Irrigation method, device, equipment and product based on crop model

Abstract

The invention relates to an irrigation method, device, equipment and product based on a crop model. The method comprises the following steps: acquiring user irrigation behavior data, crop information associated with crops, and environment information associated with a crop growth environment; the method further includes generating a predicted irrigation strategy using the crop model based on the crop information and the environmental information. In addition, the method includes generating a recommended irrigation policy based on the user irrigation behavior data and the predicted irrigation policy. By considering the user irrigation behavior data, the user preference can be used as an important input and feedback index for generating the recommended irrigation strategy, so that the effectiveness of the irrigation strategy can be improved under the specific user preference, and the growth conditions of crops are optimized.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence, and more particularly to irrigation methods, devices, equipment and products based on crop models. Background Art

[0002] With the development of digital agriculture, existing greenhouse irrigation intelligent equipment can be combined with the Internet of Things, sensor technology, and automated control systems to achieve precise irrigation management by real-time monitoring of soil moisture, ambient temperature, air humidity, and light intensity. Intelligent irrigation control systems can automatically control irrigation time, frequency, and water or fertilizer volume through expert pre-adjustment, and also support zoning irrigation, drip irrigation, sprinkler irrigation, etc., greatly improving water resource utilization efficiency.

[0003] The advantages of these intelligent devices are high efficiency, precision and environmental protection. They not only save labor costs, but also reduce resource waste and environmental pollution. Intelligent greenhouse irrigation equipment has been used in agricultural science and technology parks or greenhouses of large enterprises, providing technical support for the sustainable development of modern agriculture. Summary of the invention

[0004] In a first aspect of an embodiment of the present disclosure, a crop model-based irrigation method is provided. The method includes obtaining user irrigation behavior data, crop information associated with the crop, and environmental information associated with the crop growth environment. The method also includes generating a predicted irrigation strategy using the crop model based on the crop information and the environmental information. In addition, the method also includes generating a recommended irrigation strategy based on the user irrigation behavior data and the predicted irrigation strategy.

[0005] In a second aspect of an embodiment of the present disclosure, an irrigation device based on a crop model is provided. The device includes a crop data acquisition module configured to acquire user irrigation behavior data, crop information associated with the crop, and environmental information associated with the crop growth environment. The device also includes a prediction strategy generation module configured to generate a prediction irrigation strategy using the crop model based on the crop information and the environmental information. In addition, the device also includes a recommendation strategy generation module configured to generate a recommended irrigation strategy based on the user irrigation behavior data and the prediction irrigation strategy.

[0006] In a third aspect of an embodiment of the present disclosure, an electronic device is provided. The electronic device includes one or more processors; and a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement an irrigation method based on a crop model. The method includes obtaining user irrigation behavior data, crop information associated with the crop, and environmental information associated with the crop growth environment. The method also includes generating a predicted irrigation strategy using a crop model based on the crop information and the environmental information. In addition, the method also includes generating a recommended irrigation strategy based on the user irrigation behavior data and the predicted irrigation strategy.

[0007] In a fourth aspect of an embodiment of the present disclosure, a computer program product is provided. The computer program product is tangibly stored on a non-transitory computer-readable medium and includes machine executable instructions that, when executed, cause a machine to implement an irrigation method based on a crop model. The method includes obtaining user irrigation behavior data, crop information associated with the crop, and environmental information associated with the crop growth environment. The method also includes generating a predicted irrigation strategy using a crop model based on the crop information and the environmental information. In addition, the method also includes generating a recommended irrigation strategy based on the user irrigation behavior data and the predicted irrigation strategy.

[0008] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0010] Figure 1 A schematic diagram illustrating an example environment in which various embodiments of the present disclosure may be implemented;

[0011] Figure 2 A flow chart showing an irrigation method based on a crop model according to some embodiments of the present disclosure;

[0012] Figure 3 A schematic diagram illustrating the architecture of an example system for irrigation according to some embodiments of the present disclosure;

[0013] Figure 4 A schematic diagram showing an example of generating a recommended irrigation strategy score and a user irrigation strategy score according to some embodiments of the present disclosure;

[0014] Figure 5 A schematic diagram showing an example of generating a predictive irrigation strategy according to some embodiments of the present disclosure;

[0015] Figure 6 A schematic diagram showing an example of a soil moisture content variation curve according to some embodiments of the present disclosure;

[0016] Figure 7 A block diagram of an irrigation device based on a crop model according to some embodiments of the present disclosure is shown;

[0017] Figure 8 A block diagram of a device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0018] It is understood that all user-related data involved in this technical solution should be obtained and used after the user's authorization. This means that in this technical solution, if it is necessary to use data associated with user behavior or user information, the user's explicit consent and authorization are required before obtaining this data, otherwise the relevant data will not be collected and used. It should also be understood that when implementing this technical solution, relevant laws and regulations should be strictly observed during the collection, use and storage of data, and necessary technologies and measures should be taken to protect the user's data security and ensure the safe use of data.

[0019] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0020] In the description of the embodiments of the present disclosure, the term "including" and similar terms should be understood as open inclusion, that is, "including but not limited to". The term "based on" should be understood as "based at least in part on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects, unless explicitly stated. Other explicit and implicit definitions may also be included below.

[0021] With the advancement of agricultural modernization, intelligent equipment has gradually been applied to various agricultural scenarios, especially in greenhouse cultivation with a high degree of standardization. Precision water and fertilizer irrigation is essential for the healthy growth of crops. In some existing technologies, high-end greenhouse irrigation equipment is provided to professional farmers. These devices require complex parameters to be set and require refined irrigation knowledge as support. Therefore, farmers need to have a deep understanding of the working principle and crop characteristics of the equipment to fully utilize its functions. However, in many solar greenhouses and single plastic greenhouses, farmers still rely mainly on personal experience and irrigate through simple mechanical switches, which is difficult to achieve scientific management. Therefore, it is urgent to develop a digital intelligent irrigation system for ordinary farmers to bridge the gap between traditional empirical irrigation and professional high-end irrigation, so that modern agricultural technology can benefit a wider user group.

[0022] In some related intelligent irrigation solutions, enterprise-level and laboratory-level professional irrigation solutions require professional knowledge and skills. Users must have a deep understanding of knowledge such as plant water requirements, nutrient ratios, and irrigation frequency, and have the ability to set up programs. Although these solutions are suitable for large-scale planting companies, they are not friendly to ordinary farmers with weak technical capabilities and small-scale greenhouses. On the other hand, farmers mainly rely on personal experience when performing traditional irrigation and cannot accurately control the use of water and fertilizers. In order to avoid crop fertilizer deficiency, they often over-irrigate, resulting in a waste of water and fertilizers, and may also cause problems such as soil compaction and salinization. This method not only harms the environment, but also reduces production efficiency.

[0023] To this end, an embodiment of the present disclosure provides a scheme for irrigation. In this scheme, a controller can obtain user irrigation behavior data, crop information associated with crops, and environmental information associated with the crop growth environment. Then, the controller can generate a predicted irrigation strategy using a crop model based on the crop information and environmental information. In addition, the controller can also generate a recommended irrigation strategy based on the user irrigation behavior data and the predicted irrigation strategy. The generated recommended irrigation strategy can be displayed to the farmer via a display device to help the farmer determine the irrigation strategy to be implemented.

[0024] In this way, the learned crop model can generate a predictive irrigation strategy suitable for crop growth in the current greenhouse based on crop information and environmental information, without the need for professionals to adjust the system and set parameters for the current greenhouse, thus improving the versatility of smart irrigation. In addition, by considering user irrigation behavior data, user preferences can be used as an important input and feedback indicator for generating recommended irrigation strategies, thereby improving the effectiveness of irrigation strategies under specific user preferences and optimizing crop growth conditions.

[0025] It should be noted that, for ease of understanding, some embodiments are described herein using a greenhouse environment as an example, but this is not intended to limit the irrigation environment to which the embodiments of the present disclosure are applied. The solutions provided by the embodiments of the present disclosure may also be applicable to other irrigation scenarios.

[0026] Figure 1 1 is a schematic diagram of an example environment 100 in which various embodiments of the present disclosure may be implemented. Figure 1 As shown, environment 100 includes greenhouse 102, in which crops 104 may be planted. In addition, greenhouse 102 may also include sensor 106, controller 108, and actuator 110. Sensor 106 can be used to monitor the environment inside greenhouse 102 and the growth status of crops. For example, sensor 106 may include soil moisture sensor, soil temperature sensor, air temperature and humidity sensor, light sensor, visual sensor (e.g., camera), etc. For example, soil moisture sensor can be used to measure the moisture content in soil, soil temperature sensor can be used to monitor the temperature of soil, air temperature and humidity sensor can be used to monitor the temperature and humidity level of air in greenhouse, light sensor can be used to measure light intensity and sunshine duration, and visual sensor can be used to capture images of crops. In some embodiments, sensor 106 can also be used to monitor the flow rate and flow rate of water and fertilizer during irrigation.

[0027] The controller 108 may be a device with any computing or processing capabilities. For example, the controller 108 may be an embedded device, an IoT device, a personal computer, a laptop computer, a tablet computer, a mobile phone, or a smart wearable device. The controller 108 may receive data from the sensor 106 and perform logical judgment and control operations according to system-set parameters.

[0028] The actuator 110 may automatically perform various irrigation operations based on instructions from the controller 108. For example, the actuator 110 may include a water valve that controls the flow rate and flow rate of water and a fertilizer valve that controls the flow rate and flow rate of fertilizer. In some examples, the actuator 110 may also include a water pump or a fertilizer pump that provides pressure for irrigation, a fertilizer mixer that automatically mixes fertilizer and water, or a nozzle controller that adjusts the spraying pattern of a sprinkler or atomizer.

[0029] In some embodiments, the greenhouse 102 may further include a display device, which may be a device for displaying a user interface to a user. In some embodiments, the display device may have an interactive function, for example, the controller 108 may display a user interface through the display device, and then the user may interact with the user interface through the display device, so that the controller 108 may obtain user input (for example, user input for adjusting an irrigation strategy) through the display device.

[0030] In the environment 100, a data storage and transmission module may also be included, which is mainly responsible for the storage and transmission of multimodal data (e.g., soil moisture, ambient temperature, air humidity, light intensity, etc.) to ensure the coordinated operation of each subsystem. After the sensor 106 collects the environmental and crop status data in real time, the collected data can be uploaded to the controller 108 or the cloud platform through wired or wireless communication (e.g., Wi-Fi, LoRa, 5G). Local storage can support real-time computing and local decision-making, and cloud storage can be used for long-term data analysis and optimization management.

[0031] In terms of data processing, the collected data can be pre-processed (e.g., cleaned and format converted) and analyzed in real time through intelligent algorithms to generate optimized irrigation strategies. These decision parameters can then be sent by the controller 108 to the actuator 110 through the network to achieve precise water and fertilizer irrigation. At the same time, the actuator 110 can collect execution feedback data (e.g., water volume, fertilizer concentration, etc.) through built-in sensors and upload it to the controller 108 for closed-loop optimization and dynamic adjustment to ensure the accuracy and efficiency of irrigation operations.

[0032] In addition, in the environment 100, the greenhouse 102 can also support remote monitoring functions. For example, data can be transmitted to a user terminal, such as a mobile phone, a tablet computer, or a personal computer, through an Internet of Things platform, so that the user can view the status of the greenhouse 102 in real time. The system also visualizes the data through charts and dashboards so that the user can clearly understand the operating status of the greenhouse 102 and perform remote control or strategy adjustment as needed. Through an efficient data storage and transmission mechanism, the greenhouse 102 can not only achieve accurate irrigation decisions, but also support long-term environmental optimization, providing technical support for improving crop yields and resource utilization efficiency.

[0033] like Figure 1As shown, in the environment 100, the controller 108 can obtain the user irrigation behavior data 112, the crop information 114 associated with the crop 104, and the environmental information 116 associated with the growth environment of the crop 104. Since the irrigation habits of farmers may be to open and close the water valve multiple times a day (for example, first irrigate a part of the water and fertilizer to observe whether the amount required by the crop is met, and decide whether to continue to irrigate or fertilize based on the observation results), the system can record and integrate the user's behavior data. The user's irrigation behavior data 112 may include, for example, the time to open or close the valve, or the time of irrigating before fertilization, etc. In some embodiments, the user's irrigation behavior data 112 may include irrigation behavior (for example, opening the water valve to irrigate), parameters associated with the irrigation behavior (for example, the degree of opening of the water valve, the duration of opening the water valve), and the time corresponding to the irrigation behavior (for example, the time to open the water valve), wherein the irrigation behavior may include irrigation and fertilization.

[0034] Crop information 114 may include, for example, crop varieties, planting cycles, and phenological periods. Crop varieties are key factors in agricultural production, determining the growth characteristics, yield and quality of crops. According to their uses, crops can be classified into food crops (e.g., wheat, rice, etc.), cash crops (e.g., cotton, soybeans, etc.), fruit crops (e.g., apples, grapes, etc.), and vegetable crops (e.g., tomatoes, cucumbers, etc.). Crops of different varieties have different environmental adaptability. The planting cycle is the time process from seedling transplantation to the field or greenhouse and growth and maturity of crops. For example, the planting cycle may include the seedling period, planting period, growth and development period, and harvest period. For example, the planting cycle of tomatoes may be several months, while the planting cycle of leafy crops may be 30 to 50 days. Reasonable arrangement of the planting cycle can optimize resource utilization, avoid competitive pressure caused by planting peaks, and improve planting efficiency. The phenological period is a specific physiological state exhibited by crops during their growth and development, including germination period, growth period, flowering period, fruit maturity period, and dormancy period. Accurate judgment of phenological periods is crucial to agricultural management. The flowering period directly affects the yield, the fruit ripening period determines the time of harvest, and the dormancy period provides time for crops to accumulate energy.

[0035] In some embodiments, the crop information 114 may also include crop images captured by a camera in the greenhouse 102. For example, the crop image may be an image of the leaf surface of the crop or an image of the fruit of the crop taken by the camera. By analyzing the crop image using a machine learning model, for example, learning the change pattern of the leaf area, etc., the growth status of the crop may be determined.

[0036] In some embodiments, the environmental information 116 may include environmental data within the greenhouse 102 (for example, including but not limited to air temperature and humidity, light intensity, carbon dioxide concentration, soil temperature and humidity, etc.), meteorological information (for example, including but not limited to recent meteorological information and weather forecasts at the location of the greenhouse 102), weather station data (for example, including but not limited to temperature, humidity, solar radiation, light intensity, etc.), and geographic information (for example, including but not limited to longitude and latitude, climate information, seasonal information), etc.

[0037] In environment 100, crop model 118 can be configured to generate a predictive irrigation strategy based on crop information and environmental information. Figure 1 As shown, the controller 108 can input the crop information 114 and the environmental information 116 into the crop model 118. Then, the crop model 118 can generate a predicted irrigation strategy 120 based on the crop information 114 and the environmental information 116. In some embodiments, the crop model 118 can be a trained machine learning model. The crop model 118 can generate crop features based on the crop information 114, and generate environmental features based on the environmental information 116. In some embodiments, the crop model 118 can also generate time series features indicating soil moisture changes based on the environmental information 116. Then, the crop model 118 can generate a predicted irrigation strategy 120 based on the crop features, the environmental features, and the time series features. The predicted irrigation strategy 120 may include an irrigation action sequence, which may include an irrigation action, a parameter associated with the irrigation action, and a time associated with the irrigation action.

[0038] In the environment 100, after the predicted irrigation strategy 120 is generated by the crop model 118, the controller 108 may generate a recommended irrigation strategy 122 based on the user irrigation behavior data 112 and the predicted irrigation strategy 120. In some embodiments, the controller 108 may determine the execution result corresponding to the user irrigation behavior data 112, and then adjust the predicted irrigation strategy 120 based on the effectiveness of the execution result, thereby generating the adjusted predicted irrigation strategy 120 as the recommended irrigation strategy 122. Since the effectiveness of the irrigation strategy actually executed by the user contained in the user irrigation behavior data 112 may be higher than the effectiveness of the expected predicted irrigation strategy 120 (for example, because the irrigation strategy preferred by the user is more suitable for the local greenhouse environment and crop varieties), the effectiveness of the generated recommended irrigation strategy 122 can be improved by combining the user irrigation behavior data 112 and the predicted irrigation strategy 120.

[0039] In this way, the learned crop model 118 can generate a predicted irrigation strategy 120 suitable for crop growth in the current greenhouse based on the crop information 114 and the environmental information 116, without the need for professionals to perform system adjustment and parameter setting for the current greenhouse, thereby improving the versatility of intelligent irrigation. In addition, by considering the user irrigation behavior data 112, user preferences can be used as an important input and feedback indicator for generating recommended irrigation strategies, thereby improving the effectiveness of irrigation strategies under specific user preferences and optimizing crop growth conditions.

[0040] Figure 2 2 shows a flow chart of a crop model-based irrigation method 200 according to some embodiments of the present disclosure. The method 200 may be executed by a controller. For example, the method 200 may be executed by a controller. Figure 1 The controller 108 in the embodiment is executed. Figure 2 As shown, at block 202, the controller may obtain user irrigation behavior data, crop information associated with the crop, and environmental information associated with the crop growth environment. Figure 1 In the environment 100 shown, the controller 108 can obtain user irrigation behavior data 112, crop information 114 associated with the crop 104, and environmental information 116 associated with the growth environment of the crop 104. The user irrigation behavior data 112 may include, for example, the time of opening or closing a valve, or the time of watering before fertilization, etc. In some embodiments, the user irrigation behavior data 112 may include irrigation behavior (e.g., opening a water valve for watering), parameters associated with the irrigation behavior (e.g., the degree of opening of the water valve, the duration of opening the water valve), and the time corresponding to the irrigation behavior (e.g., the time of opening the water valve), wherein the irrigation behavior may include watering and fertilizing.

[0041] The crop information 114 may include, for example, crop varieties, planting cycles, and phenological periods. In some embodiments, the crop information 114 may also include crop images captured by a camera in the greenhouse 102. For example, the crop image may be an image of the leaf surface of the crop or an image of the fruit of the crop taken by the camera. By analyzing the crop image using a machine learning model, for example, learning the change pattern of the leaf area, the growth status of the crop may be determined.

[0042] In some embodiments, the environmental information 116 may include environmental data within the greenhouse 102 (for example, including but not limited to air temperature and humidity, light intensity, carbon dioxide concentration, soil temperature and humidity, etc.), meteorological information (for example, including but not limited to recent meteorological information and weather forecasts at the location of the greenhouse 102), weather station data (for example, including but not limited to temperature, humidity, solar radiation, light intensity, etc.), and geographic information (for example, including but not limited to longitude and latitude, climate information, seasonal information), etc.

[0043] At block 204, the controller may utilize the crop model to generate a predictive irrigation strategy based on the crop information and the environmental information. Figure 1 In the illustrated environment 100, the controller 108 may input crop information 114 and environmental information 116 into a crop model 118. The crop model 118 may then generate a predicted irrigation strategy 120 based on the crop information 114 and environmental information 116. In some embodiments, the crop model 118 may be a trained machine learning model. The predicted irrigation strategy 120 may include an irrigation action sequence, which may include irrigation actions, parameters associated with the irrigation actions, and times associated with the irrigation actions.

[0044] At block 206, the controller may generate a recommended irrigation strategy based on the user irrigation behavior data and the predicted irrigation strategy. Figure 1 In the illustrated environment 100, the controller 108 may generate a recommended irrigation strategy 122 based on the user irrigation behavior data 112 and the predicted irrigation strategy 120. In some embodiments, the controller 108 may determine an execution result corresponding to the user irrigation behavior data 112, and then adjust the predicted irrigation strategy 120 based on the effectiveness of the execution result, thereby generating the adjusted predicted irrigation strategy 120 as the recommended irrigation strategy 122.

[0045] In this way, the learned crop model can generate a predictive irrigation strategy suitable for crop growth in the current greenhouse based on crop information and environmental information, without the need for professionals to adjust the system and set parameters for the current greenhouse, thus improving the versatility of smart irrigation. In addition, by considering user irrigation behavior data, user preferences can be used as an important input and feedback indicator for generating recommended irrigation strategies, thereby improving the effectiveness of irrigation strategies under specific user preferences and optimizing crop growth conditions.

[0046] In some embodiments, when generating a recommended irrigation strategy, the controller may obtain an irrigation behavior execution result associated with the user irrigation behavior data. The controller may generate a user irrigation behavior score based on the irrigation behavior execution result. In addition, the controller may generate a predicted irrigation strategy score based on the predicted irrigation strategy. Then, the controller may generate a recommended irrigation strategy based on the user irrigation behavior data, the predicted irrigation strategy, the user irrigation behavior score, and the predicted irrigation strategy score. In some embodiments, the irrigation behavior execution result includes crop images captured by a camera in the greenhouse, sensor data during the irrigation behavior, and meteorological data during the irrigation behavior.

[0047] In some embodiments, when generating a recommended irrigation strategy based on the user irrigation behavior data, the predicted irrigation strategy, the user irrigation behavior score, and the predicted irrigation strategy score, the controller may compare the user irrigation behavior score and the predicted irrigation strategy score. In response to the user irrigation behavior score being greater than the predicted irrigation strategy score, the controller may generate a recommended irrigation strategy by adjusting the predicted irrigation strategy using the user irrigation behavior data.

[0048] Figure 3 Schematic diagram showing the architecture of an example system 300 for irrigation according to some embodiments of the present disclosure. Figure 3 As shown, the system 300 includes an irrigation prediction model 302, an irrigation assessment model 304, an irrigation decision model 306, and an irrigation strategy execution module 308. The irrigation prediction model 302 (e.g., Figure 1 The crop model 118 in the embodiment of the present invention can be configured to generate a predicted irrigation strategy based on environmental information of the crop growth environment and crop information associated with the crop. The irrigation assessment model 304 can be configured to evaluate the irrigation strategy to generate a score indicating the effectiveness of the irrigation strategy. The irrigation assessment model 304 can also be configured to evaluate the execution result of the user's irrigation behavior to generate a score indicating the health of the crop growth corresponding to the execution result. The irrigation decision model 306 can be configured to adjust the predicted irrigation strategy based on the user irrigation behavior data, the user irrigation behavior score, the predicted irrigation strategy, and the predicted irrigation strategy score to generate a recommended irrigation strategy provided to the user. The irrigation strategy execution module 308 can be configured to execute irrigation behavior according to the recommended irrigation strategy or the irrigation strategy input by the user.

[0049] like Figure 3 As shown, the system 300 can determine the user's irrigation behavior data 310 (e.g., Figure 1 The execution result 316 corresponding to the user irrigation behavior data 112 in the irrigation water may be included in the irrigation water evaluation model 304. The execution result 316 may include, for example, the EC value and pH value of the soil. The EC value is an indicator of the concentration of dissolved salt ions in the irrigation water or soil solution, which is used to reflect the conductivity of the solution. The EC value is an important parameter for measuring the nutrient concentration in the soil or irrigation water. The pH value is an indicator of the acidity or alkalinity of the solution, which is used to reflect the acidity or alkalinity of the irrigation water or soil solution. The irrigation evaluation model 304 may determine the user irrigation behavior score 320 based on the execution result 316, and the user irrigation behavior score 320 may indicate the growth health of the crop after executing the irrigation behavior included in the user irrigation behavior data 310.

[0050] In some embodiments, the system 300 can predetermine the EC value and pH value range for the target crop as a reference for the healthy growth of the crop. For example, the EC value range can be set based on the salt tolerance of the target crop, and the pH value range can be set based on the acidity and alkalinity requirements of the crop. These ranges can be set in combination with agricultural research data or expert knowledge, and dynamically adjusted according to the needs of the crop at different growth stages. The system 300 can then compare the currently measured EC value and pH value contained in the execution result 316 with the corresponding predetermined ranges to calculate the EC value score and pH value score, and the higher the score, the healthier the crop. The system 300 can then fuse the EC value score and the pH value score according to a predetermined weight to obtain a comprehensive health score as the user irrigation behavior score 320.

[0051] like Figure 3 As shown, in system 300, irrigation prediction model 302 can be based on environmental information 312 of the crop growth environment (e.g., Figure 1 ) and crop information 314 associated with the crop (e.g., Figure 1 The crop information 314 in the image may be used to generate a predicted irrigation strategy 318. In some embodiments, the crop information 314 may include a crop image captured by a camera, and the crop image may include the leaf surface or fruit of the crop. In some embodiments, the system 300 may use a trained visual model to determine features such as the leaf surface area or fruit size of the crop from the crop image, which may reflect the current growth status of the crop. In addition, the crop information 314 may also include crop varieties, customized cycles, and phenological periods. In some embodiments, the environmental information 312 may include soil moisture content captured by a soil moisture sensor, environmental information in a greenhouse, meteorological information, weather station data, and geographic information. In this way, the irrigation prediction model 302 can generate corresponding predicted irrigation strategies 318 based on different crop growth environments and different crop growth states.

[0052] After generating the predicted irrigation strategy 318, the system 300 can input it to the irrigation assessment model 304. The irrigation assessment model 304 can evaluate the predicted irrigation strategy 318 to generate a predicted irrigation strategy score 322. The predicted irrigation strategy score 322 can indicate the effectiveness of the predicted irrigation strategy 318. The irrigation decision model 306 can then generate a recommended irrigation strategy 324 based on the user irrigation behavior data 310, the user irrigation behavior score 320, the predicted irrigation strategy 318, and the predicted irrigation strategy score 322.

[0053] In some embodiments, the irrigation decision model 306 may compare the user irrigation behavior score 320 with the predicted irrigation strategy score 322. In some cases, the user irrigation behavior score 320 may be higher than the predicted irrigation strategy score 322. For example, after the system 300 recommends an irrigation strategy to the user, the farmer does not irrigate according to the recommended irrigation strategy, but irrigates according to his own irrigation habits. After the farmer irrigates according to his own irrigation habits, the execution result may indicate that the growth state of the crop is good, so the user irrigation behavior score 320 is higher than the predicted irrigation strategy score 322. In this case, the irrigation decision model 306 can adjust the predicted irrigation strategy 318 based on the user irrigation behavior data 310 to generate a recommended irrigation strategy 324.

[0054] In the system 300, the generated recommended irrigation strategy 324 can be provided to the farmer. The farmer can decide to use the recommended irrigation strategy 324 for irrigation, or adjust the recommended irrigation strategy 324 to make the irrigation strategy more in line with the user's irrigation habits or preferences. Then, the determined irrigation strategy can be executed by the irrigation strategy execution module 308, and new user irrigation behavior data 310 is generated.

[0055] In this way, the system 300 can learn irrigation strategies suitable for the local environment and crop varieties from the user's irrigation behavior and the user's irrigation preferences, so that it can continuously optimize the irrigation model (for example, the irrigation prediction model 302 and the irrigation decision model 306), improve the effectiveness of the generated recommended irrigation strategy 324, and optimize the growth conditions of the crops.

[0056] In some embodiments, the controller may obtain a user irrigation strategy provided by a user. The controller may generate a user irrigation strategy score based on the user irrigation strategy. In addition, the controller may generate a recommended irrigation strategy score based on the recommended irrigation strategy. Then, the controller may provide the user with the user irrigation strategy score and the recommended irrigation strategy score through a display device.

[0057] Figure 4 FIG. 4 is a schematic diagram showing an example 400 of generating a recommended irrigation strategy score and a user irrigation strategy score according to some embodiments of the present disclosure. Figure 4 As shown, example 400 includes a controller 402 (e.g., Figure 1 Controller 402 may generate a recommended irrigation strategy 406 (e.g., Figure 3The recommended irrigation strategy 406 may then be displayed to the user via the display device 404. In the example 400, the user may modify the recommended irrigation strategy 406 based on their own irrigation habits or preferences on the display device 404 to generate a new user irrigation strategy 408, or may input a new user irrigation strategy 408 through the display device 404. The controller 402 may then utilize an irrigation assessment model (e.g., Figure 3 The recommended irrigation strategy 406 and the user irrigation strategy 408 are evaluated by using the irrigation evaluation model 304 in the display device 404 to generate a recommended irrigation strategy score 410 for the recommended irrigation strategy 406 and a user irrigation strategy score 412 for the user irrigation strategy 408. The recommended irrigation strategy score 410 and the user irrigation strategy score 412 can be provided to the user via the display device 404.

[0058] In this way, the user can determine the irrigation strategy to be finally used by comparing the recommended irrigation strategy score 410 and the user irrigation strategy score 412. In addition, the user can also regenerate the user irrigation strategy score 412 by adjusting the user irrigation strategy 408 to continuously optimize the user irrigation strategy 408, thereby retaining the user preference in the user irrigation strategy 408 and allowing the user to continuously optimize the user irrigation strategy 408 by referring to the recommended irrigation strategy.

[0059] In some embodiments, when generating a forecast irrigation strategy, the controller can generate a forecast transpiration based on crop information and environmental information. Then, the controller can determine the transpiration change trend by using a soil moisture sensor. Then, the controller can generate a forecast irrigation strategy based on the forecast transpiration and the transpiration change trend.

[0060] In some embodiments, when generating the predicted transpiration amount based on the crop information and the environmental information, the controller may determine the current crop growth state based on the crop image using a visual model. Then, the controller may generate the predicted transpiration amount based on the crop growth state and the environmental information.

[0061] In some embodiments, when determining the transpiration change trend by using a soil moisture sensor, the controller can obtain the soil moisture change curve of the crop area through the soil moisture sensor. Then, the controller can determine the transpiration change trend based on the soil moisture change curve.

[0062] In some embodiments, when generating a predicted irrigation strategy based on the predicted transpiration amount and the transpiration amount change trend, the controller may adjust the predicted transpiration amount based on the transpiration amount change trend. Then, the controller may generate a predicted irrigation strategy based on the adjusted predicted transpiration amount.

[0063] Figure 5 A schematic diagram of example 500 of generating a predicted irrigation strategy according to some embodiments of the present disclosure is shown. In some related technologies, the controller determines the irrigation strategy based on the absolute value of the soil moisture sensor. However, as a sensitive microelectronic component, the soil moisture sensor needs to be calibrated regularly. In addition, due to different soil textures, the wrapping of the sensitive probe is also different, so that a model established based on soil moisture data in a certain area may have calculation deviations when implemented in another area. In this case, the model needs to be calibrated multiple times in the new area. To this end, in example 500, a transpiration prediction model can be used to determine the predicted transpiration, and the transpiration change trend can be determined based on the data of the soil moisture sensor, and then the predicted transpiration and the transpiration change trend can be combined to generate a predicted transpiration with higher accuracy.

[0064] like Figure 5 As shown, in example 500, the controller can use camera 504 to obtain crop image 514, and crop image 514 can include, for example, the leaf surface of the crop or the fruit of the crop. The controller can use the trained visual model to determine the characteristics of the leaf surface area or fruit size of the crop from the crop image 514. Then, the controller can determine the crop growth state 516 based on these characteristics. In addition, the controller can also obtain environmental information 518 of the crop growth environment, and the environmental information 518 can include environmental data in the greenhouse (for example, including but not limited to air temperature and humidity, light intensity, carbon dioxide concentration, soil temperature and humidity, etc.), meteorological information (for example, including but not limited to recent meteorological information and weather forecasts at the location of the greenhouse), weather station data (for example, including but not limited to temperature, humidity, solar radiation, light intensity, etc.), and geographic information (for example, including but not limited to longitude and latitude, climate information, and seasonal information).

[0065] In example 500, the controller may input the crop growth state 516 and the environmental information 518 into the transpiration prediction model 506. The transpiration prediction model 506 may generate a predicted transpiration 520 based on the crop growth state 516 and the environmental information 518. The transpiration refers to the total amount of water vapor released by plants to the outside through the stomata of leaves, stems and other parts. The transpiration is a quantitative indicator of plant transpiration, which can be expressed as the amount of water released by plants per unit time.

[0066] To further improve the accuracy of the predicted transpiration 520, the controller may use the soil moisture sensor 502 to determine the transpiration change trend. Figure 5 As shown, the controller can use the soil moisture sensor 502 to obtain the soil moisture content variation curve 510 . Figure 6 FIG. 6 is a schematic diagram showing an example 600 of a soil moisture content variation curve according to some embodiments of the present disclosure. Figure 6As shown, after each irrigation, the water content of the soil reaches a peak value, for example, at time T1, the water content of the soil reaches a peak value. After a period of time, the water content of the soil continues to decrease and reaches a trough, for example, at time T2, the water content of the soil reaches a trough.

[0067] In such Figure 5 In the example 500 shown, the controller can determine the transpiration change trend 512 based on the soil moisture change curve 510. The transpiration change trend 512 can indicate the change rate of the transpiration. Figure 6 In the example 600 shown, the controller can calculate the slope of the curve by calculating the soil moisture content change curve corresponding to the calculation box 602. The larger the slope, the faster the water content in the soil decreases, and the faster the corresponding transpiration changes. Since this change trend is less affected by the calibration of the soil moisture sensor and the soil differences in different regions, it can more reliably reflect the actual transpiration.

[0068] In such Figure 5 In the example 500 shown, the controller can adjust the predicted transpiration 520 generated by the transpiration prediction model 506 based on the transpiration change trend 512 to generate an adjusted predicted transpiration 522. Then, the adjusted predicted transpiration 522 can be input into the irrigation prediction model 508 (e.g., Figure 3 In the irrigation prediction model 302 in FIG. 5 , for example, the adjusted predicted transpiration 522 is input into the irrigation prediction model 508 as part of the crop information or environmental information. Then, the irrigation prediction model 508 can generate a predicted irrigation strategy 524 based on the adjusted predicted transpiration 52.

[0069] In this way, the transpiration prediction model 506 can predict the transpiration based on the crop growth state 516 and the environmental information 518, rather than using the absolute value of the soil moisture to estimate the transpiration, thereby improving the accuracy of the determined transpiration. In addition, using the transpiration change trend 512 to adjust the predicted transpiration can further improve the accuracy of the determined transpiration, thereby improving the effectiveness of the irrigation strategy generated based on the transpiration.

[0070] Figure 7 FIG. 7 is a block diagram of a crop model-based irrigation device 700 according to some embodiments of the present disclosure. Figure 7As shown, the device 700 includes a crop data acquisition module 702, which is configured to acquire user irrigation behavior data, crop information associated with the crop, and environmental information associated with the crop growth environment. The device 700 also includes a prediction strategy generation module 704, which is configured to generate a prediction irrigation strategy using a crop model based on the crop information and environmental information. In addition, the device 700 also includes a recommendation strategy generation module 706, which is configured to generate a recommended irrigation strategy based on the user irrigation behavior data and the prediction irrigation strategy.

[0071] In some embodiments, the user irrigation behavior data includes irrigation behavior, parameters associated with the irrigation behavior, and time corresponding to the irrigation behavior, and the irrigation behavior includes watering and fertilizing.

[0072] In some embodiments, the crop information includes crop images captured by a camera within the greenhouse, crop varieties, planting cycles, and phenological periods, and the environmental information includes environmental information within the greenhouse, meteorological information, weather station data, and geographic information.

[0073] In some embodiments, the recommended strategy generation module 706 includes: an execution result acquisition module, configured to acquire irrigation behavior execution results associated with user irrigation behavior data; a behavior score generation module, configured to generate a user irrigation behavior score based on the irrigation behavior execution results; a prediction strategy score generation module, configured to generate a predicted irrigation strategy score based on the predicted irrigation strategy; and a score usage module, configured to generate a recommended irrigation strategy based on the user irrigation behavior data, the predicted irrigation strategy, the user irrigation behavior score, and the predicted irrigation strategy score.

[0074] In some embodiments, the irrigation action execution results include crop images captured by a camera within the greenhouse, sensor data during the irrigation action, and meteorological data during the irrigation action.

[0075] In some embodiments, the score usage module includes: a score comparison module configured to compare the user irrigation behavior score and the predicted irrigation strategy score; and a strategy adjustment module configured to generate a recommended irrigation strategy by adjusting the predicted irrigation strategy using the user irrigation behavior data in response to the user irrigation behavior score being greater than the predicted irrigation strategy score.

[0076] In some embodiments, the device 700 also includes: a user strategy acquisition module, configured to acquire a user irrigation strategy provided by a user; a user strategy score generation module, configured to generate a user irrigation strategy score based on the user irrigation strategy; a recommended strategy score generation module, configured to generate a recommended irrigation strategy score based on the recommended irrigation strategy; and a score display module, configured to provide the user irrigation strategy score and the recommended irrigation strategy score to the user through a display device.

[0077] In some embodiments, the prediction strategy generation module 704 includes: a predicted transpiration amount generation module, configured to generate predicted transpiration amount based on crop information and environmental information; a transpiration amount change trend determination module, configured to determine the transpiration amount change trend by utilizing a soil moisture sensor; and a transpiration amount change trend utilization module, configured to generate a predicted irrigation strategy based on the predicted transpiration amount and the transpiration amount change trend.

[0078] In some embodiments, the crop information includes crop images captured by a camera within a greenhouse, and the predicted transpiration amount generation module includes: a growth state determination module, configured to determine the current crop growth state based on the crop image using a visual model; and a growth state utilization module, configured to generate a predicted transpiration amount based on the crop growth state and environmental information.

[0079] In some embodiments, the transpiration change trend determination module includes: a change curve acquisition module, configured to obtain the soil moisture change curve of the crop area through a soil moisture sensor; and a change curve use module, configured to determine the transpiration change trend based on the soil moisture change curve.

[0080] In some embodiments, the transpiration amount change trend using module includes: a predicted transpiration amount adjustment module configured to adjust the predicted transpiration amount based on the transpiration amount change trend; and a transpiration amount adjustment using module configured to generate a predicted irrigation strategy based on the adjusted predicted transpiration amount.

[0081] It can be understood that by using the device 700 of the present disclosure, at least one of the many advantages that can be achieved by the method or process described above can be achieved. For example, the learned crop model can generate a predictive irrigation strategy suitable for crop growth in the current greenhouse based on crop information and environmental information, without the need for professionals to perform system adjustment and parameter setting for the current greenhouse, thereby improving the versatility of intelligent irrigation. In addition, by considering user irrigation behavior data, user preferences can be used as an important input and feedback indicator for generating recommended irrigation strategies, thereby improving the effectiveness of irrigation strategies under specific user preferences and optimizing crop growth conditions.

[0082] Figure 8800 is a block diagram of a device that can implement multiple embodiments of the present disclosure. The device 800 can be, for example, Figure 1 The controller 108 is shown. Figure 8 As shown, the device 800 includes a central processing unit (CPU) and / or a graphics processing unit (GPU) 801, which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 802 or loaded from a storage unit 808 to a random access memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the device 800 can also be stored. The CPU / GPU 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804. Although not shown in FIG. Figure 8 As shown in FIG. 8 , device 800 may also include a co-processor.

[0083] A number of components in the device 800 are connected to the I / O interface 805, including: an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the device 800 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0084] The various methods or processes described above may be performed by the CPU / GPU 801. For example, in some embodiments, the methods may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the CPU / GPU 801, one or more steps or actions in the methods or processes described above may be performed.

[0085] In some embodiments, the methods and processes described above may be implemented as a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present disclosure.

[0086] Computer readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Computer readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination thereof. More specific examples (non-exhaustive list) of computer readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, for example, a punch card or a convex structure in a groove on which instructions are stored, and any suitable combination thereof. The computer readable storage medium used here is not interpreted as a transient signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated by a waveguide or other transmission medium (for example, a light pulse by an optical fiber cable), or an electrical signal transmitted by a wire.

[0087] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0088] The computer program instructions for performing the disclosed operation may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, programming languages ​​including object-oriented programming languages, and conventional procedural programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, executed as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., utilizing an Internet service provider to connect via the Internet). In certain embodiments, by utilizing the state information of a computer-readable program instruction to customize an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit may execute a computer-readable program instruction, thereby realizing various aspects of the present disclosure.

[0089] These computer-readable program instructions can be provided to a processing unit of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processing unit of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0090] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0091] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the equipment, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each frame in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the frame can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous frames can actually be executed substantially in parallel, and they can also be executed in the opposite order sometimes, depending on the functions involved. It should also be noted that each frame in the block diagram and / or flow chart, and the combination of frames in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0092] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. An irrigation method based on a crop model, comprising: Acquiring user irrigation behavior data, crop information associated with the crop, and environmental information associated with the crop growth environment; generating a predicted irrigation strategy using the crop model based on the crop information and the environmental information; as well as A recommended irrigation strategy is generated based on the user irrigation behavior data and the predicted irrigation strategy.

2. The method according to claim 1, wherein the user irrigation behavior data comprises irrigation behavior, parameters associated with the irrigation behavior, and time corresponding to the irrigation behavior, and the irrigation behavior comprises watering and fertilizing.

3. The method according to claim 1, wherein the crop information includes crop images captured by a camera in a greenhouse, crop varieties, planting cycles, and phenological periods, and the environmental information includes environmental information in the greenhouse, meteorological information, weather station data, and geographic information.

4. The method according to claim 1, wherein generating the recommended irrigation strategy based on the user irrigation behavior data and the predicted irrigation strategy comprises: Acquire an irrigation behavior execution result associated with the user irrigation behavior data; generating a user irrigation behavior score based on the irrigation behavior execution result; generating a predicted irrigation strategy score based on the predicted irrigation strategy; as well as The recommended irrigation strategy is generated based on the user irrigation behavior data, the predicted irrigation strategy, the user irrigation behavior score, and the predicted irrigation strategy score. 5 . The method according to claim 4 , wherein the irrigation action execution result comprises crop images captured by a camera in the greenhouse, sensor data during the irrigation action, and meteorological data during the irrigation action.

6. The method according to claim 4, wherein generating the recommended irrigation strategy based on the user irrigation behavior data, the predicted irrigation strategy, the user irrigation behavior score, and the predicted irrigation strategy score comprises: comparing the user irrigation behavior score and the predicted irrigation strategy score; as well as In response to the user irrigation behavior score being greater than the predicted irrigation strategy score, the recommended irrigation strategy is generated by adjusting the predicted irrigation strategy using the user irrigation behavior data.

7. The method according to claim 1, further comprising: Get the user irrigation strategy provided by the user; generating a user irrigation strategy score based on the user irrigation strategy; generating a recommended irrigation strategy score based on the recommended irrigation strategy; as well as The user irrigation strategy score and the recommended irrigation strategy score are provided to the user through a display device.

8. The method of claim 1, wherein generating the predicted irrigation strategy using the crop model based on the crop information and the environmental information comprises: generating a predicted transpiration amount based on the crop information and the environmental information; Determine evapotranspiration trends by using soil moisture sensors; as well as The predicted irrigation strategy is generated based on the predicted transpiration amount and the transpiration amount change trend.

9. The method of claim 8, wherein the crop information comprises crop images captured by a camera within a greenhouse, and generating the predicted transpiration based on the crop information and the environmental information comprises: Based on the crop image, using a visual model to determine the current crop growth status; as well as The predicted transpiration amount is generated based on the crop growth status and the environmental information.

10. The method according to claim 8, wherein determining the transpiration variation trend by using the soil moisture sensor comprises: The soil moisture sensor is used to obtain a soil moisture change curve of the area where the crops are located; as well as The transpiration variation trend is determined based on the soil moisture content variation curve.

11. The method according to claim 8, wherein generating the predicted irrigation strategy based on the predicted transpiration and the transpiration change trend comprises: Adjusting the predicted transpiration amount based on the transpiration amount change trend; as well as The predicted irrigation strategy is generated based on the adjusted predicted transpiration.

12. An irrigation device based on a crop model, comprising: A crop data acquisition module, configured to acquire user irrigation behavior data, crop information associated with the crop, and environmental information associated with the crop growth environment; A prediction strategy generation module is configured to generate a prediction irrigation strategy using the crop model based on the crop information and the environmental information; as well as The recommended strategy generation module is configured to generate a recommended irrigation strategy based on the user irrigation behavior data and the predicted irrigation strategy.

13. An electronic device, comprising: processor; as well as A memory coupled to the processor, the memory having instructions stored therein, wherein when the instructions are executed by the processor, the electronic device executes the method according to any one of claims 1 to 11.

14. A computer program product tangibly stored on a non-transitory computer readable medium and comprising machine executable instructions which, when executed, cause a machine to implement the method according to any one of claims 1 to 11.

Images