Agricultural planting scheme dynamic optimization method and system based on knowledge graph

Abstract

The present application relates to the technical field of agricultural management, and specifically includes a knowledge graph-based dynamic optimization method and system for agricultural planting schemes, which comprises the following steps: preparing a planting topology graph, determining density and water-fertilizer matching parameters in combination with soil fertility grades and resource consumption coefficients, determining first and second deviation compensation data, configuring a distributed planting optimization architecture, and performing dynamic optimization of the agricultural planting scheme. The present application solves the technical problems of static solidification of agricultural planting schemes, lack of dynamic consideration of factors such as resource consumption and pest damage, poor consistency of crop growth, and low resource utilization efficiency, and achieves the technical effects of introducing crop growth state data and a deviation compensation mechanism, real-time adaptation of the planting scheme to environmental changes and crop growth states, precise mapping of the suitable growth range of crops and the nodes of the planting area based on the planting topology graph, improved consistency of crop growth and resource utilization efficiency, and significantly improved reliability and stability of the optimization of the planting scheme.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of agricultural management, and particularly relates to a knowledge graph-based dynamic optimization method and system for an agricultural planting scheme. BACKGROUND

[0002] With the rapid development of smart agriculture, precision planting has become the core direction for improving agricultural production efficiency and ensuring the quality of agricultural products. The spatial differences in soil fertility, light, temperature, etc. in the agricultural planting area, as well as the dynamic changes in the growth state of crops, all put forward higher requirements for the scientificity and adaptability of the planting scheme.

[0003] However, the current optimization of the agricultural planting scheme is mostly a fixed scheme based on historical experience or single environmental data, which cannot adapt to the differences in the needs of different growth periods of crops, and does not fully consider the spatial heterogeneity characteristics of soil fertility, microclimate, etc. in the planting area, resulting in low resource utilization efficiency, poor consistency of crop growth, and the like. In addition, the dynamic consideration of factors such as resource consumption and pest damage is lacking, which leads to insufficient reliability and stability of the optimization of the planting scheme, and it is difficult to meet the dynamic adaptation needs of precision planting in smart agriculture.

[0004] In summary, the existing technology has the technical problems of static solidification of the agricultural planting scheme, lack of dynamic consideration of factors such as resource consumption and pest damage, poor consistency of crop growth, and low resource utilization efficiency. SUMMARY

[0005] The present application provides a knowledge graph-based dynamic optimization method and system for an agricultural planting scheme, which aims to solve the technical problems of static solidification of the agricultural planting scheme in the prior art, lack of dynamic consideration of factors such as resource consumption and pest damage, poor consistency of crop growth, and low resource utilization efficiency.

[0006] In view of the above problems, the technical scheme of the present application is as follows:

[0007] In a first aspect, this application provides a method for dynamic optimization of agricultural planting schemes based on knowledge graphs. The method includes: developing a planting topology map mapping suitable crop growth range data and planting area node distribution based on environmental perception data of the agricultural planting area; generating a preset planting scheme associated with a dynamic planting optimization task based on the planting topology map, and determining density and water-fertilizer matching parameters by combining soil fertility level and resource consumption coefficient; introducing crop growth status data, and compensating for suitable crop growth range data in the planting topology map by combining the preset planting scheme, density, and water-fertilizer matching parameters to determine first deviation compensation data; compensating for the planting area node distribution in the planting topology map by combining the preset planting scheme, density, and water-fertilizer matching parameters through the dynamic planting optimization task to determine second deviation compensation data; connecting multiple collaboratively optimized planting management nodes, configuring a distributed planting optimization architecture by combining the first and second deviation compensation data, and performing dynamic optimization of the agricultural planting scheme using the distributed planting optimization architecture.

[0008] In a possible implementation, based on the preset planting scheme, and in combination with the first deviation compensation data and the second deviation compensation data, a dynamic planting adjustment path is set, and crop growth rate, resource utilization efficiency, and pest and disease incidence rate are recorded; based on the dynamic planting optimization task, and in combination with the crop growth rate, resource utilization efficiency, and pest and disease incidence rate, a distributed planting optimization architecture under the collaborative optimization of multiple planting management nodes is established.

[0009] In a possible implementation, the crop growth status data includes crop height, leaf area index, and growth cycle stage; a central optimization node that performs master optimization scheduling and a field adjustment node that performs slave optimization responses are defined; based on the crop growth status data, the distributed planting optimization architecture is used to dynamically optimize the planting plan for the central optimization node and the field adjustment node among the multiple planting management nodes.

[0010] In one possible implementation, the planting status data packet is broadcast to the field adjustment node in real time based on the central optimization node, and the crop growth status data is stored in the planting status data packet; after receiving the planting status data packet, the field adjustment node determines the lag compensation amount for growth deviation.

[0011] In a possible implementation, based on the crop growth state data, the central optimization node analyzes crop suitability of a corresponding planting area under different soil conditions and a first growth environment, acquires resource allocation data, and the first growth environment is used to represent light, temperature combination conditions of the central optimization node coverage area; based on the crop growth state data and growth deviation lag compensation amount, the field adjustment node analyzes crop growth matching degree of a corresponding planting area under different soil conditions and a second growth environment, acquires growth regulation quality data, and the second growth environment is used to represent microclimate differences of the field adjustment node relative to the central optimization node; and according to the central optimization node and resource allocation data, the field adjustment node and growth regulation quality data, a distributed planting optimization architecture under master-slave collaborative optimization control is set.

[0012] In a possible implementation, through the central optimization node and resource allocation data, a first master-slave collaborative optimization network layer having a mapping relationship with the central optimization node is configured by using feedforward regulation control under resource allocation data; through the central optimization node and resource allocation data, a second master-slave collaborative optimization network layer having a mapping relationship with the field adjustment node is configured by using active adaptive control of the crop growth sensor; and the first master-slave collaborative optimization network layer and the second master-slave collaborative optimization network layer are connected to obtain the distributed planting optimization architecture.

[0013] In a possible implementation, according to the dynamic planting adjustment path, a planting area coverage overlap coefficient is determined; and a resource consumption decay rate of the plurality of planting management nodes is introduced, and the planting scheme is fine-tuned in combination with the planting area coverage overlap coefficient.

[0014] In a possible implementation, based on the crop growth sensor, a coupling relationship between crop growth state and water and fertilizer supply amount is extracted; according to the coupling relationship between crop growth state and water and fertilizer supply amount, in combination with the planting area node distribution in the planting topology graph, compensation perpendicular to the main optimization direction is performed to determine a dynamic water and fertilizer offset amount that meets the growth stability constraint.

[0015] In a possible implementation, the density and water and fertilizer matching parameter includes a basic water and fertilizer supply amount; the dynamic water and fertilizer offset amount is superimposed on the basic water and fertilizer supply amount to form an actual water and fertilizer supply amount after dynamic adjustment, and the actual water and fertilizer supply amount is used for crop cultivation of a corresponding planting area of the field adjustment node; at the same time, environmental stress tolerance is evaluated, if the environmental stress tolerance jumps into an environmental stress tolerance risk controllable interval, three-dimensional stress vector data is acquired, the three-dimensional stress vector data includes a drought stress component, a saline-alkali stress component, and a disease and pest stress component; a water and fertilizer regulation unit is activated, a growth cycle calibration mechanism is started to realign a planting optimization link, and in combination with the three-dimensional stress vector data, the planting area coverage overlap coefficient is updated.

[0016] In a second aspect, the application provides a knowledge graph-based dynamic optimization system for an agricultural planting scheme, wherein the system comprises: a planting topology map formulation module configured to formulate a planting topology map having crop suitable growth range data and planting area node distribution mapped according to environmental perception data of an agricultural planting area; a density and water and fertilizer matching parameter determination module configured to generate a preset planting scheme associated with a dynamic planting optimization task according to the planting topology map, and determine density and water and fertilizer matching parameters in combination with soil fertility grades and resource consumption coefficients; a first deviation compensation data determination module configured to introduce crop growth state data, and compensate for the crop suitable growth range data in the planting topology map in combination with the preset planting scheme and the density and water and fertilizer matching parameters to determine first deviation compensation data; a second deviation compensation data determination module configured to compensate for the planting area node distribution in the planting topology map in combination with the preset planting scheme and the density and water and fertilizer matching parameters through the dynamic planting optimization task to determine second deviation compensation data; and a distributed planting optimization architecture configuration module configured to connect multiple planting management nodes for collaborative optimization, configure a distributed planting optimization architecture in combination with the first deviation compensation data and the second deviation compensation data, and perform dynamic optimization of an agricultural planting scheme based on the distributed planting optimization architecture.

[0017] In summary, the one or more technical solutions provided in the application introduce crop growth state data and a deviation compensation mechanism, perform real-time adaptation of a planting scheme to environmental changes and crop growth states, perform accurate mapping of crop suitable growth ranges and planting area nodes based on a planting topology map, improve crop growth consistency and resource utilization efficiency, and significantly improve the reliability and stability of planting scheme optimization. BRIEF DESCRIPTION OF DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the application or the prior art, the following will briefly introduce the drawings needed in the embodiments or the prior art description. Obviously, the drawings in the following description are only exemplary, and those skilled in the art can obtain other drawings according to the provided drawings without creative labor.

[0019] Figure 1 A flowchart of a knowledge graph-based dynamic optimization method for an agricultural planting scheme is provided for the application.

[0020] Figure 2 A structural diagram of a knowledge graph-based dynamic optimization system for an agricultural planting scheme is provided for the application.

[0021] Label explanation: planting topology map planning module M100, density and water and fertilizer matching parameter determination module M200, first deviation compensation data determination module M300, second deviation compensation data determination module M400, distributed planting optimization architecture configuration module M500. DETAILED DESCRIPTION

[0022] Below, the technical solutions in the present application will be described clearly and completely with reference to the drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described here. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application. In addition, it should be noted that, for the convenience of description, only part of the present application is shown in the drawings, not all.

[0023] Embodiment one, the present application will be described in detail below with reference to the drawings, as shown in Figure 1 The present application provides a knowledge graph-based dynamic optimization method for agricultural planting schemes, wherein the method comprises:

[0024] S1: According to the environmental perception data of the agricultural planting area, a planting topology map is planned, which maps the crop suitable growth range data and the node distribution of the planting area; S2: According to the planting topology map, a preset planting scheme associated with dynamic planting optimization tasks is generated, and the density and water and fertilizer matching parameters are determined in combination with the soil fertility grade and resource consumption coefficient.

[0025] Specifically, the environmental perception data refers to various environmental parameters collected by a sensor network in the agricultural planting area, including soil moisture, temperature, light intensity, and carbon dioxide concentration, which can reflect the environmental conditions of the planting area in real time and provide basic information for the formulation of the planting scheme; The planting topology map refers to a structured chart that divides the planting area into multiple nodes and maps the crop suitable growth range data and the node distribution. The planting topology map shows the spatial layout of the planting area, including the environmental characteristics of each node and the type, density, and other information of the suitable planting crops.

[0026] The dynamic planting optimization task refers to adjusting the planting scheme in real time according to the growth stage of crops and environmental changes. Unlike traditional static planting schemes, the dynamic optimization task can be adjusted according to real-time data to adapt to various changes that occur during planting. The soil fertility level refers to the classification of soil fertility based on factors such as nutrient content, texture, and structure. It is usually divided into high, medium, and low levels to guide the application amount of fertilizer and planting density during planting. The resource consumption coefficient refers to the proportion of resources consumed per unit area or unit yield during planting. By calculating the resource consumption coefficient, resource allocation can be optimized, and resource utilization efficiency can be improved. Further, the resources consumed per unit area or unit yield include water and fertilizer.

[0027] Execution steps: Collect environmental perception data, including soil fertility, light, temperature, humidity, and other parameters, through a sensor network deployed in the agricultural planting area. According to the collected environmental perception data, divide the planting area into multiple nodes and assign appropriate crop growth range data to each node. Further, determine the appropriate crop species and density for different nodes based on soil fertility and light conditions.

[0028] Based on the planting topology map, combine soil fertility levels and resource consumption coefficients to generate a preset planting scheme associated with dynamic planting optimization tasks. Specifically, determine the fertilizer application amount for different nodes by analyzing soil fertility levels. Optimize planting density and water-fertilizer ratio based on resource consumption coefficients to ensure efficient resource utilization. On the basis of the preset planting scheme, further determine the density and water-fertilizer matching parameters, for example, for nodes with high fertility, appropriately increase the planting density and optimize the water-fertilizer ratio to improve yield and resource utilization efficiency.

[0029] In the above steps, the planting area can be subdivided into multiple small nodes through the division of the planting topology map. Each node determines the appropriate crop species and density based on its soil fertility and light conditions. This fine management approach can significantly improve the consistency of crop growth and avoid uneven growth caused by environmental differences. In addition, the planting density and water-fertilizer matching parameters determined based on soil fertility levels and resource consumption coefficients accurately map the environmental characteristics of the planting area and the appropriate growth range of crops, effectively improving resource utilization efficiency.

[0030] S3: Introduce crop growth state data, combine the preset planting scheme, density and water and fertilizer matching parameters, compensate the crop suitable growth range data in the planting topological graph, and determine the first deviation compensation data; S4: Through the dynamic planting optimization task, combine the preset planting scheme, density and water and fertilizer matching parameters, compensate the planting area node distribution in the planting topological graph, and determine the second deviation compensation data; S5: Connect multiple planting management nodes of collaborative optimization, combine the first deviation compensation data and the second deviation compensation data, configure a distributed planting optimization architecture, and perform dynamic optimization of the agricultural planting scheme based on the distributed planting optimization architecture.

[0031] Specifically, the crop growth state data refers to data reflecting the current growth status of crops, including crop height, leaf area index, leaf nutrient element content, growth cycle stage, etc., which can real-time feedback the health status and growth demand of crops, and is the basis for dynamic optimization of the planting scheme; the first and second deviation compensation data refers to data calculated to correct the deviation in the planting scheme caused by environmental perception error, crop growth prediction error and other factors, further, the first deviation compensation data compensates the crop suitable growth range data, and the second deviation compensation data compensates the planting area node distribution.

[0032] The multiple planting management nodes of collaborative optimization refer to multiple management units distributed in the planting area, including a central optimization node and a field adjustment node, and the multiple planting management nodes realize global dynamic optimization of the planting scheme through collaborative work, further, the central optimization node refers to a core intelligent fertilizer distribution station, and the field adjustment node refers to a distributed monitoring node; the distributed planting optimization architecture refers to an optimization architecture based on the collaborative work of multiple planting management nodes, which realizes dynamic adjustment and optimization of the planting scheme through distributed computing and data sharing, and the distributed planting optimization architecture can real-time respond to environmental changes and crop growth demand, and improve the flexibility and adaptability of the planting scheme.

[0033] Execution steps: through the sensor network deployed in the planting area, real-time collection of crop growth state data, including crop height, leaf area index, leaf nutrient element content, combination of crop growth state data and preset planting scheme, density and water and fertilizer matching parameters, for evaluating the rationality of the current planting scheme; comparison and analysis of the collected crop growth state data and the crop suitable growth range data in the planting topological graph, calculation of the first deviation compensation data, for example, the actual growth state of crops in a certain area is lower than expected, which indicates that the suitable growth range data of the area needs to be adjusted, and the crop suitable growth range data is corrected through the compensation mechanism to make it more consistent with the actual growth demand.

[0034] In combination with the dynamic planting optimization task, the distribution of the planting area nodes in the planting topology graph is analyzed, and the second deviation compensation data is calculated. For example, the growth of crops in a certain node is affected by the microclimate difference, and the node distribution needs to be adjusted. The node distribution is corrected through the compensation mechanism to make it more suitable for environmental changes. The first deviation compensation data and the second deviation compensation data are applied to the multiple planting management nodes to configure the distributed planting optimization architecture. Further, the central optimization node is responsible for overall optimization scheduling, and the on-site adjustment node is responsible for specific implementation. Through master-slave collaborative optimization control, dynamic adjustment and optimization of the planting scheme are realized. Under the distributed planting optimization architecture, the planting scheme is dynamically adjusted according to real-time data and the compensation mechanism. Further, the water and fertilizer supply is adjusted according to the crop growth state data, and the planting density is adjusted according to the environmental changes to ensure that the planting scheme is always in the optimal state.

[0035] In the above steps, by introducing the crop growth state data and the deviation compensation mechanism, errors in the planting scheme can be corrected in real time. Specifically, the first deviation compensation data is adjusted to reduce the growth imbalance caused by environmental differences, ensuring that the planting scheme always matches the actual growth needs and environmental conditions. The second deviation compensation data is adjusted to optimize the node distribution of the planting area, improve resource utilization efficiency, and reduce resource waste. In addition, through the collaborative work of the distributed planting optimization architecture, global dynamic optimization of the planting scheme can be realized, improving the optimization efficiency and reliability, and significantly improving the stability and adaptability of the planting scheme optimization.

[0036] Further, the multiple planting management nodes are connected in collaboration with the optimization, and the first deviation compensation data and the second deviation compensation data are configured to form a distributed planting optimization architecture. The method of the present application comprises:

[0037] Based on the preset planting scheme, the first deviation compensation data and the second deviation compensation data are combined to set a dynamic planting adjustment path, and the crop growth rate, resource utilization efficiency, and pest incidence are recorded. Based on the dynamic planting optimization task, the crop growth rate, resource utilization efficiency, and pest incidence are combined to establish a distributed planting optimization architecture under the collaborative optimization of the multiple planting management nodes.

[0038] Specifically, the dynamic planting adjustment path refers to the specific implementation path of adjusting various parameters in the planting process according to the preset planting scheme and the deviation compensation data. It is a dynamic and gradual adjustment process used to ensure that the planting scheme can adapt to environmental changes and crop growth needs. Further, the various parameters in the planting process include water and fertilizer supply, and planting density. The crop growth rate refers to the speed of crop growth per unit time, which is usually evaluated by measuring plant height, leaf area index, and other indicators, and is an important parameter for measuring the effect of the planting scheme.

[0039] Resource utilization efficiency refers to the efficiency of resource utilization in the planting process, which is measured by calculating the yield obtained per unit of resource input, and is an important indicator for evaluating the economic and sustainable nature of the planting scheme. Furthermore, resources in the planting process include water, fertilizer, and the incidence of plant diseases and insect pests. Disease and insect pest incidence refers to the frequency and severity of plant diseases and insect pests in the planting area, which is usually evaluated by monitoring the types and quantities of plant diseases and insect pests, and is an indicator for measuring the health and stability of the planting scheme. Plant management node collaborative optimization refers to the process of multiple plant management nodes working together through data sharing and collaboration to optimize the planting scheme. Plant management node collaborative optimization can achieve global dynamic optimization, improve the adaptability and reliability of the planting scheme, and further, the multiple plant management nodes include a central optimization node and a field adjustment node.

[0040] Execution step: based on the preset planting scheme, combined with the first deviation compensation data and the second deviation compensation data, the specific path of dynamic planting adjustment is determined, further, the water and fertilizer supply amount, planting density and other parameters are adjusted according to the deviation compensation data; during the adjustment process, the crop growth rate, resource utilization efficiency and disease and insect pest incidence are recorded in real time, further, the growth rate is calculated by real-time monitoring of crop height changes through a sensor network, the resource utilization efficiency is calculated by recording resource consumption through water and fertilizer sensors, and the disease and insect pest incidence is recorded through disease and insect pest monitoring equipment.

[0041] Based on the dynamic planting optimization task, combined with the recorded crop growth rate, resource utilization efficiency and disease and insect pest incidence, the effect of the current planting scheme is analyzed; according to the analysis result, a distributed planting optimization architecture for collaborative optimization of multiple plant management nodes is established, further, the central optimization node is responsible for overall optimization scheduling, and the field adjustment node is responsible for specific implementation adjustment; through master-slave collaborative optimization control, dynamic adjustment and optimization of the planting scheme are realized, further, the central optimization node adjusts the core parameters according to the overall data, and the field adjustment node fine-tunes according to the local data.

[0042] In the above steps, by setting the dynamic planting adjustment path, the parameters in the planting scheme can be adjusted in real time to ensure that the planting scheme always matches the actual growth needs and environmental conditions, for example, adjusting the water and fertilizer supply amount according to the crop growth rate, optimizing resource allocation according to the resource utilization efficiency, and adjusting the control measures according to the disease and insect pest incidence; the central optimization node adjusts the core parameters according to the overall data, and the field adjustment node fine-tunes according to the local data, thereby improving the flexibility and adaptability of the planting scheme, significantly improving the consistency of crop growth and resource utilization efficiency, reducing the occurrence of plant diseases and insect pests, and improving the stability and reliability of the planting scheme optimization.

[0043] Further, the method of the present application further comprises:

[0044] The crop growth state data includes crop plant height, leaf area index, and growth cycle stage; a central optimization node for executing main optimization scheduling and a field adjustment node for executing slave optimization response are defined; based on the crop growth state data, the central optimization node and the field adjustment node in the plurality of planting management nodes are dynamically optimized for planting scheme using the distributed planting optimization architecture.

[0045] Specifically, the crop plant height refers to the vertical height from the ground to the top of the crop, which is one of the important indicators for measuring the growth condition of the crop, reflecting the growth speed and health condition of the crop; the leaf area index refers to the ratio of the total area of plant leaves to the land area per unit of land area, reflecting the coverage degree of plant leaves, which is a key parameter for evaluating the photosynthesis efficiency and the growth condition of the crop; the growth cycle stage refers to the specific stage of the crop in the growth process, such as the seedling stage, the growth stage, the flowering stage, the fruiting stage, etc., and different growth stages have different demands for environmental conditions and resources, thus requiring targeted management measures.

[0046] The central optimization node is the core node in the distributed planting optimization architecture, responsible for overall optimization scheduling and decision-making, usually located at the center of the planting area, capable of collecting and processing data from each field adjustment node, and making global optimization according to these data; the field adjustment node is a plurality of local nodes distributed in the planting area, responsible for executing the instructions of the central optimization node, and making real-time adjustments according to the local environment and the growth state of the crop, capable of quickly responding to local changes, ensuring the implementation effect of the planting scheme, further, the instructions of the central optimization node include fertilization instructions, watering instructions.

[0047] Execution step: collect crop growth state data, including plant height, leaf area index and growth cycle stage, the crop growth state data is obtained in real time through a sensor network, further, the plant height is measured by laser radar, the leaf area index is measured by optical sensor, and the growth stage is determined by growth cycle monitoring equipment; the collected data is transmitted to the central optimization node for preliminary analysis and processing.

[0048] The central optimization node and the field adjustment node are defined, specifically, the central optimization node is responsible for overall optimization scheduling, and the field adjustment node is responsible for executing specific optimization measures; a communication link between the central optimization node and the field adjustment node is established to ensure real-time transmission and sharing of data; the central optimization node formulates a global optimization strategy according to the collected crop growth state data, combined with the preset planting scheme and the deviation compensation data, further, adjusts the light management strategy according to the leaf area index, and adjusts the fertilization plan according to the growth cycle stage; the field adjustment node receives the instructions of the central optimization node, and makes real-time adjustments according to the local environmental conditions and the growth state of the crop, further, adjusts the irrigation amount according to the plant height data, and adjusts the disease and pest control measures according to the growth cycle stage.

[0049] Through master-slave cooperative optimization control, dynamic adjustment of the planting scheme is realized. Specifically, the central optimization node adjusts the core parameters according to the overall data, and the field adjustment node fine-tunes according to the local data.

[0050] In the above steps, by introducing multi-dimensional growth state data such as crop height, leaf area index and growth cycle stage, the growth status of the crop can be more comprehensively reflected, providing more accurate basis for optimizing the planting scheme. Further, by monitoring the leaf area index, the photosynthesis efficiency can be more accurately evaluated, thereby optimizing the light management strategy; by monitoring the growth cycle stage, the fertilization and irrigation plan can be adjusted accordingly to ensure that the crop can obtain suitable growth conditions at different stages. At the same time, by defining the central optimization node and the field adjustment node, and using the distributed planting optimization architecture for cooperative optimization, global and local dynamic adjustment can be realized. Further, the central optimization node can adjust the core parameters according to the overall data, and the field adjustment node can fine-tune according to the local data, thereby improving the flexibility and adaptability of the planting scheme.

[0051] Further, the method of the application further comprises:

[0052] Based on the central optimization node, the planting state data packet is broadcasted to the field adjustment node in real time, and the crop growth state data is stored in the planting state data packet; after receiving the planting state data packet, the field adjustment node determines the growth deviation lag compensation amount.

[0053] Specifically, the planting state data packet refers to a data structure containing crop growth state data, used for transmitting key information between the central optimization node and the field adjustment node, to ensure efficient transmission and sharing of information. Further, the crop growth state data includes height, leaf area index, and growth cycle stage; real-time broadcast refers to the central optimization node sending the planting state data packet to all field adjustment nodes in the form of broadcast, to ensure that each node can obtain the latest crop growth state information in real time; the growth deviation lag compensation amount refers to the field adjustment node calculating the amount of compensation according to the deviation between the current crop growth state and the preset target after receiving the planting state data packet. The growth deviation lag compensation amount takes into account the hysteresis of the growth deviation, i.e. the time delay and spatial difference between the actual growth state and the expected target.

[0054] The execution step: the central optimization node collects and integrates the crop growth state data from various sensors, including plant height, leaf area index and growth cycle stage, encapsulates the crop growth state data into a planting state data package and broadcasts it to all field adjustment nodes in real time through the communication network, for example, the central optimization node broadcasts the planting state data package every 10 minutes, ensuring that the field adjustment node can obtain the latest growth information in time; the field adjustment node receives the planting state data package broadcast by the central optimization node and analyzes the crop growth state data therein; the field adjustment node calculates the growth deviation lag compensation amount according to the deviation between the actual growth state of the current crop and the preset target, for example, if the plant height of the crop in a certain area is lower than the expected target, the field adjustment node will calculate the irrigation amount or fertilizer amount that needs to be increased to compensate for the growth deviation, and the field adjustment node adjusts the local planting management measures according to the calculated compensation amount, including adjusting the irrigation time, fertilizer amount or pest control strategy.

[0055] In the above steps, by broadcasting the planting state data package in real time, the central optimization node can quickly transmit global information to each field adjustment node, so that each field adjustment node can make local adjustments based on the latest data, ensuring information synchronization and collaborative work between the central optimization node and the field adjustment node, for example, in a planting area, the central optimization node discovers through broadcasting that the leaf area index of the crop in a certain area is lower than expected, which means that the area is insufficient in light or nutrient supply, after receiving this information, the field adjustment node calculates the increased fertilizer amount or adjusts the irrigation strategy to compensate for the growth deviation, this mechanism can significantly improve the consistency of crop growth and reduce the growth imbalance caused by local environmental differences, at the same time, by timely adjusting the planting management measures, it can effectively improve the resource utilization efficiency and reduce waste, in addition, the calculation of the growth deviation lag compensation amount takes into account the hysteresis of the growth deviation, so as to more accurately adjust the planting scheme.

[0056] Further, based on the crop growth state data, the distributed planting optimization architecture is used to dynamically optimize the planting scheme of the central optimization node and the field adjustment node in the plurality of planting management nodes, the method of the present application comprises:

[0057] Based on the crop growth state data, the central optimization node analyzes the crop suitability of the corresponding planting area under different soil conditions and a first growth environment, obtains resource allocation data, and the first growth environment is used to represent the light, temperature combination conditions of the central optimization node coverage area; based on the crop growth state data, growth deviation lag compensation amount, the field adjustment node analyzes the crop growth matching degree of the corresponding planting area under different soil conditions and a second growth environment, obtains growth regulation quality data, and the second growth environment is used to represent the microclimate difference of the field adjustment node relative to the central optimization node; according to the central optimization node and resource allocation data, the field adjustment node and growth regulation quality data, a distributed planting optimization architecture under master-slave collaborative optimization control is set.

[0058] Specifically, crop suitability refers to the growth adaptability of crops under the conditions of the first growth environment, reflecting the potential of crops to grow healthily and achieve expected yield under these conditions. Further, the first growth environment includes soil fertility, light, and temperature. Resource allocation data refers to the specific parameters of resources allocated to the central optimization node coverage area based on crop suitability analysis results, which is used to guide the central optimization node to reasonably allocate resources to meet the crop growth needs. The second growth environment is used to represent the microclimate difference of the field adjustment node relative to the central optimization node, specifically including water, air humidity, wind speed, and carbon dioxide concentration. These factors directly affect the real-time state of local crop growth and are the core of field control decisions.

[0059] The second growth environment includes water, air humidity, wind speed, and carbon dioxide concentration. Specifically, the second growth environment focuses on the microclimate difference of the field adjustment node relative to the central optimization node. Key elements of farmland microclimate include water vapor, air flow, and gas composition. Water is the foundation and needs to be combined with related elements that affect crop transpiration, pollination, and metabolism. Further, air humidity affects crop transpiration and disease occurrence, wind speed is related to field ventilation and heat exchange, and carbon dioxide concentration directly determines photosynthesis efficiency. Air humidity, wind speed, and carbon dioxide concentration are all microenvironment parameters that need to be controlled in field fine-tuning.

[0060] The first growth environment and the second growth environment are complementary. The first growth environment includes soil fertility, light, and temperature, focusing on regional macro basic conditions and having a general impact on crop growth in the entire region. The second growth environment includes water, air humidity, wind speed, and carbon dioxide concentration, which refers to the microclimate difference of the field adjustment node relative to the central optimization node, and precisely corresponds to the differentiated adjustment needs of local areas, having a direct impact on crop growth in local areas.

[0061] The growth regulation quality data refers to data obtained by analyzing the crop growth matching degree of the planting area corresponding to the field adjustment node according to the crop growth state data and the growth deviation lag compensation amount, and reflects the growth regulation effect of the field adjustment node under the microclimate condition; the master-slave collaborative optimization control refers to the collaborative working mode between the central optimization node and the field adjustment node, the master node is responsible for overall resource allocation and optimization strategy formulation, and the slave node is responsible for executing specific growth regulation measures according to local conditions.

[0062] The execution step is: based on the crop growth state data, analyzing the crop suitability of the central optimization node coverage area under different soil conditions and the first growth environment, further, the crop growth state data includes plant height, leaf area index, growth cycle stage, and the first growth environment includes soil fertility, light, temperature, for example, through analysis, it is found that the soil fertility of a certain area is high and the light is sufficient, which is suitable for planting high-yield crop varieties; according to these analysis results, resource allocation data is obtained to determine the water and fertilizer supply amount and light management strategy of the area.

[0063] Based on the crop growth state data and the growth deviation lag compensation amount, the crop growth matching degree of the planting area corresponding to the field adjustment node under different soil conditions and the second growth environment is analyzed, further, the second growth environment includes water, air humidity, wind speed, and carbon dioxide concentration, for example, the field adjustment node finds that the crop growth rate is slow due to the microclimate difference in a local area; by calculating the growth deviation lag compensation amount, growth regulation quality data is obtained to determine the light time and fertilizer amount that need to be increased.

[0064] According to the resource allocation data of the central optimization node and the growth regulation quality data of the field adjustment node, a distributed planting optimization architecture under master-slave collaborative optimization control is set; the central optimization node formulates a global optimization strategy according to the overall resource allocation data, and the field adjustment node executes specific local optimization measures according to the growth regulation quality data, further, the central optimization node adjusts the overall irrigation plan, and the field adjustment node adjusts the irrigation amount according to the local demand.

[0065] In the above steps, through the crop suitability analysis of the central optimization node, resources can be reasonably allocated to ensure that the crop growth needs of the entire area are met, at the same time, the growth regulation quality analysis of the field adjustment node can accurately regulate according to the local microclimate difference to ensure that the crops in each local area can grow in the best conditions; through the master-slave collaborative optimization control architecture, the central optimization node and the field adjustment node can work efficiently and collaboratively to ensure the collaborative work of global optimization and local adjustment, significantly improving the fine management level of intelligent agricultural planting.

[0066] Further, the distributed planting optimization architecture under master-slave collaborative optimization control is set, and the method of the present application comprises:

[0067] By the central optimization node and resource allocation data, a first master-slave collaborative optimization network layer with a mapping relationship with the central optimization node is configured by using feedforward regulation control under resource allocation data; by the central optimization node and resource allocation data, a second master-slave collaborative optimization network layer with a mapping relationship with the field adjustment node is configured by using active adaptive control of crop growth sensors; the first master-slave collaborative optimization network layer and the second master-slave collaborative optimization network layer are connected to obtain the distributed planting optimization architecture.

[0068] Specifically, feedforward regulation control refers to adjusting system parameters in advance to cope with known or predictable changes based on prediction and pre-set control strategies. In agricultural planting, feedforward regulation can adjust irrigation, fertilization and other operations in advance according to resource allocation data to adapt to the needs of crop growth; active adaptive control refers to actively adjusting planting management measures to adapt to the actual growth needs of crops and environmental changes by monitoring the growth state of crops in real time. Further, the growth state of crops includes data such as plant height and leaf area index obtained through sensors.

[0069] The first master-slave collaborative optimization network layer refers to the optimization network layer directly related to the central optimization node, which is responsible for formulating and implementing global optimization strategies according to resource allocation data, has a mapping relationship with the central optimization node, and is the core part of the distributed optimization architecture; the second master-slave collaborative optimization network layer refers to the optimization network layer directly related to the field adjustment node, which is responsible for local optimization adjustment according to real-time data of crop growth sensors, has a mapping relationship with the field adjustment node, and is the execution part of the distributed optimization architecture; the distributed planting optimization architecture refers to a system architecture composed of multiple optimization network layers, which realizes dynamic optimization of planting schemes through the collaborative work of the central optimization node and the field adjustment node. The distributed planting optimization architecture combines the advantages of global optimization and local adjustment, and can flexibly cope with various changes in the planting process.

[0070] Execution steps: based on the resource allocation data of the central optimization node, a first master-slave collaborative optimization network layer is configured by using a feedforward regulation control strategy, for example, according to the resource allocation data, the growth needs of crops in different regions are predicted, and irrigation and fertilization plans are adjusted in advance. If the soil fertility of a certain region is low, the feedforward regulation will increase the amount of fertilizer in that region to ensure that the growth needs of crops are met; based on the resource allocation data of the central optimization node, a second master-slave collaborative optimization network layer is configured by using an active adaptive control strategy combined with real-time data of crop growth sensors, for example, the field adjustment node monitors the leaf area index of crops in a certain region through sensors and finds that it is lower than expected. Active adaptive control will adjust the light time and irrigation amount in that region to promote crop growth.

[0071] The first master-slave collaborative optimization network layer and the second master-slave collaborative optimization network layer are connected to form a complete distributed planting optimization architecture, the central optimization node is responsible for global resource allocation and optimization strategy formulation, and the field adjustment node is responsible for real-time adjustment according to local data. Further, the central optimization node adjusts the irrigation plan according to the overall resource allocation data, and the field adjustment node fine-tunes the irrigation amount according to the local sensor data.

[0072] In the above steps, through feedforward control, the first master-slave collaborative optimization network layer can adjust the planting management measures in advance, reducing the hysteresis problem caused by changes in the environment or changes in the growth needs of crops. At the same time, through active adaptive control, the second master-slave collaborative optimization network layer can make precise adjustments according to real-time monitoring data to ensure that crops in each local area can grow in the best conditions. By connecting the first master-slave collaborative optimization network layer and the second master-slave collaborative optimization network layer, a distributed planting optimization architecture is formed, and the central optimization node and the field adjustment node can work efficiently to achieve dynamic optimization of the global and local.

[0073] Further, the method of the present application further comprises:

[0074] According to the dynamic planting adjustment path, a planting area coverage overlap coefficient is determined; a resource consumption decay rate of the plurality of planting management nodes is introduced, and the planting scheme is fine-tuned in combination with the planting area coverage overlap coefficient.

[0075] Specifically, the planting area coverage overlap coefficient is a quantitative indicator of the degree of overlap of the coverage area between different management nodes due to resource allocation and planting operations in the planting area, reflecting the accuracy and efficiency of resource allocation in the planting management process. A higher overlap coefficient means resource waste or management redundancy. The resource consumption decay rate refers to the proportion of resource loss in the transmission and use process in the planting management process, reflecting the effective utilization rate of resources in actual application, which is usually related to the distance of resource allocation, transmission mode and environmental conditions. Resources include water, fertilizer and pesticides. Planting scheme fine-tuning refers to local adjustment of the planting scheme based on the planting area coverage overlap coefficient and the resource consumption decay rate to optimize resource allocation and improve planting efficiency. Planting scheme fine-tuning usually involves adjusting irrigation amount, fertilizer amount, planting density and other parameters.

[0076] Execution step: based on the dynamic planting adjustment path, the resource allocation and coverage area of different planting management nodes are analyzed, the planting area coverage overlap coefficient is calculated, further, through geographic information system technology, the overlap degree between different irrigation areas or fertilization areas is determined in combination with sensor data, further, for two adjacent irrigation areas located in the same planting area, the two adjacent irrigation areas have partial overlap, which means that part of the area will receive double the irrigation amount, resulting in resource waste.

[0077] Collect resource consumption attenuation rate data of multiple planting management nodes, which is monitored in real time by a sensor network, including monitoring water pressure loss of irrigation systems and diffusion efficiency of fertilizers in soil; analyze the influence of resource consumption attenuation rate on actual resource utilization efficiency, for example, find that in areas far from the irrigation water source, water pressure attenuation leads to reduced irrigation efficiency; adjust the planting scheme by combining the resource consumption attenuation rate and the overlap coefficient of the planting area, for example, reduce the irrigation or fertilization amount in the overlapping area, while increasing the resource supply in the area with high resource consumption; optimize resource allocation by adjusting irrigation and fertilization plans, specifically, reduce irrigation in overlapping areas and increase irrigation in areas with high resource consumption to ensure efficient use of resources.

[0078] In the above steps, by accurately analyzing the resource allocation and the overlap of the coverage area, combined with the resource consumption attenuation rate, the planting scheme can be further optimized, resource waste can be reduced, and planting efficiency can be improved. At the same time, optimizing resource allocation reduces efficiency loss due to resource waste or management redundancy, further improving overall planting efficiency. In addition, this fine-tuning mechanism can significantly improve the adaptability and flexibility of the planting scheme, ensuring the stability and reliability of the planting scheme under different environmental conditions.

[0079] Further, the active adaptive control of the crop growth sensor is used, and the second master-slave collaborative optimization network layer with a mapping relationship with the on-site adjustment node is configured. The method of the present application further comprises:

[0080] Based on the crop growth sensor, the coupling relationship between crop growth state and water and fertilizer supply is extracted; according to the coupling relationship between crop growth state and water and fertilizer supply, combined with the distribution of planting area nodes in the planting topology graph, compensation perpendicular to the main optimization direction is performed to determine the dynamic water and fertilizer offset that meets the growth stability constraint.

[0081] Specifically, the crop growth sensor is a sensor for real-time monitoring of the growth status of crops, including measuring plant height, leaf area index, and leaf nutrient element content. The crop growth sensor can provide quantitative data on crop growth for analyzing the health status and growth needs of crops. In agricultural planting, there is a coupling relationship between the growth status of crops and the supply of water and fertilizer, i.e., the growth status of crops will affect their demand for water and fertilizer, and the supply of water and fertilizer will in turn affect the growth status of crops. The main optimization direction refers to the direction mainly concerned in the planting optimization process, usually the overall planting scheme optimization, such as planting density, irrigation and fertilization plan, etc. The compensation perpendicular to the main optimization direction refers to the adjustment made for local areas or specific conditions outside the main optimization direction. The dynamic water and fertilizer offset refers to the adjustment value of the water and fertilizer supply calculated based on the coupling relationship between the growth status of crops and the supply of water and fertilizer, combined with the distribution of planting area nodes, for compensating for the growth needs difference of local areas and ensuring the stability of crop growth.

[0082] Execution steps: Collect crop growth status data using crop growth sensors, including plant height, leaf area index, and leaf nutrient element content. Analyze the relationship between these growth status data and water and fertilizer supply, and extract the coupling relationship, for example, through data analysis, it is found that when the leaf area index reaches a certain threshold, the demand for nitrogen fertilizer of crops will increase significantly; when the soil humidity is lower than a certain threshold, the growth rate of crops will slow down.

[0083] Based on the distribution of planting area nodes in the planting topology graph, analyze the growth status of crops and the water and fertilizer supply of each node. According to the coupling relationship, calculate the dynamic water and fertilizer offset of each node, for example, the growth status of crops in a certain node shows that the demand for phosphorus fertilizer increases, and the current supply is insufficient, so the phosphorus fertilizer supply of this node needs to be increased. This compensation is perpendicular to the main optimization direction, i.e., based on the overall optimization scheme, fine-tune the local area to meet the growth needs of crops under specific conditions.

[0084] In the above steps, by extracting the coupling relationship between the growth status of crops and the supply of water and fertilizer, the planting scheme can be adjusted more accurately to ensure that the needs of crops in different growth stages and environmental conditions are met, for example, in a planting area, through crop growth sensors, it is found that the leaf nutrient element content of crops in a certain area is lower than expected, indicating that the area lacks a certain nutrient element. By analyzing the coupling relationship, determine the type and amount of fertilizer that needs to be increased, calculate the dynamic water and fertilizer offset, and fine-tune the area to improve the consistency and stability of crop growth, reduce the growth difference caused by local nutrient deficiency. In addition, through the compensation perpendicular to the main optimization direction, resource allocation can be further optimized, and resource utilization efficiency can be improved.

[0085] Further, the method of the present application further comprises:

[0086] The density and water and fertilizer matching parameters include a basic water and fertilizer supply amount; the dynamic water and fertilizer offset amount is superimposed on the basic water and fertilizer supply amount to form a dynamically adjusted actual water and fertilizer supply amount, which is used for on-site adjustment of the crop cultivation of the planting area corresponding to the node; at the same time, environmental stress tolerance evaluation is performed, if the environmental stress tolerance jumps into an environmental stress tolerance risk controllable interval, three-dimensional stress vector data is obtained, the three-dimensional stress vector data includes drought stress component, saline-alkali stress component, and disease and pest stress component; a water and fertilizer regulation unit is activated, and a growth cycle calibration mechanism is started to realign the planting optimization link, and the three-dimensional stress vector data is combined to update the planting area coverage overlap coefficient.

[0087] Specifically, the basic water and fertilizer supply amount refers to the water and fertilizer supply amount pre-set in the planting scheme to meet the basic growth needs of crops, which is used to ensure that crops can grow healthily under normal environmental conditions; the dynamic water and fertilizer offset amount refers to the adjustment value of the water and fertilizer supply amount calculated according to the coupling relationship between the crop growth state and the water and fertilizer supply amount and the specific conditions of the planting area, which is used to compensate for the growth requirement difference of the local area and ensure the stability of crop growth; the actual water and fertilizer supply amount refers to the final water and fertilizer supply amount obtained by superimposing the dynamic water and fertilizer offset amount on the basic water and fertilizer supply amount, which is used to guide the specific water and fertilizer management measures of the corresponding planting area of the on-site adjustment node.

[0088] The environmental stress tolerance evaluation refers to the evaluation of the environmental stress faced by the planting area to determine whether these stresses are within an acceptable risk range, which is usually based on sensor data and historical experience to determine whether additional control measures are needed, further, the environmental stress includes drought, saline-alkali, and disease and pest; the three-dimensional stress vector data refers to comprehensive data containing drought stress component, saline-alkali stress component, and disease and pest stress component, which is used to quantify the multiple environmental stresses faced by the planting area and provide a basis for control measures; the water and fertilizer regulation unit refers to a device or system responsible for adjusting water and fertilizer supply according to the evaluation results and stress data, which can dynamically adjust the water and fertilizer supply amount according to real-time data to cope with environmental stress; the growth cycle calibration mechanism refers to an adjustment mechanism for realigning the planting optimization link to ensure that the planting scheme is consistent with the actual growth cycle of crops, which dynamically adjusts the key parameters in the planting scheme by analyzing the crop growth state and environmental stress data.

[0089] The execution step is: superimposing the dynamic water and fertilizer offset on the basic water and fertilizer supply amount to form the actual water and fertilizer supply amount after dynamic adjustment, and the actual water and fertilizer supply amount after dynamic adjustment is used to guide the specific water and fertilizer management measures of the planting area corresponding to the node on the spot; the environmental stress faced by the planting area is evaluated to determine whether the stress is within an acceptable risk range. Specifically, the soil humidity, salinity and disease and pest incidence are monitored by sensors to evaluate whether the drought stress, salinity stress and disease and pest stress exceed the preset tolerance threshold; if the environmental stress tolerance jumps into the risk controllable interval, three-dimensional stress vector data including the drought stress component, the salinity stress component and the disease and pest stress component are obtained.

[0090] The water and fertilizer regulation unit is activated to adjust the water and fertilizer supply amount according to the three-dimensional stress vector data; the growth cycle calibration mechanism is started to realign the planting optimization link, and the planting area coverage overlap coefficient is updated. Specifically, the irrigation amount is increased according to the drought stress component, the fertilizer type is adjusted according to the salinity stress component, the pesticide application amount is increased according to the disease and pest stress component, and the planting area coverage overlap coefficient is updated to optimize resource allocation.

[0091] In the above steps, by dynamically adjusting the water and fertilizer supply amount, the growth needs of crops under different environmental conditions can be more accurately met. Further, by superimposing the dynamic water and fertilizer offset on the basic water and fertilizer supply amount, the consistency and stability of crop growth can be significantly improved, and the growth difference caused by local nutrient deficiency or environmental stress can be reduced. At the same time, through the environmental stress tolerance evaluation and the acquisition of three-dimensional stress vector data, environmental stress problems that may occur during planting can be discovered and addressed in a timely manner. Further, by activating the water and fertilizer regulation unit and starting the growth cycle calibration mechanism, the planting scheme can be dynamically adjusted to ensure that crops can still grow healthily under stress conditions. This dynamic adjustment mechanism improves planting efficiency and realizes fine agricultural planting management.

[0092] In summary, the beneficial effects of the embodiments of the present application are:

[0093] The crop suitable growth range data and the planting area node distribution are mapped in the planting topology graph according to the environmental perception data of the agricultural planting area; the preset planting scheme associated with the dynamic planting optimization task is generated according to the planting topology graph, the density and water and fertilizer matching parameters are determined in combination with the soil fertility grade and the resource consumption coefficient; the crop growth state data is introduced, the preset planting scheme, the density and water and fertilizer matching parameters are combined, the crop suitable growth range data in the planting topology graph is compensated, the first deviation compensation data is determined; the planting area node distribution in the planting topology graph is compensated through the dynamic planting optimization task, the preset planting scheme, the density and water and fertilizer matching parameters are combined, the second deviation compensation data is determined; the distributed planting optimization architecture is configured in combination with the first deviation compensation data and the second deviation compensation data by connecting the multiple planting management nodes optimized in collaboration, and the agricultural planting scheme dynamic optimization is performed based on the distributed planting optimization architecture. The application realizes the introduction of the crop growth state data and the deviation compensation mechanism, the real-time adaptation of the planting scheme to the environmental changes and the crop growth state, the accurate mapping of the crop suitable growth range and the planting area node based on the planting topology graph, the improvement of the crop growth consistency and the resource utilization efficiency, and the significant improvement of the reliability and stability of the planting scheme optimization.

[0094] In the embodiment two, based on the same inventive concept as the agricultural planting scheme dynamic optimization method based on the knowledge graph in the foregoing embodiments, as shown in the embodiment two, the application provides an agricultural planting scheme dynamic optimization system based on the knowledge graph, wherein the system comprises: Figure 2 The planting topology graph determination module M100 determines the planting topology graph which maps the crop suitable growth range data and the planting area node distribution according to the environmental perception data of the agricultural planting area.

[0095] The density and water and fertilizer matching parameter determination module M200 generates the preset planting scheme associated with the dynamic planting optimization task according to the planting topology graph, and determines the density and water and fertilizer matching parameters in combination with the soil fertility grade and the resource consumption coefficient.

[0096] The first deviation compensation data determination module M300 introduces the crop growth state data, combines the preset planting scheme, the density and water and fertilizer matching parameters, compensates the crop suitable growth range data in the planting topology graph, and determines the first deviation compensation data.

[0097] The second deviation compensation data determination module M400 compensates the planting area node distribution in the planting topology graph through the dynamic planting optimization task in combination with the preset planting scheme, the density and water and fertilizer matching parameters, and determines the second deviation compensation data.

[0098]

[0099] ​The distributed planting optimization architecture configuration module M500 is connected with multiple planting management nodes in cooperative optimization, combines the first deviation compensation data and the second deviation compensation data, configures a distributed planting optimization architecture, and performs dynamic optimization of an agricultural planting scheme based on the distributed planting optimization architecture.

[0100] Further, the distributed planting optimization architecture configuration module M500 is used to perform the following method:

[0101] Based on the preset planting scheme, the dynamic planting adjustment path is set in combination with the first deviation compensation data and the second deviation compensation data, and the crop growth rate, resource utilization efficiency, and pest occurrence rate are recorded; based on the dynamic planting optimization task, the distributed planting optimization architecture under the cooperative optimization of multiple planting management nodes is established in combination with the crop growth rate, resource utilization efficiency, and pest occurrence rate.

[0102] Further, the distributed planting optimization architecture configuration module M500 is also used to perform the following method:

[0103] The crop growth state data includes crop plant height, leaf area index, and growth cycle stage; a central optimization node performing main optimization scheduling and a field adjustment node performing slave optimization response are defined; based on the crop growth state data, the central optimization node and the field adjustment node in the multiple planting management nodes are dynamically optimized for a planting scheme using the distributed planting optimization architecture.

[0104] Further, the distributed planting optimization architecture configuration module M500 is also used to perform the following method:

[0105] Based on the central optimization node, a planting state data packet is broadcast in real time to the field adjustment node, and the crop growth state data is stored in the planting state data packet; after the field adjustment node receives the planting state data packet, a growth deviation lag compensation amount is determined.

[0106] Further, the distributed planting optimization architecture configuration module M500 is also used to perform the following method:

[0107] Based on the crop growth state data, the central optimization node analyzes the crop suitability of the corresponding planting area under different soil conditions and a first growth environment, obtains resource allocation data, and the first growth environment is used to represent the light and temperature combination conditions of the central optimization node coverage area; based on the crop growth state data and growth deviation lag compensation amount, the field adjustment node analyzes the crop growth matching degree of the corresponding planting area under different soil conditions and a second growth environment, obtains growth regulation quality data, and the second growth environment is used to represent the microclimate difference of the field adjustment node relative to the central optimization node; according to the central optimization node and resource allocation data, the field adjustment node and growth regulation quality data, a distributed planting optimization architecture under master-slave collaborative optimization control is set.

[0108] Further, the distributed planting optimization architecture configuration module M500 is also used to execute the following method:

[0109] Through the central optimization node and resource allocation data, a first master-slave collaborative optimization network layer with a mapping relationship with the central optimization node is configured by using feedforward regulation control under resource allocation data; through the central optimization node and resource allocation data, a second master-slave collaborative optimization network layer with a mapping relationship with the field adjustment node is configured by using active adaptive control of the crop growth sensor; the first master-slave collaborative optimization network layer and the second master-slave collaborative optimization network layer are connected to obtain the distributed planting optimization architecture.

[0110] Further, the distributed planting optimization architecture configuration module M500 is also used to execute the following method:

[0111] According to the dynamic planting adjustment path, a planting area coverage overlap coefficient is determined; a resource consumption attenuation rate of the plurality of planting management nodes is introduced, and the planting area coverage overlap coefficient is combined to fine-tune the planting scheme.

[0112] Further, the distributed planting optimization architecture configuration module M500 is also used to execute the following method:

[0113] Based on the crop growth sensor, the coupling relationship between crop growth state and water and fertilizer supply amount is extracted; according to the coupling relationship between crop growth state and water and fertilizer supply amount, the vertical to the main optimization direction is compensated in combination with the planting area node distribution in the planting topology graph to determine the dynamic water and fertilizer offset amount that meets the growth stability constraint.

[0114] Further, the distributed planting optimization architecture configuration module M500 is also used to execute the following method:

[0115] The density and water and fertilizer matching parameters include a basic water and fertilizer supply amount; the dynamic water and fertilizer offset amount is superimposed on the basic water and fertilizer supply amount to form a dynamically adjusted actual water and fertilizer supply amount, and the actual water and fertilizer supply amount is used for on-site adjustment of crop cultivation in the planting area corresponding to the node; at the same time, environmental stress tolerance evaluation is carried out, if the environmental stress tolerance jumps into the environmental stress tolerance risk controllable interval, three-dimensional stress vector data is obtained, the three-dimensional stress vector data includes drought stress component, saline-alkali stress component and pest and disease stress component; a water and fertilizer regulation unit is activated, and a growth cycle calibration mechanism is started to realign the planting optimization link, and the three-dimensional stress vector data is combined to update the planting area coverage overlap coefficient.

[0116] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the difference from other embodiments. The foregoing Figure 1 The knowledge graph-based agricultural planting scheme dynamic optimization method and specific examples in Embodiment One are also applicable to the knowledge graph-based agricultural planting scheme dynamic optimization system of the present embodiment. Based on the foregoing detailed description of the knowledge graph-based agricultural planting scheme dynamic optimization method, those skilled in the art can clearly understand the knowledge graph-based agricultural planting scheme dynamic optimization system in the present embodiment. Therefore, in the interest of brevity, the knowledge graph-based agricultural planting scheme dynamic optimization system will not be described in detail here.

[0117] The above description of the disclosed embodiments enables a person skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0118] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application also intends to include these modifications and variations.

Claims

1. A dynamic optimization method for agricultural planting schemes based on knowledge graphs, characterized in that, The method includes: Based on environmental perception data of agricultural planting areas, a planting topology map is proposed, which maps crop suitable growth range data with the distribution of planting area nodes. Based on the planting topology map, a preset planting plan associated with the dynamic planting optimization task is generated, and the density and water and fertilizer matching parameters are determined by combining the soil fertility level and resource consumption coefficient. By introducing crop growth status data and combining it with the preset planting plan, density and water and fertilizer matching parameters, the suitable growth range data of crops in the planting topology map is compensated to determine the first deviation compensation data. Through the dynamic planting optimization task, combined with the preset planting scheme, density and water and fertilizer matching parameters, the distribution of planting area nodes in the planting topology map is compensated to determine the second deviation compensation data. Multiple planting management nodes are connected for collaborative optimization. A distributed planting optimization architecture is configured by combining the first deviation compensation data and the second deviation compensation data, and the agricultural planting scheme is dynamically optimized using the distributed planting optimization architecture.

2. The method for dynamic optimization of agricultural planting schemes based on knowledge graphs as described in claim 1, characterized in that, Connecting multiple planting management nodes for collaborative optimization, and combining the first deviation compensation data and the second deviation compensation data to configure a distributed planting optimization architecture, the method includes: Based on the preset planting plan, combined with the first deviation compensation data and the second deviation compensation data, a dynamic planting adjustment path is set, and crop growth rate, resource utilization efficiency, and pest and disease incidence rate are recorded. Based on the dynamic planting optimization task, and combined with the crop growth rate, resource utilization efficiency, and pest and disease incidence rate, a distributed planting optimization architecture is established under the collaborative optimization of multiple planting management nodes.

3. The method for dynamic optimization of agricultural planting schemes based on knowledge graphs as described in claim 2, characterized in that, The crop growth status data includes crop height, leaf area index, and growth cycle stage. Define the central optimization node that executes the main optimization scheduling and the field adjustment node that executes the secondary optimization response; Based on the crop growth status data, the distributed planting optimization architecture is used to dynamically optimize the planting plan for the central optimization node and the field adjustment node among the multiple planting management nodes.

4. The method for dynamic optimization of agricultural planting schemes based on knowledge graphs as described in claim 3, characterized in that, The method further includes: Based on the central optimization node, planting status data packets are broadcast to the field adjustment nodes in real time, and the crop growth status data is stored in the planting status data packets. After receiving the planting status data packet, the on-site adjustment node determines the amount of lag compensation for growth deviation.

5. The method for dynamic optimization of agricultural planting schemes based on knowledge graphs as described in claim 4, characterized in that, Based on the crop growth status data, the distributed planting optimization architecture is used to dynamically optimize the planting plan for the central optimization node and the field adjustment node among the multiple planting management nodes. The method includes: Based on the crop growth status data, the crop suitability of the planting area corresponding to the central optimization node under different soil conditions and the first growth environment is analyzed to obtain resource allocation data. The first growth environment is used to characterize the combination of light and temperature conditions in the area covered by the central optimization node. Based on the crop growth status data and the lag compensation amount for growth deviation, the crop growth matching degree of the planting area corresponding to the field adjustment node under different soil conditions and second growth environment is analyzed to obtain growth regulation quality data. The second growth environment is used to characterize the microclimate difference between the field adjustment node and the central optimization node. Based on the central optimization node and resource allocation data, the on-site adjustment node and growth regulation quality data, a distributed planting optimization architecture under master-slave collaborative optimization control is set up.

6. The method for dynamic optimization of agricultural planting schemes based on knowledge graphs as described in claim 5, characterized in that, The method for setting up a distributed planting optimization architecture under master-slave collaborative optimization control includes: Using the central optimization node and resource allocation data, a first master-slave collaborative optimization network layer with a mapping relationship with the central optimization node is configured by adopting feedforward regulation and control under the resource allocation data. Using the central optimization node and resource allocation data, and employing the active adaptation control of crop growth sensors, a second master-slave collaborative optimization network layer with a mapping relationship to the field adjustment nodes is configured. The distributed planting optimization architecture is obtained by connecting the first master-slave collaborative optimization network layer and the second master-slave collaborative optimization network layer.

7. The method for dynamic optimization of agricultural planting schemes based on knowledge graphs as described in claim 3, characterized in that, The method further includes: Based on the dynamic planting adjustment path, determine the overlap coefficient of the planting area coverage; The resource consumption attenuation rate of the multiple planting management nodes is introduced, and the planting scheme is fine-tuned by combining the planting area coverage overlap coefficient.

8. The method for dynamic optimization of agricultural planting schemes based on knowledge graphs as described in claim 7, characterized in that, The method employs active adaptive control using crop growth sensors, and configures a second master-slave collaborative optimization network layer with a mapping relationship to field adjustment nodes. The method further includes: Based on the crop growth sensor, the coupling relationship between crop growth status and water and fertilizer supply is extracted; Based on the coupling relationship between crop growth status and water and fertilizer supply, and combined with the distribution of planting area nodes in the planting topology map, compensation perpendicular to the main optimization direction is performed to determine the dynamic water and fertilizer offset that meets the growth stability constraint.

9. The method for dynamic optimization of agricultural planting schemes based on knowledge graphs as described in claim 8, characterized in that, The method further includes: The density and water-fertilizer matching parameters include the basic water and fertilizer supply; The dynamic water and fertilizer offset is superimposed on the basic water and fertilizer supply to form the dynamically adjusted actual water and fertilizer supply. The actual water and fertilizer supply is used for crop cultivation in the planting area corresponding to the on-site adjustment node. Simultaneously, an environmental stress tolerance assessment is conducted. If the environmental stress tolerance falls into the controllable range of environmental stress tolerance risk, three-dimensional stress vector data is obtained. The three-dimensional stress vector data includes drought stress component, salinity stress component, and pest and disease stress component. The water and fertilizer regulation unit is activated, and the growth cycle calibration mechanism is initiated to realign the planting optimization link. The coverage overlap coefficient of the planting area is updated in conjunction with the three-dimensional stress vector data.

10. A dynamic optimization system for agricultural planting schemes based on knowledge graphs, characterized in that, The system is used to implement the knowledge graph-based dynamic optimization method for agricultural planting schemes according to any one of claims 1-9, wherein the system comprises: Planting Topology Map Constructing Module: Based on environmental perception data of agricultural planting areas, constructs a planting topology map that maps crop suitable growth range data with the distribution of nodes in the planting area. Density and water-fertilizer matching parameter determination module: Based on the planting topology map, it generates a preset planting plan associated with the dynamic planting optimization task, and determines the density and water-fertilizer matching parameters by combining the soil fertility level and resource consumption coefficient. First Deviation Compensation Data Determination Module: Introduces crop growth status data, combines it with the preset planting plan, density and water and fertilizer matching parameters, compensates for the crop suitable growth range data in the planting topology map, and determines the first deviation compensation data; Second Deviation Compensation Data Determination Module: Through the dynamic planting optimization task, combined with the preset planting scheme, density and water and fertilizer matching parameters, the distribution of planting area nodes in the planting topology map is compensated to determine the second deviation compensation data. Distributed planting optimization architecture configuration module: connects multiple planting management nodes for collaborative optimization, combines the first deviation compensation data and the second deviation compensation data to configure a distributed planting optimization architecture, and uses the distributed planting optimization architecture to dynamically optimize agricultural planting schemes.

Images