heterogeneous graph to generate the rice-fish association knowledge graph, including:

[0022] Optimizing PC calculations on rice-fish association data, and adding time lag constraints and ecological prior constraints during the optimization PC calculation process, wherein the time lag constraints are used to constrain the causes of causal reasoning, and the ecological prior constraints are used to constrain the reasoning logic of causal reasoning, obtain the linear causal relationship between rice and fish based on the optimized PC calculations, perform nonlinear expansion on non-Gaussian distributed data in the rice-fish association data, identify and obtain the nonlinear causal relationship in the rice-fish association data, and generate an initial rice-fish causal network based on the nonlinear causal relationship and the linear causal relationship;

[0023] Calculate the rice-fish treatment effect data of rice and fish, and construct a rice-fish association knowledge graph based on the initial rice-fish causal network and the rice-fish treatment effect data of rice and fish.

[0024] As a further solution of the present invention, the rice-fish decision model is established, the rice-fish association knowledge graph is imported into the rice-fish decision model, and the rice-fish regulation decision is generated, including:

[0025] Based on the rice-fish association knowledge graph and combined with rice-fish symbiotic ecological data, a rice-fish decision space is constructed. Rice-fish ecology is predicted based on the initial rice-fish causal network contained in the rice-fish association knowledge graph. Rice-fish regulation decisions are generated based on the results of the rice-fish ecology prediction. The rice-fish regulation decisions include explicit regulation decisions and implicit regulation decisions.

[0026] As a further solution of the present invention, the rice-fish decision space is constructed based on the rice-fish association knowledge graph and combined with the rice-fish symbiotic ecological data, including:

[0027] Obtain rice knowledge nodes, fish knowledge nodes, and environmental knowledge nodes in the rice-fish association knowledge graph, obtain knowledge node data based on the rice knowledge nodes, fish knowledge nodes, and environmental knowledge nodes, convert the knowledge node data into a rice-fish decision space vector, and convert the initial rice-fish causal network contained in the rice-fish association knowledge graph into a rice-fish association weight matrix;

[0028] The rice-fish decision space is constructed based on the rice-fish decision space vector and the rice-fish association weight matrix.

[0029] As a further solution of the present invention, the method of constructing a rice-fish data heterogeneous graph based on the rice-fish symbiotic ecological data after data preprocessing includes:

[0030] The preprocessed rice-fish symbiotic ecological data is used to define graph nodes, obtain rice heterogeneous nodes, fish heterogeneous nodes and environment heterogeneous nodes, add edge relationship rules to the rice heterogeneous nodes, fish heterogeneous nodes and environment heterogeneous nodes, and link the rice heterogeneous nodes, fish heterogeneous nodes and environment heterogeneous nodes based on the edge relationship rules to generate a rice-fish data heterogeneous graph.

[0031] As a further solution of the present invention, the rice-fish symbiotic regional network is used to collect multi-source data on rice, fish, and the environment to obtain rice-fish symbiotic ecological data, wherein the rice-fish symbiotic ecological data includes rice data, fish data, and environmental data, including:

[0032] Rice-fish symbiosis ecological data are obtained based on the rice data collection terminal, fish data collection terminal and environmental data collection terminal of the rice-fish symbiosis regional network. The rice data includes chlorophyll content and canopy nitrogen accumulation, the fish data includes fish movement trajectory, fish feeding frequency and fish population density, and the environmental data includes water dissolved oxygen concentration, water nitrogen and ammonia concentration, water pH value and water temperature.

[0033] On the other hand, an embodiment of the present invention further provides a smart agricultural management system based on image processing, comprising:

[0034] A rice-fish symbiosis area network, wherein the rice-fish symbiosis network is used to collect rice data, fish data, and environmental data within the rice-fish symbiosis area to obtain rice-fish symbiosis ecological data;

[0035] A mapping module, which is used to preprocess the rice-fish symbiotic ecological data and construct a heterogeneous graph of the rice-fish data;

[0036] A rice-fish model module, which is used to construct a rice-fish attention network model and obtain rice-fish association data based on a rice-fish data heterogeneous graph and rice-fish symbiotic ecological data;

[0037] A knowledge construction module, which is used to perform rice-fish causal reasoning and generate a rice-fish association knowledge graph;

[0038] The rice-fish decision module is used to generate rice-fish regulation decisions, and users can dynamically regulate the rice-fish symbiotic area based on the rice-fish regulation decisions.

[0039] As a further embodiment of the present invention, the rice-fish symbiotic regional network comprises:

[0040] A rice data collection terminal includes a drone swarm that patrols the rice-fish symbiotic area twice a day, acquiring chlorophyll content and canopy nitrogen accumulation based on the drone swarm.

[0041] A fish data acquisition terminal, comprising an underwater sonar array and an infrared module, monitors fish based on the underwater sonar array and the infrared module to obtain fish movement trajectories, fish feeding frequency, and fish population density;

[0042] The environmental data acquisition terminal is used to monitor the environment of the rice-fish symbiosis area and obtain the dissolved oxygen concentration, nitrogen and ammonia concentration, pH value and temperature of the water.

[0043] Based on the above aspects, the embodiment of the present application obtains rice-fish symbiotic ecological data consisting of rice, fish and environmental data in the rice-fish symbiotic area through multi-source network deployment in the rice-fish symbiotic area, and cleans the abnormal data in the rice-fish symbiotic ecological data through data preprocessing to reduce the impact of abnormal data on the accuracy of the rice-fish symbiotic ecological data. The complex ecological relationship in the rice-fish symbiotic area is analyzed and quantified through the combination of the rice-fish attention network and causal reasoning, and the abstract and complex causal relationship between rice and fish, rice and environment, and fish and environment is simplified into a specific causal quantification set, and the real-time rice-fish symbiotic ecological data is combined with the causal quantification set to generate accurate and user-friendly dynamic control decisions. In summary, the smart agricultural management method improves the technical limitations of traditional rice-fish symbiotic system monitoring fragmentation, shallow analysis, and static decision-making, and provides more accurate control decisions for the intelligent management of the rice-fish symbiotic system. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a schematic diagram of the execution flow of an intelligent agricultural management method based on image processing provided by an embodiment of the present invention.

[0045] Figure 2 This is a schematic diagram of an intelligent agricultural management system based on image processing provided by an embodiment of the present invention.

[0046] Figure 3 This is a schematic diagram of a rice-fish symbiotic regional network in an image processing-based smart agricultural management system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The present invention will be described in detail below with reference to the accompanying drawings. Figure 1 This is a schematic diagram of the execution flow of an intelligent agricultural management method based on image processing provided by an embodiment of the present invention. The following is a detailed introduction to the intelligent agricultural management method based on image processing.

[0048] Step S1, deploying a rice-fish symbiosis area network in a rice-fish symbiosis area, wherein the rice-fish symbiosis area is a rice-fish symbiosis area where rice is planted and fish are raised simultaneously.

[0049] Step S2: collecting multi-source data of rice, fish and environment based on the rice-fish symbiosis regional network to obtain rice-fish symbiosis ecological data, wherein the rice-fish symbiosis ecological data includes rice data, fish data and environmental data, and performing data preprocessing on the rice-fish symbiosis ecological data.

[0050] In this embodiment, step S2 includes:

[0051] Step S21 : collecting multi-source data of rice, fish and environment based on the rice-fish symbiosis regional network to obtain rice-fish symbiosis ecological data.

[0052] Specifically, based on the rice data collection terminal in the rice-fish symbiosis area network, rice data in the rice-fish symbiosis area is obtained, and the rice data includes chlorophyll content and canopy nitrogen accumulation. Based on the fish data collection terminal in the rice-fish symbiosis area network, fish data in the rice-fish symbiosis area is obtained, and the fish data includes fish movement trajectory, fish feeding frequency and fish group density. Based on the environmental data collection terminal in the rice-fish symbiosis area network, environmental data in the rice-fish symbiosis area is obtained, and the environmental data includes dissolved oxygen concentration, nitrogen and ammonia concentration, pH value and water temperature in the rice-fish symbiosis area.

[0053] Step S22: preprocessing the rice-fish symbiotic ecological data.

[0054] In this embodiment, step S22 includes:

[0055] Step S22-1: Detect and process outliers on the rice-fish symbiotic ecological data.

[0056] Specifically, the sliding window size is set to 1 hour, and the dynamic mean of similar sensors is monitored in real time. If the sensor data deviates from the mean by more than 20% for three consecutive times and lasts for 10 minutes, it is determined whether the sensor has failed. Redundant switching is used to process the abnormal data for the faulty sensor. For example, if the data uploaded by PH sensor A1 exceeds 20% of the dynamic mean of similar sensors for three consecutive times, and the PH sensor is confirmed to have failed 10 minutes later, the PH sensor data within 5 meters of the PH sensor and the PH sensor historical data are obtained, and weighted summation is performed to obtain corrected data. The data uploaded by the abnormal sensor is shielded, and the corrected data is used to smooth the abnormal data through sliding window linear interpolation. At the same time, a maintenance information sheet is pushed to the maintenance personnel for maintenance. After the maintenance personnel confirms that the maintenance is completed, the value of PH sensor A1 is obtained again, and the value of PH sensor A1 is verified for consistency with the corrected data. After confirming the consistency, the data shielding of PH sensor A1 is canceled.

[0057] Step S22-2: standardize the rice-fish symbiotic ecological data.

[0058] Specifically, the environmental data within the rice-fish symbiosis ecological data is standardized based on the standardization operation. For example, the water temperature on a certain day is 27 degrees Celsius, the seasonal mean of the quarter in which the day is located is 26 degrees Celsius, and the seasonal standard deviation is 3.1. The water temperature on the day is 0.32 after standardization. The dissolved oxygen concentration of the day is obtained, and the dissolved oxygen offset of the day is calculated based on the Z-score algorithm. The rice data in the rice-fish symbiosis ecological data is standardized based on the normalization operation. For example, the original chlorophyll value of rice in a certain area is 55 SPAD, and the standardized chlorophyll value is 0.58. The fish data in the rice-fish symbiosis ecological data is standardized based on the standardization operation. For example, the fish density in a certain area is 150 fish / acre. The data is standardized using a logarithmic transformation, and the standardized fish density data is 2.18. The underwater sonar array data in the area is obtained, and the underwater sonar array data is calculated based on the Shannon entropy to obtain the entropy of the fish motion trajectory, which is used to reflect the disorder of the fish movement.

[0059] Furthermore, standardized parameters are calculated according to the tillering period, heading period, and maturity period of rice. For example, the quarterly average water temperature during the tillering period of rice in a certain rice-fish symbiotic area is 24 degrees Celsius, and the quarterly average water temperature during the heading period is 28 degrees Celsius. Data standardization uses different standardized parameters for different quarters to avoid deviations in standardized data parameters due to seasonal deviations. The data of adjacent areas of the calculation area are weighted and added to the local mean calculation. The weight changes with the distance to enhance the accuracy of the local mean calculation.

[0060] Step S3: constructing a rice-fish data heterogeneous graph based on the rice-fish symbiotic ecological data after data preprocessing.

[0061] In this embodiment, step S3 includes:

[0062] Step S31: defining heterogeneous nodes based on rice-fish symbiotic ecological data.

[0063] Specifically, the rice-fish symbiosis area is divided into multiple 5m×5m rice grid units according to the grid, and the rice data in each rice grid unit is used as a rice heterogeneous node, where each rice heterogeneous node contains three node attributes: chlorophyll content, canopy nitrogen accumulation, and the spatial coordinates of the grid unit. For example, the node attributes of rice node A01 are [chlorophyll = 0.65, nitrogen accumulation = 0.44, coordinates (15982, 35746)]. Based on the distribution of underwater sonar arrays in the fish data collection terminal of the rice-fish symbiosis area network, the rice-fish symbiosis area is divided into multiple 5m×5m water blocks, and each water block is used as a fish heterogeneous node, where each fish Heterogeneous nodes include three node attributes: fish population density, fish feeding frequency, fish movement trajectory entropy, and spatial coordinates. For example, the node attributes of fish node B32 are [density = 2.5, feeding = 13 times / 10 minutes, trajectory entropy = 1.8, coordinates (13795, 24658)]. Each sensor group at the environmental data acquisition end in the rice-fish symbiosis regional network is regarded as an environmental heterogeneous node, where each environmental heterogeneous node includes four node attributes: dissolved oxygen offset, ammonia nitrogen concentration, water temperature, and pH value. For example, the node attributes of environmental node C13 are [dissolved oxygen concentration offset = -1.2, ammonia nitrogen concentration = 0.8, water temperature = 0.6, pH = 0.4].

[0064] Step S32: Establish heterogeneous graph edge relationship rules.

[0065] Specifically, when the distance between the center of the rice node and the sensor group in the environmental node does not exceed 10 meters, a bidirectional edge is established between the rice node and the environmental node. When the distance between the sonar array in the fish node and the sensor group in the environmental node does not exceed 15 meters, a bidirectional edge is established. A symbiotic relationship is set between rice data, fish data and environmental data. For example, there is a positive correlation between the chlorophyll content of rice and the dissolved oxygen offset of the water body, and there is a dynamic response relationship between the feeding frequency of fish and water temperature. A competitive relationship is set between rice data, fish data and environmental data. For example, when the nitrogen and ammonia concentration in the water body is greater than 0.5 mg / L, a resource competition relationship is established between rice and fish.

[0066] Furthermore, if it is detected that the dissolved oxygen concentration in the water body has dropped significantly, resulting in a significant increase in the entropy of the fish movement trajectory, a causal edge will be established between the dissolved oxygen concentration in the water body and the entropy of the fish movement trajectory. For example, if the dissolved oxygen offset in a certain area drops by 1.3, and the entropy of the fish movement trajectory in the area increases by 0.9, a causal edge will be established between the dissolved oxygen concentration in the water body and the entropy of the fish movement trajectory, and the causal weight will be set to 0.7.

[0067] Step S33: construct a heterogeneous graph of rice-fish data based on the relationship rules between heterogeneous nodes and heterogeneous graph edges.

[0068] Specifically, all rice grid units, water blocks and sensor locations are traversed to obtain multiple rice nodes, fish nodes and environmental nodes. The geometric distances between rice nodes, fish nodes and environmental nodes are calculated to obtain initial edges. Based on the heterogeneous graph edge relationship rules, bidirectional edges, competitive edges, associated edges and causal edges are generated. A heterogeneous graph of rice and fish data is constructed based on rice nodes, fish nodes, environmental nodes and heterogeneous graph edges.

[0069] Step S4, constructing a rice-fish attention network model, importing the rice-fish data heterogeneous graph into the rice-fish attention network model, performing cross-domain feature fusion on the rice-fish symbiotic ecological data based on the rice-fish attention network model, and obtaining rice-fish associated data.

[0070] In this embodiment, step S4 includes:

[0071] Step S41, constructing a rice-fish attention network model.

[0072] In this embodiment, step S41 includes:

[0073] Step S41-1, when constructing the rice-fish attention network model, import the dynamic meta-learning framework into the rice-fish attention network model.

[0074] Step S41 - 2 , dividing the rice-fish symbiotic area into blocks, dividing the rice-fish symbiotic area into rectangular sub-areas of equal area, and obtaining historical rice-fish symbiotic ecological data of each rectangular sub-area.

[0075] Step S41-3: Use the historical rice-fish symbiotic ecological data of the same rectangular sub-region at different periods as training positive samples, randomly combine the historical rice-fish symbiotic ecological data of different rectangular sub-regions at the same period, and use the randomly combined historical rice-fish symbiotic ecological data as training negative samples.

[0076] Step S41-4: training the rice-fish attention network model based on the training positive samples and the training negative samples.

[0077] Step S42: import the preprocessed rice-fish symbiotic ecological data and the rice-fish data heterogeneous graph into the rice-fish attention network model, obtain the rice-fish symbiotic ecological data feature vector based on the rice-fish attention network model, perform spatial projection on the rice-fish symbiotic ecological data feature vector, and map the rice-fish symbiotic ecological data feature vector to the same space.

[0078] Specifically, based on the heterogeneous graph of rice-fish data, the heterogeneous node attributes of rice, fish, and environment are obtained, and the heterogeneous node attributes of rice, fish, and environment are integrated into the corresponding node feature matrix. For example, the node attribute of rice node A01 is [chlorophyll = 0.65, nitrogen accumulation = 0.44, coordinate (15982, 35746)], the node attribute of rice node A02 is [chlorophyll = 0.58, nitrogen accumulation = 0.43, coordinate (15982, 35750)], and the node attribute of rice node A03 is [chlorophyll = 0.74, nitrogen accumulation = 0.41, coordinate (15982, 35754)]. Then the rice node feature matrix composed of these three rice nodes is:

[0079]

[0080] Each row vector of the matrix represents a rice node, and the column vectors from left to right represent the chlorophyll content, canopy nitrogen accumulation, and the spatial coordinates of the rice node.

[0081] For example, the node attributes of fish node B31 are [density = 2.7, feeding = 13 times / 10 minutes, trajectory entropy = 1.7, coordinates (13785, 24658)], the node attributes of fish node B32 are [density = 2.5, feeding = 14 times / 10 minutes, trajectory entropy = 1.8, coordinates (13795, 24658)], and the node attributes of fish node B33 are [density = 2.1, feeding = 15 times / 10 minutes, trajectory entropy = 1.6, coordinates (13805, 24658)], then the fish node feature matrix composed of these three fish nodes is:

[0082] Each row vector of the matrix represents a fish node, and the column vectors from left to right represent the fish population density, fish feeding frequency, fish movement trajectory entropy, and spatial coordinates.

[0083] For example, the node attributes of environmental node C11 are [dissolved oxygen concentration offset = -1.1, ammonia nitrogen concentration = 0.8, water temperature = 0.6, pH = 0.4], the node attributes of environmental node C12 are [dissolved oxygen concentration offset = -1.2, ammonia nitrogen concentration = 0.7, water temperature = 0.6, pH = 0.4], and the node attributes of environmental node C13 are [dissolved oxygen concentration offset = -1.3, ammonia nitrogen concentration = 0.8, water temperature = 0.5, pH = 0.4]. The environmental node feature matrix formed by these three environmental nodes is:

[0084]

[0085] Each row vector of the matrix represents an environmental node, and the column vectors from left to right represent dissolved oxygen offset, ammonia nitrogen concentration, water temperature, and pH value.

[0086] Furthermore, an adjacency matrix is ​​constructed to store the heterogeneous graph edge relationships between nodes. The heterogeneous graph edge relationships include bidirectional edges, symbiotic edges, competitive edges, and causal edges. For example, there is a bidirectional edge connection between rice node A01 and environmental node C11, a symbiotic edge connection between fish node B32 and environmental node C12, a competitive edge connection between environmental node C11 and rice node A03, and a causal edge connection between environmental node C13 and fish node B31. The adjacency matrix storing the above edge connections is:

[0087] Each row vector of the matrix represents a heterogeneous graph edge relationship, and the column vectors represent the source node, target node, edge relationship type and weight from left to right. The edge relationship type is expressed as Indicates a bidirectional edge connection, Indicates symbiotic edge connections, represents the competitive edge connection, Causal edge connections.

[0088] Step S43: Obtain the ecological attention weights of the nodes contained in the rice-fish data heterogeneous graph, perform rice-fish association discovery on the rice-fish symbiotic ecological data feature vector based on the ecological attention weights, and obtain rice-fish association data.

[0089] Specifically, the source nodes and target nodes with edge connections in the rice-fish data heterogeneous graph are obtained, the ecological attention weights between the source nodes and the target nodes are calculated according to the ecological attention weight formula, and the ecological attention weight matrix is ​​constructed. The ecological attention weight formula is expressed as

[0090] ;

[0091] in, is the ecological attention weight, is the bidirectional edge connection weight between the source node and the target node, is the symbiotic edge connection weight between the source node and the target node, The competition edge connection weight between the source node and the target node, is the causal edge connection weight between the source node and the target node.

[0092] For example, there are bidirectional edge connections, symbiotic edge connections, competitive edge connections and causal edge connections between rice node A01 and environmental node C11. The bidirectional edge connection weight is 0.7, the symbiotic edge connection weight is 0.5, the competitive edge connection weight is 0.2, and the causal edge connection weight is 0.6. Then the ecological attention weight between rice node A01 and environmental node C11 is 0.52.

[0093] Furthermore, the ecological attention weight matrix is ​​screened for correlation strength to obtain rice-fish correlation data. The correlation strength screening is performed by dividing the data with ecological attention weights in the range of [0.6, 1] in the ecological attention weight matrix into high-level correlation data, dividing the data with ecological attention weights in the range of [0.3, 0.6) into medium-level correlation data, and dividing the data with ecological attention weights in the range of [0, 0.3) into low-level correlation data.

[0094] Step S5: Perform rice-fish causal reasoning based on the rice-fish association data to generate a rice-fish association knowledge graph.

[0095] In this embodiment, step S5 includes:

[0096] Step S51 , performing optimized PC calculation on the rice-fish association data, and in the process of optimizing PC calculation, adding time lag constraints and ecological prior constraints, and obtaining the linear causal relationship between rice and fish based on the optimized PC calculation.

[0097] Specifically, first, lagged observation variables of rice-fish association data are generated based on the ecological response characteristics. The lag order is determined by maximizing the mutual information to ensure that the causal variables of the current causal inference only come from historical data. For example, the dissolved oxygen concentration and water temperature in the environmental data are aligned with the fish population density with a lag of 2-3 hours. Secondly, the causal direction is forced to be that historical data determines current data, and future variables are prohibited from affecting past variables. For example, causal inference that the fish population density changes due to changes in historical water temperature data is allowed, and causal inference that the water temperature data changes due to changes in fish population density is prohibited. In the conditional independence test, the condition set is limited to only include earlier variables to avoid time inversion. Finally, a greedy algorithm is used to dynamically optimize the lag order of each variable. If the mutual information between a certain lag order and the biological indicator is significantly higher than that of other orders, then the order is fixed to capture the maximum causal effect.

[0098] Furthermore, the causal relationships in the rice-fish association data that violate biological common sense are deleted. For example, the causal relationship in the rice-fish association data that violates biological common sense, that is, the change in fish population density leads to the change in water temperature data, is deleted. The independence test is skipped to retain the known strong causal relationships. For example, the strong causal relationship that the dissolved oxygen concentration in the water body affects the fish population density is forced to be retained. The range of the test variables is restricted. For example, when testing the correlation between water temperature and rice chlorophyll content, the dissolved oxygen concentration data in the water body is forced to be added into the correlation test process between water temperature and rice chlorophyll content. The optimized PC algorithm accurately extracts the linear causal relationship between rice and fish by integrating time lag constraints with ecological prior constraints.

[0099] Step S52: performing nonlinear expansion on the non-Gaussian distributed data in the rice-fish association data to identify and obtain the nonlinear causal relationship in the rice-fish association data.

[0100] Specifically, the complex causal relationship of non-Gaussian distribution data in rice-fish association data is captured through data preprocessing and nonlinear test methods. First, the non-Gaussian variables in the rice-fish association data are screened through the KS test, and polynomial terms and interaction terms are introduced to capture the nonlinear interaction effects of the data in the rice-fish association data. Then, the nonlinear causal relationship in the rice-fish association data is obtained with the assistance of deep learning.

[0101] Step S53: generating an initial rice-fish causal network based on the nonlinear causal relationship and the linear causal relationship.

[0102] Step S54, calculating the rice-fish treatment effect data of rice and fish, and constructing a rice-fish association knowledge graph based on the initial rice-fish causal network and the rice-fish treatment effect data of rice and fish.

[0103] Step S6: Establish a rice-fish decision model, import the rice-fish associated knowledge graph into the rice-fish decision model, and generate a rice-fish regulation decision. Users can dynamically regulate the rice-fish symbiotic area based on the rice-fish regulation decision.

[0104] Specifically, the real-time rice-fish symbiotic ecological data is fused with the rice-fish related knowledge graph to construct a rice-fish prediction matrix, for example:

[0105]

[0106] The above matrix is ​​a rice-fish prediction matrix for a rice-fish symbiotic area, in which each row vector represents the rice-fish symbiotic ecological data of the rice-fish symbiotic area within a certain time period, and the column vectors represent the time period, water temperature, oxygen concentration, ammonia nitrogen concentration and fish feeding frequency from left to right. The time periods include the current time period t, the historical time periods t-2h and t-1h50m, that is, the data two hours ago and the data one hour and fifty minutes ago, and the predicted time periods t+10m and t+2h, that is, the predicted data ten minutes later and the predicted data two hours later.

[0107] Furthermore, the data in the rice-fish association knowledge graph are divided into environmental dimension, biological dimension and operational dimension, and the environmental dimension, biological dimension and operational dimension are merged into a decision space, wherein the environmental dimension includes two dimensional features: safety threshold interval and risk level, the biological dimension includes two dimensional features: rice growth stage and fish activity status, and the operational dimension includes two dimensional features: direct control action and indirect control strategy. For example, the safety threshold interval of the environmental dimension in a rice-fish symbiotic area includes the water temperature safety threshold interval of [25, 30℃], the dissolved oxygen concentration safety threshold interval of [3, 5mg / L] and the ammonia nitrogen concentration safety threshold interval of [0.4, 0.8mg / L]. The risk level dimension is characterized by the degree of deviation from the safety threshold, which is divided into three risk levels: low, medium and high. In the biological dimension, the rice growth stage is determined by the chlorophyll content. It is divided into three growth stages: tillering stage, heading stage and maturity stage. It is the tillering period, It is the heading period, The maturity period is 3600 hours, and the fish activity status is divided into three states according to the fish density Den per unit area: normal, warning and escape. When Den ≥ 80 fish / mu, it is the normal state; when 50 fish / mu ≤ Den < 80 fish / mu, it is the warning state; when Den < 50 fish / mu, it is the escape state. The direct control actions in the operational dimension include oxygenation, water change, feeding adjustment and fertilization. The indirect control strategies include adjustment of fish fry density and replacement of rice varieties.

[0108] Decisions are generated for the causal relationships contained in the rice-fish association knowledge graph, and immediate execution decisions are set as explicit regulatory decisions, and long-term execution decisions are set as implicit regulatory decisions to obtain a set of regulatory decisions. For example, if there is a causal edge in the rice-fish association knowledge graph, "the dissolved oxygen concentration is lower than 2.8 mg / L, resulting in a decrease in fish density", then this causal edge is generated into a regulatory decision, "if the dissolved oxygen concentration is lower than 2.8 mg / L and lasts for more than two hours, start the aerator for oxygenation".

[0109] A state-decision mapping table is constructed based on the set of control decisions. The row vectors of the state-decision mapping table represent the combination of rice-fish ecological states. For example, state 1 is {water temperature = 34°C, dissolved oxygen concentration = 2.8 mg / L, SPAD = 28}, and state 2 is {ammonia nitrogen concentration = 0.9 mg / L, Density = 65 fish / mu, SPAD = 44}. The column vectors of the state-decision mapping table represent candidate control decisions. For example, {decision: start the aerator, trigger condition: dissolved oxygen concentration < 2.8 mg / L or water temperature > 30°C and dissolved oxygen concentration < 4.0 mg / L, intensity: operation time = (target dissolved oxygen concentration - current dissolved oxygen concentration) / 0.5}.

[0110] Establish priority rules for regulatory decisions. For example, set the implementation priority of explicit regulatory decisions to be higher than that of implicit regulatory decisions, the implementation priority of decisions in high-risk areas to be higher than that in medium- and low-risk areas, give priority to decisions with higher absolute weights at the same risk level, and give priority to nonlinear causal relationships over linear causal relationships.

[0111] A rice-fish decision-making model is constructed based on the decision space, state-decision mapping table and control decision priority rules. Users can obtain the control decision of the rice-fish symbiotic area based on the rice-fish decision model and accurately control the rice-fish symbiotic area.

[0112] Figure 2 A schematic diagram of an image processing-based smart agricultural management system provided by some embodiments of the present application that can implement the concept of the present application is shown. Figure 3 A schematic diagram of a rice-fish symbiotic regional network in an image processing-based smart agricultural management system provided by some embodiments of the present application that can implement the ideas of the present application is shown. The following is a detailed introduction to the image processing-based smart agricultural management system.

[0113] Specifically, a smart agricultural management system based on image processing includes:

[0114] The rice-fish symbiosis area network is used to collect rice data, fish data and environmental data in the rice-fish symbiosis area to obtain rice-fish symbiosis ecological data.

[0115] A mapping module is used to preprocess the rice-fish symbiotic ecological data and construct a heterogeneous graph of the rice-fish data.

[0116] The rice-fish model module is used to construct a rice-fish attention network model and obtain rice-fish association data based on the rice-fish data heterogeneous graph and rice-fish symbiotic ecological data.

[0117] A knowledge construction module is used to perform rice-fish causal reasoning and generate a rice-fish association knowledge graph.

[0118] The rice-fish decision module is used to generate rice-fish regulation decisions, and users can dynamically regulate the rice-fish symbiotic area based on the rice-fish regulation decisions.

[0119] Furthermore, the rice-fish symbiosis regional network includes:

[0120] The rice data collection terminal includes a drone cluster, which is used to patrol the rice-fish symbiosis area twice a day, and obtain chlorophyll content and canopy nitrogen accumulation based on the drone cluster.

[0121] The fish data acquisition end comprises an underwater sonar array and an infrared module, and the fish is monitored based on the underwater sonar array and the infrared module to obtain the fish movement track, the fish feeding frequency and the fish group density.

[0122] The environment data acquisition end is used for monitoring the environment of the rice-fish symbiotic area to obtain the water dissolved oxygen concentration, the water nitrogen ammonia concentration, the water pH value and the water temperature.

[0123] The specific use mode and role of the embodiment are described below:

[0124] First, the rice-fish symbiotic area is deployed in a rice-fish symbiotic area network, and multi-source data of the rice, fish and environment are collected based on the rice-fish symbiotic area network to obtain rice-fish symbiotic ecological data, and then the rice-fish symbiotic ecological data is preprocessed to eliminate the influence of abnormal data on the rice-fish symbiotic ecological data and improve the accuracy of the rice-fish symbiotic ecological data, and a rice-fish data heterogeneous graph is constructed based on the preprocessed rice-fish symbiotic ecological data, and then a rice-fish attention network model is constructed, the rice-fish data heterogeneous graph is imported into the rice-fish attention network model, cross-domain feature fusion of the rice-fish symbiotic ecological data is performed based on the rice-fish attention network model to obtain rice-fish correlation data, then rice-fish causal reasoning is performed based on the rice-fish correlation data to generate a rice-fish correlation knowledge graph, and finally a rice-fish decision model is established, the rice-fish correlation knowledge graph is imported into the rice-fish decision model, and a rice-fish regulation and control decision is generated. The embodiment integrates multi-source data and complex ecological relationships in the rice-fish symbiotic area by constructing a rice-fish data heterogeneous graph and a rice-fish correlation knowledge graph, and quantifies the complex ecological relationships in the rice-fish symbiotic area into a specific causal relationship set, and provides more accurate and personalized intelligent dynamic regulation and control decisions for users in combination with the causal relationship set and real-time data.

[0125] In addition, the embodiment of the present application also provides an electronic device, comprising:

[0126] At least one processor; and a memory connected with the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method proposed in the embodiment of the present application.

[0127] The various constituent components of the electronic device are specifically introduced as follows:

[0128] The term "processor" is the control center of an electronic device and can be a single processor or a collective term for multiple processing elements. For example, the processor can be one or more central processing units (CPUs), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the first embodiment of the present invention, such as one or more digital signal processors (DSPs) or one or more field programmable gate arrays (FPGAs).

[0129] The processor can execute various functions of the electronic device by running or executing software programs stored in the memory and calling data stored in the memory.

[0130] The memory is used to store the software program that executes the solution of the present invention, and the execution is controlled by the processor. The specific implementation method can refer to the above method embodiment and will not be repeated here.

[0131] The memory may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, a random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. The memory may be integrated with the processor or exist independently and be coupled to the processor via an interface circuit of the electronic device, and this is not specifically limited in the embodiments of the present invention.

[0132] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wireless communication (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer, or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0133] It should be understood that the term "and / or" as used herein simply describes an association between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent the existence of A alone, the existence of both A and B, or the existence of B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the related objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0134] It should be understood that in the embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0135] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A smart agricultural management method based on image processing, characterized in that: The method comprises: Deploying a rice-fish symbiosis area network in a rice-fish symbiosis area, wherein the rice-fish symbiosis area is a rice-fish symbiosis area where rice is grown and fish are cultured simultaneously; Based on the rice-fish symbiosis regional network, multi-source data of rice, fish and environment are collected to obtain rice-fish symbiosis ecological data, wherein the rice-fish symbiosis ecological data includes rice data, fish data and environmental data, and data preprocessing is performed on the rice-fish symbiosis ecological data; Construct a rice-fish data heterogeneous graph based on the rice-fish symbiotic ecological data after data preprocessing; Construct a rice-fish attention network model, import the rice-fish data heterogeneous graph into the rice-fish attention network model, perform cross-domain feature fusion on the rice-fish symbiotic ecological data based on the rice-fish attention network model, and obtain rice-fish correlation data; Conduct causal reasoning on rice and fish based on rice-fish association data to generate a rice-fish association knowledge graph; Optimizing PC calculations on rice-fish association data, and adding time lag constraints and ecological prior constraints during the optimization PC calculation process, wherein the time lag constraints are used to constrain the causes of causal reasoning, and the ecological prior constraints are used to constrain the reasoning logic of causal reasoning, obtain the linear causal relationship between rice and fish based on the optimized PC calculations, perform nonlinear expansion on non-Gaussian distributed data in the rice-fish association data, identify and obtain the nonlinear causal relationship in the rice-fish association data, and generate an initial rice-fish causal network based on the nonlinear causal relationship and the linear causal relationship; Calculate the rice-fish treatment effect data for rice and fish, and construct a rice-fish association knowledge graph based on the initial rice-fish causal network and the rice-fish treatment effect data for rice and fish; Establish a rice-fish decision-making model, import the rice-fish association knowledge graph into the rice-fish decision-making model, and generate rice-fish regulation decisions. Users can dynamically regulate the rice-fish symbiotic area based on the rice-fish regulation decisions. Based on the rice-fish association knowledge graph and combined with rice-fish symbiotic ecological data, a rice-fish decision space is constructed. Rice-fish ecology is predicted based on the initial rice-fish causal network contained in the rice-fish association knowledge graph. Rice-fish regulation decisions are generated based on the results of the rice-fish ecology prediction. The rice-fish regulation decisions include explicit regulation decisions and implicit regulation decisions.

2. The method for intelligent agricultural management based on image processing according to claim 1, characterized in that: The method of importing the rice-fish data heterogeneous graph into the rice-fish attention network model, performing cross-domain feature fusion on the rice-fish symbiotic ecological data based on the rice-fish attention network model, and obtaining rice-fish associated data includes: The preprocessed rice-fish symbiotic ecological data and the rice-fish data heterogeneous graph are imported into the rice-fish attention network model, the feature vectors of the rice-fish symbiotic ecological data are obtained based on the rice-fish attention network model, and the feature vectors of the rice-fish symbiotic ecological data are spatially projected so that the feature vectors of the rice-fish symbiotic ecological data are mapped to the same space; The ecological attention weights of the nodes in the rice-fish data heterogeneous graph are obtained, and the rice-fish association is discovered based on the characteristic vectors of the rice-fish symbiotic ecological data based on the ecological attention weights to obtain the rice-fish association data.

3. The method of intelligent agricultural management based on image processing according to claim 1, characterized in that: The construction of the rice-fish attention network model includes: When constructing a rice-fish attention network model, a dynamic meta-learning framework is introduced into the rice-fish attention network model; The rice-fish symbiotic area was divided into blocks, and the rice-fish symbiotic area was divided into rectangular sub-areas of equal area, and the historical rice-fish symbiotic ecological data of each rectangular sub-area were obtained; The historical rice-fish symbiotic ecological data of different periods in the same rectangular sub-region are used as training positive samples, and the historical rice-fish symbiotic ecological data of the same period in different rectangular sub-regions are randomly combined, and the randomly combined historical rice-fish symbiotic ecological data are used as training negative samples. The rice-fish attention network model is trained based on training positive samples and training negative samples.

4. The method of intelligent agricultural management based on image processing according to claim 1, characterized in that: The rice-fish decision space is constructed based on the rice-fish association knowledge graph and combined with the rice-fish symbiotic ecological data, including: Obtain rice knowledge nodes, fish knowledge nodes, and environmental knowledge nodes in the rice-fish association knowledge graph, obtain knowledge node data based on the rice knowledge nodes, fish knowledge nodes, and environmental knowledge nodes, convert the knowledge node data into a rice-fish decision space vector, and convert the initial rice-fish causal network contained in the rice-fish association knowledge graph into a rice-fish association weight matrix; The rice-fish decision space is constructed based on the rice-fish decision space vector and the rice-fish association weight matrix.

5. The method for intelligent agricultural management based on image processing according to claim 1, characterized in that: The method of constructing a rice-fish data heterogeneous graph based on the rice-fish symbiotic ecological data after data preprocessing includes: The preprocessed rice-fish symbiotic ecological data is used to define graph nodes, obtain rice heterogeneous nodes, fish heterogeneous nodes and environment heterogeneous nodes, add edge relationship rules to the rice heterogeneous nodes, fish heterogeneous nodes and environment heterogeneous nodes, and link the rice heterogeneous nodes, fish heterogeneous nodes and environment heterogeneous nodes based on the edge relationship rules to generate a rice-fish data heterogeneous graph.

6. The method for intelligent agricultural management based on image processing according to claim 1, characterized in that: The method collects multi-source data of rice, fish and environment based on the rice-fish symbiosis regional network to obtain rice-fish symbiosis ecological data, wherein the rice-fish symbiosis ecological data includes rice data, fish data and environmental data, including: Rice-fish symbiosis ecological data are obtained based on the rice data collection terminal, fish data collection terminal and environmental data collection terminal of the rice-fish symbiosis regional network. The rice data includes chlorophyll content and canopy nitrogen accumulation, the fish data includes fish movement trajectory, fish feeding frequency and fish population density, and the environmental data includes water dissolved oxygen concentration, water nitrogen and ammonia concentration, water pH value and water temperature.

7. A smart agricultural management system based on image processing, used to implement the method according to any one of claims 1 to 6, characterized in that: include: A rice-fish symbiotic regional network, wherein the rice-fish symbiotic regional network is used to collect rice data, fish data, and environmental data within the rice-fish symbiotic region to obtain rice-fish symbiotic ecological data; A mapping module, which is used to preprocess the rice-fish symbiotic ecological data and construct a heterogeneous graph of the rice-fish data; A rice-fish model module, which is used to construct a rice-fish attention network model and obtain rice-fish association data based on a rice-fish data heterogeneous graph and rice-fish symbiotic ecological data; A knowledge construction module, which is used to perform rice-fish causal reasoning and generate a rice-fish association knowledge graph; The rice-fish decision module is used to generate rice-fish regulation decisions, and users can dynamically regulate the rice-fish symbiotic area based on the rice-fish regulation decisions.

8. The image processing-based smart agricultural management system according to claim 7, characterized in that: The rice-fish symbiotic regional network includes: A rice data collection terminal includes a drone swarm that patrols the rice-fish symbiotic area twice a day, acquiring chlorophyll content and canopy nitrogen accumulation based on the drone swarm. A fish data acquisition terminal, comprising an underwater sonar array and an infrared module, monitors fish based on the underwater sonar array and the infrared module to obtain fish movement trajectories, fish feeding frequency, and fish population density; The environmental data acquisition terminal is used to monitor the environment of the rice-fish symbiosis area and obtain the dissolved oxygen concentration, nitrogen and ammonia concentration, pH value and temperature of the water.

Images