An AI large model driven agricultural irrigation control method, system, device and medium

Abstract

The application provides an AI large model driven agricultural irrigation control method, system, device and medium, and belongs to the technical field of agricultural irrigation control. The method comprises the following steps: constructing an irrigation knowledge base and an irrigation decision set for a target crop based on an AI large model; constructing a target crop parameter set and a water requirement prediction model, and training the water requirement prediction model by using the target crop parameter set in combination with the irrigation knowledge base; inputting real-time collected target crop parameters into the trained water requirement prediction model to predict the water requirement of the target crop; selecting an irrigation strategy from the irrigation knowledge base and the irrigation decision set according to the predicted water requirement of the target crop, and controlling the irrigation equipment based on the irrigation strategy. The application accurately predicts the water requirement of crops and generates an irrigation strategy in a combination mode of an AI large model and a deep learning model, improves the accuracy of irrigation decision, reduces water resource waste, and improves irrigation efficiency.

Description

Technical Field

[0001] This application belongs to the field of agricultural irrigation control technology, specifically relating to an AI-driven agricultural irrigation control method, system, equipment, and medium. Background Technology

[0002] With the development of agriculture, irrigation plays a vital role in improving crop yield and quality. Traditional irrigation methods, such as flood irrigation, not only waste a large amount of water resources but can also lead to soil compaction and root hypoxia. With the development of modern agriculture, intelligent irrigation control systems based on sensor data acquisition and preset irrigation rules are gradually being applied. Existing intelligent irrigation control systems monitor soil moisture in real time using soil moisture sensors, obtain meteorological data from weather stations, and control the on / off of irrigation equipment according to preset irrigation rules. However, this approach has many drawbacks.

[0003] First, in terms of irrigation demand forecasting, it mainly relies on preset rules and lacks the ability to dynamically respond to environmental factors and crop growth status. Environmental factors such as temperature, sunlight, wind speed, and precipitation are constantly changing, and climatic conditions vary significantly across different regions. Taking temperature as an example, during the high-temperature period in summer, crop transpiration intensifies, leading to a significant increase in water demand, while preset rules are insufficient to adjust irrigation demand in real time and accurately according to temperature fluctuations.

[0004] Secondly, crops exhibit significant differences in water requirements at different growth stages. From seedling to maturity, root development, plant size, and physiological metabolic activities continuously change. Fixed, pre-defined rules cannot adapt to these dynamic changes, leading to substantial discrepancies between predicted and actual irrigation needs. Furthermore, different crop types possess unique water requirements. Even different varieties of the same crop may have varying water requirements and irrigation preferences at the same growth stage. In addition, soil conditions, including texture, fertility, and water-holding capacity, differ between different fields and even within different areas of the same field. Existing, relatively fixed irrigation strategies struggle to comprehensively consider these diverse factors and cannot be flexibly adjusted according to actual conditions, resulting in ineffective irrigation that fails to fully meet crop growth needs, ultimately impacting crop yield and quality. Summary of the Invention

[0005] In a first aspect, embodiments of this application provide an AI-driven large-scale model-based agricultural irrigation control method, comprising the following steps:

[0006] S1. Based on a large AI model, construct an irrigation knowledge base and irrigation decision set for the target crop;

[0007] S2. Construct a set of target crop parameters and a water demand prediction model, and use the target crop parameter set combined with an irrigation knowledge base to train the water demand prediction model;

[0008] S3. Input the real-time collected target crop parameters into the trained water demand prediction model to predict the water demand of the target crop;

[0009] S4. Based on the predicted water requirement of the target crop, select irrigation strategies from the irrigation knowledge base and irrigation decision set, and control the irrigation equipment based on the irrigation strategies.

[0010] Furthermore, the specific steps of step S1 are as follows:

[0011] S11. Determine the target crop, target historical period, target region, target crop parameters, soil moisture, meteorological data, and irrigation operation data to construct a query command;

[0012] S12. Input the query command into the AI ​​big model to start the collection of target crop parameter-related data in the target area and the target historical period, as well as the collection of knowledge documents related to target crop parameters, soil moisture, meteorological data and irrigation operation data;

[0013] The S13.AI large model analyzes the relationship between the target crop's water requirement and target crop parameters, soil moisture, meteorological data, and irrigation operation data based on the collected data and knowledge documents, and generates an irrigation knowledge base and irrigation decision set, which are then returned.

[0014] Furthermore, the specific steps of step S2 are as follows:

[0015] S21. Determine the target irrigation range and target time period, and deploy sensors within the target irrigation range to collect target crop parameters, soil moisture, and meteorological data within the target time period, and construct a target crop parameter set;

[0016] S22. Construct a water demand prediction model driven by an irrigation knowledge base, and train it using a set of target crop parameters. Adjust the parameters of the water demand prediction model based on the error between the predicted water demand output by the water demand prediction model and the water demand analysis value in the irrigation knowledge base until the error meets the requirements.

[0017] Furthermore, the specific steps of step S22 are as follows:

[0018] S221. Construct a water demand prediction model based on convolutional neural network, bidirectional long short-term memory network and attention mechanism;

[0019] S222. Train the water demand prediction model using the target crop parameter set, calculate the error between the water demand prediction value output by the water demand prediction model and the water demand analysis value in the corresponding irrigation knowledge base, define the error as the loss function, and then adjust the parameters of the water demand prediction model according to the loss function until the training is completed.

[0020] Furthermore, the specific steps of step S3 are as follows:

[0021] S31. Use sensors to collect real-time target crop parameters, soil moisture, and meteorological data within the target irrigation area;

[0022] S32. Input the real-time target crop parameters, soil moisture, and meteorological data into the water demand prediction model to obtain the predicted water demand of the target crop within a set time period.

[0023] Furthermore, the specific steps of step S4 are as follows:

[0024] S41. Select the corresponding irrigation mode from the irrigation knowledge base based on the water demand forecast;

[0025] S42. Based on the predicted water demand and real-time soil moisture and meteorological data, query the water demand correction coefficient from the irrigation decision set, and then select the optimal irrigation strategy from the irrigation decision set based on the target crop parameters.

[0026] S43. Analyze the optimal irrigation strategy to obtain irrigation operation data, generate control commands based on the irrigation operation data, and send control commands to the irrigation equipment corresponding to the irrigation mode to execute irrigation.

[0027] Furthermore, step S43 is detailed as follows:

[0028] The specific steps of step S43 are as follows:

[0029] S431. Analyze the optimal irrigation strategy to obtain irrigation operation data and target soil moisture; the irrigation operation data includes irrigation time, irrigation amount and irrigation method;

[0030] S432. Based on the target soil moisture and real-time soil moisture data, use a PID controller to dynamically adjust the operating parameters of the irrigation equipment and calculate the control output value of the PID controller;

[0031] S433. Convert the calculated PID control output value into control commands for the irrigation equipment, so that the irrigation equipment performs irrigation according to the set irrigation amount and irrigation time;

[0032] S434. Send control commands to the irrigation equipment corresponding to the irrigation mode, execute irrigation operations, and monitor soil moisture and the operating status of the irrigation equipment in real time during the irrigation process;

[0033] S435. Feed back the execution results of irrigation operations to the AI ​​big model, evaluate the execution effect of the irrigation strategy, and update and optimize the irrigation knowledge base and irrigation strategy set based on the execution effect of the irrigation strategy.

[0034] Secondly, embodiments of this application also provide an AI-driven large-scale model-based agricultural irrigation control system, comprising:

[0035] The irrigation knowledge and strategy collection module is used to build an irrigation knowledge base and irrigation decision set for target crops based on AI big data models.

[0036] The water demand prediction model building module is used to build a set of target crop parameters and a water demand prediction model, and to train the water demand prediction model using the set of target crop parameters combined with an irrigation knowledge base.

[0037] The water demand prediction module is used to input the real-time collected target crop parameters into the trained water demand prediction model to predict the water demand of the target crop.

[0038] The irrigation control module is used to select irrigation strategies from the irrigation knowledge base and irrigation decision set based on the predicted water requirements of the target crop, and control the irrigation equipment based on the irrigation strategies.

[0039] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the highly reusable method of the AI ​​large model-driven agricultural irrigation control method as described in the first aspect.

[0040] Fourthly, embodiments of this application also provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the AI ​​large model-driven agricultural irrigation control method as described in the first aspect.

[0041] As can be seen from the above technical solutions, this application has the following advantages:

[0042] The AI-driven agricultural irrigation control method, system, equipment, and medium provided in this application utilize a large AI model to construct an irrigation knowledge base and decision set based on a large amount of data. Combined with a water demand prediction model, it can accurately predict crop water demand, implement irrigation strategies that meet crop growth needs, avoid over- or under-irrigation, and improve water resource utilization efficiency. It can also adjust irrigation volume according to real-time weather and soil moisture to meet the water needs of crops at different growth stages and ensure crop growth. Through feedback on irrigation execution results, it can continuously optimize the irrigation knowledge base and decision set, improve the accuracy and adaptability of irrigation control, and reduce the cost of manual intervention. Attached Figure Description

[0043] To more clearly illustrate the technical solution of this application, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 This is a flowchart illustrating the AI-driven agricultural irrigation control method of the present invention.

[0045] Figure 2 This is a schematic diagram of the process of the AI-driven agricultural irrigation control system of the present invention. Detailed Implementation

[0046] The various embodiments of this disclosure will be described more fully in the following detailed description of the specific steps of the AI ​​large model-driven agricultural irrigation control method. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0047] For example, with the development of agriculture, agricultural irrigation plays a crucial role in ensuring the improvement of crop yield and quality. Traditional irrigation methods, such as flood irrigation, not only waste a great deal of water resources but can also cause a series of problems such as soil hardening and obstructed root respiration. Modern agriculture has seen the application of intelligent irrigation control systems, which rely on sensor data collection and preset irrigation logic. However, despite the progress made in current intelligent irrigation control systems, they still face multiple challenges.

[0048] The primary problem lies in the irrigation demand forecasting mechanism. These systems rely heavily on pre-set rules and lack sensitivity to environmental variables and crop growth dynamics. Environmental factors such as temperature, light intensity, wind speed, and precipitation are constantly changing, and there are significant differences in climate conditions between regions. For example, during the hot summer months, crop transpiration rates increase, leading to a surge in water demand, while pre-set rules often struggle to adjust irrigation strategies accurately and in real time based on temperature fluctuations. Secondly, crops exhibit drastically different water requirements at different stages of their life cycle. From seedling to maturity, root development, plant size, and physiological metabolic activities undergo significant changes, making it difficult for fixed pre-set rules to adapt to these dynamic changes, resulting in a large discrepancy between predicted and actual irrigation demand. Furthermore, different crop species and varieties possess unique water requirements. Even different varieties of the same crop may exhibit different water requirements and irrigation preferences at the same growth stage. In addition, soil conditions also exhibit high diversity, including soil type, fertility level, and water-holding capacity, which can vary between different areas of the same farmland and even between adjacent farmlands. Current, relatively rigid irrigation strategies fail to fully consider these diverse factors and cannot be flexibly adjusted according to actual conditions, resulting in low irrigation efficiency, failure to meet the actual needs of crop growth, and consequently, adverse effects on crop yield and quality.

[0049] In summary, current intelligent irrigation control systems still have shortcomings in accurately predicting and flexibly adjusting irrigation demand, and further technological innovation and optimization are needed.

[0050] To address the aforementioned issues, this embodiment provides an AI-driven agricultural irrigation control method. By combining AI large-scale models with deep learning models, it accurately predicts crop water requirements and generates irrigation strategies, thereby improving the accuracy of irrigation decisions, reducing water waste, and increasing irrigation efficiency. It also enables automated management of the entire irrigation process, reduces the cost of manual intervention, and enhances the intelligence level of the irrigation system.

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] Please see Figure 1 The diagram shows a flowchart of an AI-driven large model-based agricultural irrigation control method in a specific embodiment. The method includes the following steps:

[0053] S1. Based on a large AI model, construct an irrigation knowledge base and irrigation decision set for the target crop;

[0054] It should be noted that by integrating multi-source information such as target crop parameters, soil moisture, meteorological data, and irrigation operation data through AI large-scale models, the relationships between data are identified, providing a knowledge base for irrigation decisions; knowledge bases and decision sets are generated for different target crops, regions, and historical periods, enabling irrigation decisions to adapt to diverse agricultural production scenarios;

[0055] S2. Construct a set of target crop parameters and a water demand prediction model, and use the target crop parameter set combined with an irrigation knowledge base to train the water demand prediction model;

[0056] It should be noted that by collecting data within the target irrigation range and time period to construct a parameter set, adaptive training data is provided for the water demand prediction model, thereby improving the model's accuracy. By combining the model with the irrigation knowledge base, the model can learn from historical experience and knowledge, optimize prediction results, and adapt to the growth needs of different crops.

[0057] S3. Input the real-time collected target crop parameters into the trained water demand prediction model to predict the water demand of the target crop;

[0058] It should be noted that water demand forecasting based on real-time data collection can promptly reflect the actual needs of crops and provide a basis for irrigation decisions; by adapting to the dynamic changes in crop growth, water demand forecasts can be adjusted in a timely manner to ensure that crops receive appropriate water supply at different growth stages.

[0059] S4. Based on the predicted water requirement of the target crop, select irrigation strategies from the irrigation knowledge base and irrigation decision set, and control the irrigation equipment based on the irrigation strategies;

[0060] It should be noted that, based on the predicted water demand, combined with factors in the knowledge base and decision set, the optimal irrigation strategy is selected to improve the rationality of irrigation; control instructions are generated based on the irrigation strategy to control the irrigation equipment, ensuring the accurate implementation of irrigation operations, thereby achieving both water-saving irrigation and ensuring crop growth.

[0061] This embodiment improves water resource utilization efficiency, ensures healthy crop growth, and achieves intelligent control of the agricultural irrigation process by more accurately predicting crop water requirements and dynamically adjusting irrigation strategies based on real-time environmental conditions and crop growth status.

[0062] Furthermore, as a refinement and extension of the specific implementation methods of the above embodiments, in order to fully illustrate the specific implementation process of this embodiment, another AI large model-driven agricultural irrigation control method is provided, which includes the following steps:

[0063] S1. Based on a large AI model, construct an irrigation knowledge base and irrigation decision set for the target crop;

[0064] The specific steps of step S1 are as follows:

[0065] S11. Determine the target crop, target historical period, target region, target crop parameters, soil moisture, meteorological data, and irrigation operation data to construct a query command;

[0066] Irrigation operation data includes irrigation time, irrigation volume, and irrigation method;

[0067] S12. Input the query command into the AI ​​big model to start the collection of target crop parameter-related data in the target area and the target historical period, as well as the collection of knowledge documents related to target crop parameters, soil moisture, meteorological data and irrigation operation data;

[0068] S13.AI large model analyzes the relationship between the target crop's water requirement and target crop parameters, soil moisture, meteorological data, and irrigation operation data based on the collected data and knowledge documents, generates an irrigation knowledge base and irrigation decision set, and returns them;

[0069] The irrigation knowledge base contains the correlation between target crop parameters, soil moisture, meteorological data, target crop water requirements, and irrigation strategies.

[0070] The set of irrigation strategies includes the calculation constraints on the target crop's water requirement and the selection method for the irrigation strategy;

[0071] S2. Construct a set of target crop parameters and a water demand prediction model, and use the target crop parameter set combined with an irrigation knowledge base to train the water demand prediction model;

[0072] The specific steps of step S2 are as follows:

[0073] S21. Determine the target irrigation range and target time period, and deploy sensors within the target irrigation range to collect target crop parameters, soil moisture, and meteorological data within the target time period, and construct a target crop parameter set;

[0074] S22. Construct a water demand prediction model driven by an irrigation knowledge base, and train it using a set of target crop parameters. Adjust the parameters of the water demand prediction model based on the error between the predicted water demand output by the water demand prediction model and the water demand analysis value in the irrigation knowledge base until the error meets the requirements.

[0075] S3. Input the real-time collected target crop parameters, soil moisture, and meteorological data into the trained water demand prediction model to predict the water demand of the target crop.

[0076] The specific steps of step S3 are as follows:

[0077] S31. Use sensors to collect real-time target crop parameters, soil moisture, and meteorological data within the target irrigation area;

[0078] S32. Input the real-time target crop parameters, soil moisture and meteorological data into the water demand prediction model to obtain the predicted water demand of the target crop in a set time period;

[0079] S4. Based on the predicted water requirement of the target crop, select irrigation strategies from the irrigation knowledge base and irrigation decision set, and control the irrigation equipment based on the irrigation strategies;

[0080] The specific steps of step S4 are as follows:

[0081] S41. Select the corresponding irrigation mode from the irrigation knowledge base based on the water demand forecast;

[0082] S42. Based on the predicted water demand and real-time soil moisture and meteorological data, query the water demand correction coefficient from the irrigation decision set, and then select the optimal irrigation strategy from the irrigation decision set based on the target crop parameters.

[0083] S43. Analyze the optimal irrigation strategy to obtain irrigation operation data, generate control commands based on the irrigation operation data, and send control commands to the irrigation equipment corresponding to the irrigation mode to execute irrigation.

[0084] In one embodiment of the present invention, based on step S22, the following will provide a possible embodiment and describe its specific implementation in a non-limiting manner.

[0085] The specific steps of step S22 are as follows:

[0086] S221. Construct a water demand prediction model based on convolutional neural network, bidirectional long short-term memory network and attention mechanism;

[0087] Specifically, the water demand prediction model consists of a convolutional neural network (CNN) layer, a bidirectional long short-term memory (BiLSTM) layer, an attention mechanism layer, and an output layer connected in sequence.

[0088] Convolutional neural network (CNN) layers extract local features from the input set of target crop parameters and construct a feature map of the target crop parameters.

[0089] Taking the three-dimensional target crop parameter set X as an example, Where R represents the target crop parameter set, N is the number of samples, T is the time step, and F is the feature dimension, the feature map C is obtained through the following convolution operation, and ;

[0090]

[0091] Where M is the height of the convolution kernel, and N is the width of the convolution kernel. It is a convolution kernel, and b is a bias term, and k represents the input feature dimension index, and l represents the output feature dimension index;

[0092] The Bidirectional Long Short-Term Memory (BiLSTM) layer receives the feature map C output by the CNN layer and performs time series modeling to obtain time series data. It then uses a forward LSTM (as a hidden layer) to capture the preceding context information of the current data within the sequence data, and a backward LSTM (also as a hidden layer) to capture the following context information. Finally, it concatenates the preceding, current, and following context information to obtain the output of the BiLSTM layer. ;

[0093]

[0094] in, , It is the dimension of the hidden layer;

[0095] The attention mechanism layer performs weighted aggregation of the output features of the convolutional neural network (CNN) layer and the bidirectional long short-term memory (BiLSTM) network layer;

[0096]

[0097]

[0098] in, It is attention weight. , It is an unnormalized attention score. , , It is a weight matrix. C is the bias term, and C is the output of the convolutional neural network (CNN) layer. It is the output of the BiLSTM layer in a bidirectional long short-term memory network. It is the length of the time series;

[0099] The final output of the Attention layer is as follows:

[0100]

[0101] in ;

[0102] The output layer is the water demand prediction value obtained by passing the output of the attention layer through a fully connected layer. ;

[0103]

[0104] in, These are the weights of the output layer. It is the bias of the output layer. , ;

[0105] S222. Train the water demand prediction model using the target crop parameter set, calculate the error between the water demand prediction value output by the water demand prediction model and the water demand analysis value in the corresponding irrigation knowledge base, define the error as the loss function, and then adjust the parameters of the water demand prediction model according to the loss function until the training is completed.

[0106] Specifically, it determines whether the loss function value is less than a set error threshold or whether a set number of iterations has been reached;

[0107] If not, calculate the gradient of the loss function with respect to the water demand prediction model, adjust the learning rate of the training process according to the gradient, and continue iterative training with the updated learning rate.

[0108] If so, complete the training;

[0109] Specifically, the loss function is defined as follows:

[0110]

[0111] in, Mean squared error (MSE) is the error of mean squared error (MSE). These are the weighting coefficients for different growth stages of the target crop. , , These are the weight parameters of the loss function.

[0112] In one embodiment of the present invention, based on step S43, a possible embodiment will be given below, and its specific implementation will be described in a non-limiting manner.

[0113] The specific steps of step S43 are as follows:

[0114] S431. Analyze the optimal irrigation strategy to obtain irrigation operation data and target soil moisture; the irrigation operation data includes irrigation time, irrigation amount and irrigation method;

[0115] S432. Based on the target soil moisture and real-time soil moisture data, use a PID controller to dynamically adjust the operating parameters of the irrigation equipment and calculate the control output value of the PID controller;

[0116] Specifically, a PID algorithm is used based on real-time soil moisture. and target soil moisture Dynamically adjust the operating status of irrigation equipment, such as valve opening, and the output of the PID controller. as follows:

[0117]

[0118]

[0119] in, It is a proportionality coefficient. It is the integral coefficient. These are differential coefficients;

[0120] S433. Convert the calculated PID control output value into control commands for the irrigation equipment, so that the irrigation equipment performs irrigation according to the set irrigation amount and irrigation time;

[0121] For example, if the irrigation equipment controls the flow rate via valves, then the output of the PID controller will be... Mapping this to the valve's opening range [0,1] yields the valve opening. :

[0122]

[0123] in, It is the minimum value output by the PID controller. It is the maximum value output by the PID controller;

[0124] S434. Send control commands to the irrigation equipment corresponding to the irrigation mode, execute irrigation operations, and monitor soil moisture and the operating status of the irrigation equipment in real time during the irrigation process;

[0125] S435. Feed back the execution results of irrigation operations to the AI ​​big model, evaluate the execution effect of the irrigation strategy, and update and optimize the irrigation knowledge base and irrigation strategy set based on the execution effect of the irrigation strategy.

[0126] Taking the intelligent irrigation control of a corn-growing field in a certain region as an example:

[0127] First, define the query instruction, using corn as the target crop, the past 10 years as the target historical period, the specific farmland in the region as the target area, and plant physiological indicators within the same time period as the target crop parameters, such as stem flow, plant height, leaf area, stem diameter, and biomass. Collect soil moisture at different depths, such as 10cm, 20cm, and 30cm, and collect meteorological data within the same time period, such as temperature, humidity, light intensity, wind speed, and precipitation. Determine the irrigation time, irrigation volume, and irrigation method as irrigation operation data. The irrigation time needs to be specified to a specific point in time, and the irrigation method includes drip irrigation and sprinkler irrigation. Specifically, the query can be constructed as follows: "Query the stem flow, plant height, leaf area, stem diameter, biomass, soil moisture at different depths, meteorological data (temperature, humidity, light intensity, wind speed, precipitation), irrigation time, irrigation volume, irrigation method, and other related data and knowledge documents of corn in XXX region over the past 10 years."

[0128] Input the query command into the AI ​​big model, and the big model will start to collect relevant data on the target crop parameters of corn in the target area and the target historical period from multiple channels such as weather station databases, agricultural research institution data, and farm historical records. At the same time, it will collect relevant knowledge documents, such as research reports on corn irrigation by agricultural experts.

[0129] The AI ​​model analyzed collected data and knowledge documents, discovering that during the jointing stage of corn, water demand increases significantly when temperatures exceed 30℃ and wind speeds exceed 3m / s; drip irrigation is more effective in utilizing water resources when soil moisture is low. The generated irrigation knowledge base includes water requirements and corresponding irrigation strategies for corn at different growth stages, under different meteorological conditions, and with varying soil moisture. For example, during hot and dry seasons, a certain corn variety experiences a significant increase in water demand during the jointing stage when soil moisture falls below a certain threshold, making drip irrigation suitable. The irrigation decision set includes constraints on water demand calculation, such as correction coefficients considering meteorological factors and methods for selecting irrigation strategies, such as choosing irrigation methods based on soil moisture and crop growth stage; determining correction coefficients for water demand calculation based on different combinations of soil types and meteorological conditions; and prioritizing irrigation strategies based on crop growth stage and meteorological disaster risks.

[0130] Soil sensors, weather stations, and stem flow sensors were deployed in this corn-grown farmland to collect data on stem flow, plant height, leaf area, soil moisture at different depths, temperature, humidity, light intensity, wind speed, and precipitation over the past week, and to construct a set of target crop parameters.

[0131] After constructing the water demand prediction model, it is trained using only the target crop parameter set. The error between the predicted water demand output by the model and the water demand analysis value in the irrigation knowledge base is calculated, and the error is defined as the loss function. For example, the error threshold is set to 0.01, and the maximum number of iterations is 100. During training, if the loss function value is greater than 0.01 but less than 100 iterations have been reached, the gradient of the loss function with respect to the model is calculated, the learning rate is adjusted according to the gradient, and training continues iteratively. If the loss function value is less than 0.01 or 100 iterations have been reached, training is complete.

[0132] Sensors are used to collect real-time data on corn stem flow, plant height, leaf area, soil moisture at different depths, temperature, humidity, light intensity, wind speed, and precipitation in farmland. The real-time collected data is then input into a trained water demand prediction model to obtain a predicted water demand for corn in the coming week, assuming a predicted value of 500 cubic meters.

[0133] Based on the predicted water demand of 500 cubic meters, the corresponding irrigation mode is selected from the irrigation knowledge base, such as the drip irrigation mode.

[0134] Based on the predicted water demand of 500 cubic meters, combined with real-time soil moisture and meteorological data, the water demand correction coefficient is retrieved from the irrigation decision set. Assuming the correction coefficient is 1.1, the corrected water demand is 550 cubic meters. Then, based on the target crop parameters such as corn plant height and leaf area, the optimal irrigation strategy is selected from the irrigation decision set, and the irrigation time is determined to be from 10 pm to 2 am every day, to be completed in 5 days, with an irrigation volume of 110 cubic meters per day.

[0135] The optimal irrigation strategy was analyzed to obtain irrigation operation data, as follows:

[0136] Irrigation time: 10 p.m. to 2 a.m. every day;

[0137] Irrigation volume: 110 cubic meters per day;

[0138] Irrigation method: Drip irrigation;

[0139] Target soil moisture: 60%;

[0140] Based on the target soil moisture of 60% and real-time soil moisture data, the operating parameters of the irrigation equipment, such as the flow rate and pressure of the water pump, are dynamically adjusted using a PID controller. For example, if the real-time soil moisture is 50%, the control output value of the PID controller is calculated.

[0141] The calculated PID control output value is converted into control commands for the irrigation equipment, such as the pump start time and valve opening degree, so that the irrigation equipment can perform irrigation according to the set irrigation amount and irrigation time; control commands are sent to the drip irrigation equipment to execute the irrigation operation, and the soil moisture and the operating status of the irrigation equipment are monitored in real time during the irrigation process to ensure that the soil moisture gradually approaches the target soil moisture and the irrigation equipment operates normally.

[0142] The results of irrigation operations, such as actual irrigation volume, changes in soil moisture, and crop growth, are fed back to the AI ​​model to evaluate the effectiveness of the irrigation strategy. If a significant deviation is found between the actual water demand and the predicted value, or if the irrigation effect is poor, the irrigation knowledge base and irrigation strategy set are updated and optimized based on the results to make the next irrigation decision more accurate.

[0143] It should be understood that the sequence number of each step in the above embodiments does not imply 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.

[0144] like Figure 2 As shown, the following are embodiments of the AI-driven agricultural irrigation control system provided in this disclosure. This system and the AI-driven agricultural irrigation control methods in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the AI-driven agricultural irrigation control system, please refer to the embodiments of the AI-driven agricultural irrigation control methods described above.

[0145] The system includes:

[0146] The irrigation knowledge and strategy collection module is used to build an irrigation knowledge base and irrigation decision set for target crops based on AI big data models.

[0147] The water demand prediction model building module is used to build a set of target crop parameters and a water demand prediction model, and to train the water demand prediction model using the set of target crop parameters combined with an irrigation knowledge base.

[0148] The water demand prediction module is used to input the real-time collected target crop parameters into the trained water demand prediction model to predict the water demand of the target crop.

[0149] The irrigation control module is used to select irrigation strategies from the irrigation knowledge base and irrigation decision set based on the predicted water requirements of the target crop, and control the irrigation equipment based on the irrigation strategies.

[0150] This embodiment achieves intelligent irrigation control by integrating an irrigation knowledge and strategy collection module, a water demand prediction model construction module, a water demand prediction module, and an irrigation control module.

[0151] The AI-driven large-model-driven agricultural irrigation control method provided in this application can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the electronic device includes, but is not limited to, laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0152] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0153] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device. In other embodiments of this application, the electronic device may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0154] A processor may include one or more processing units, such as a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0155] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0156] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0157] The aforementioned electronic equipment implements the AI-driven agricultural irrigation control method of this application, which involves: constructing an irrigation knowledge base and irrigation decision set for the target crop based on an AI large model; constructing a target crop parameter set and a water demand prediction model, and training the water demand prediction model using the target crop parameter set in conjunction with the irrigation knowledge base; inputting the real-time collected target crop parameters into the trained water demand prediction model to predict the target crop's water demand; and selecting irrigation strategies from the irrigation knowledge base and irrigation decision set based on the predicted water demand of the target crop, and controlling the irrigation equipment based on the irrigation strategies. This achieves the beneficial effects of more accurately predicting crop water demand and dynamically adjusting irrigation strategies according to real-time environmental conditions and crop growth status, thereby improving water resource utilization efficiency.

[0158] The storage medium provided in this application stores a program product capable of implementing an AI-driven agricultural irrigation control method.

[0159] The AI-driven agricultural irrigation control method includes: constructing an irrigation knowledge base and irrigation decision set for the target crop based on the AI ​​model; constructing a target crop parameter set and water demand prediction model, and training the water demand prediction model using the target crop parameter set in conjunction with the irrigation knowledge base; inputting the real-time collected target crop parameters into the trained water demand prediction model to predict the target crop's water demand; selecting irrigation strategies from the irrigation knowledge base and irrigation decision set based on the predicted water demand of the target crop, and controlling the irrigation equipment based on the irrigation strategies.

[0160] In some possible implementations, the AI ​​large model-driven agricultural irrigation control method of this disclosure can be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0161] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0162] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An AI-driven large-scale model-based method for agricultural irrigation control, characterized in that, Includes the following steps: S1. Construct an irrigation knowledge base and irrigation decision set for the target crop based on a large AI model; the specific steps of step S1 are as follows: S11. Determine the target crop, target historical period, target region, target crop parameters, soil moisture, meteorological data, and irrigation operation data to construct a query command; S12. Input the query command into the AI ​​big model to start the collection of target crop parameter-related data in the target area and the target historical period, as well as the collection of knowledge documents related to target crop parameters, soil moisture, meteorological data and irrigation operation data; S13.AI large model analyzes the relationship between the target crop's water requirement and target crop parameters, soil moisture, meteorological data, and irrigation operation data based on the collected data and knowledge documents, generates an irrigation knowledge base and irrigation decision set, and returns them; The irrigation knowledge base contains the correlation between target crop parameters, soil moisture, meteorological data, target crop water requirements, and irrigation strategies. The irrigation decision set includes the calculation constraints of the target crop's water requirement and the selection method of irrigation strategy; S2. Construct a target crop parameter set and a water demand prediction model, and train the water demand prediction model using the target crop parameter set combined with an irrigation knowledge base; the specific steps of step S2 are as follows: S21. Determine the target irrigation range and target time period, and deploy sensors within the target irrigation range to collect target crop parameters, soil moisture, and meteorological data within the target time period, and construct a target crop parameter set; S22. Construct a water demand prediction model driven by an irrigation knowledge base, and train it using a set of target crop parameters. Adjust the parameters of the water demand prediction model based on the error between the predicted water demand value output by the model and the water demand analysis value in the irrigation knowledge base until the error meets the requirements. The specific steps of step S22 are as follows: S221. Construct a water demand prediction model based on convolutional neural network, bidirectional long short-term memory network and attention mechanism; S222. Train the water demand prediction model using the target crop parameter set, calculate the error between the water demand prediction value output by the water demand prediction model and the water demand analysis value in the corresponding irrigation knowledge base, define the error as the loss function, and then adjust the parameters of the water demand prediction model according to the loss function until the training is completed. S3. Input the real-time collected target crop parameters into the trained water demand prediction model to predict the water demand of the target crop; S4. Based on the predicted water requirement of the target crop, select irrigation strategies from the irrigation knowledge base and irrigation decision set, and control the irrigation equipment based on the irrigation strategies.

2. The AI-driven large-scale model-based agricultural irrigation control method according to claim 1, characterized in that, The specific steps of step S3 are as follows: S31. Use sensors to collect real-time target crop parameters, soil moisture, and meteorological data within the target irrigation area; S32. Input the real-time target crop parameters, soil moisture, and meteorological data into the water demand prediction model to obtain the predicted water demand of the target crop within a set time period.

3. The AI-driven large-scale model-based agricultural irrigation control method according to claim 2, characterized in that, The specific steps of step S4 are as follows: S41. Select the corresponding irrigation mode from the irrigation knowledge base based on the water demand forecast; S42. Based on the predicted water demand and real-time soil moisture and meteorological data, query the water demand correction coefficient from the irrigation decision set, and then select the optimal irrigation strategy from the irrigation decision set based on the target crop parameters. S43. Analyze the optimal irrigation strategy to obtain irrigation operation data, generate control commands based on the irrigation operation data, and send control commands to the irrigation equipment corresponding to the irrigation mode to execute irrigation.

4. The AI-driven large-scale model-based agricultural irrigation control method according to claim 3, characterized in that, The specific steps of step S43 are as follows: S431. Analyze the optimal irrigation strategy to obtain irrigation operation data and target soil moisture; the irrigation operation data includes irrigation time, irrigation amount and irrigation method; S432. Based on the target soil moisture and real-time soil moisture data, use a PID controller to dynamically adjust the operating parameters of the irrigation equipment and calculate the control output value of the PID controller; S433. Convert the calculated PID control output value into control commands for the irrigation equipment, so that the irrigation equipment performs irrigation according to the set irrigation amount and irrigation time; S434. Send control commands to the irrigation equipment corresponding to the irrigation mode, execute irrigation operations, and monitor soil moisture and the operating status of the irrigation equipment in real time during the irrigation process; S435. Feed back the execution results of irrigation operations to the AI ​​big model, evaluate the execution effect of the irrigation strategy, and update and optimize the irrigation knowledge base and irrigation decision set based on the execution effect of the irrigation strategy.

5. An AI-driven large-scale model-based agricultural irrigation control system, employing the AI-driven large-scale model-based agricultural irrigation control method according to any one of claims 1-4, characterized in that, include: The irrigation knowledge and strategy collection module is used to build an irrigation knowledge base and irrigation decision set for target crops based on AI big data models. The water demand prediction model building module is used to build a set of target crop parameters and a water demand prediction model, and to train the water demand prediction model using the set of target crop parameters combined with an irrigation knowledge base. The water demand prediction module is used to input the real-time collected target crop parameters into the trained water demand prediction model to predict the water demand of the target crop. The irrigation control module is used to select irrigation strategies from the irrigation knowledge base and irrigation decision set based on the predicted water requirements of the target crop, and control the irrigation equipment based on the irrigation strategies.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the AI ​​large model-driven agricultural irrigation control method as described in any one of claims 1 to 4.

7. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the AI ​​large model-driven agricultural irrigation control method as described in any one of claims 1 to 4.

Images