Crop growth monitoring method and system based on artificial intelligence

Abstract

The invention discloses a crop growth monitoring method and system based on artificial intelligence, and the method comprises the steps: obtaining multi-source crop growth data based on a sensor, building a pre-trained BP crop state prediction model based on a BP neural network, optimizing the parameters of the BP crop state prediction model through employing an SSA sparrow optimization algorithm, and carrying out the optimization of the parameters of the BP crop state prediction model, inputting the real-time crop growth data into the target BP crop state prediction model for training, generating an irrigation strategy and a fertilization strategy of crops according to the crop growth state, and transmitting the irrigation strategy and the fertilization strategy to a crop irrigation system and a fertilization system; and obtaining target crop growth data of the irrigated and fertilized crops, and adjusting an irrigation strategy and a fertilization strategy according to the target crop growth data. Scientific and reasonable irrigation and fertilization suggestions and management strategies can be provided for farmers, so that resource allocation is optimized, and the crop yield and quality are improved.

Description

Technical Field

[0001] The present invention relates to the field of crop monitoring, and in particular to an artificial intelligence-based crop growth monitoring method and system. Background Art

[0002] With the continuous development of agricultural technology, improving crop yield and quality has become the core goal of agricultural production. In this process, crop growth monitoring is an indispensable part of agricultural production. By real-time monitoring of crop growth environment, crop status and other information, problems encountered in the crop growth process can be discovered and solved in time, ensuring the healthy growth of crops and improving yield and quality. In the prior art, crops are usually monitored and identified manually, and irrigation and fertilization of crops are adjusted according to the identification results. In this case, human judgment is prone to errors, and it is time-consuming and labor-intensive. The monitoring efficiency of crops is low, and the production efficiency of crops cannot be effectively improved. Therefore, how to improve the production efficiency of crops is a technical problem that needs to be solved at this stage. Summary of the invention

[0003] The purpose of the present invention is to solve the above problems and to design a crop growth monitoring method and system based on artificial intelligence.

[0004] To achieve the above object, the technical solution of the present invention is that, further, in the above-mentioned crop growth monitoring method based on artificial intelligence, the crop growth monitoring comprises the following steps:

[0005] Acquire multi-source crop growth data based on sensors, transmit the multi-source crop growth data to a database using wireless communication technology, and perform data preprocessing on the multi-source crop growth data to obtain real-time crop growth data;

[0006] A pre-trained BP crop state prediction model is established based on a BP neural network, and the parameters of the BP crop state prediction model are optimized using an SSA sparrow optimization algorithm to obtain a target BP crop state prediction model;

[0007] Inputting the real-time crop growth data into the target BP crop state prediction model for training to obtain the crop growth state;

[0008] Generate an irrigation strategy and a fertilization strategy for the crops according to the growth status of the crops, and transmit the irrigation strategy and the fertilization strategy to the crop irrigation system and the fertilization system;

[0009] Obtain target crop growth data of crops after irrigation and fertilization, and adjust irrigation strategies and fertilization strategies according to the target crop growth data.

[0010] Furthermore, in the above-mentioned crop growth monitoring method based on artificial intelligence, the sensor is used to obtain multi-source crop growth data, the multi-source crop growth data is transmitted to a database using wireless communication technology, and the multi-source crop growth data is preprocessed to obtain real-time crop growth data, including:

[0011] Sensors are arranged in the soil of crops, wherein the sensors include at least a soil moisture sensor, a soil temperature and humidity meter, a light intensity meter, a chlorophyll content sensor and a meteorological sensor;

[0012] The sensor acquires crop data in the crop soil every 5 hours to obtain multi-source crop growth data;

[0013] Using Zigbee wireless communication technology to transmit the multi-source crop growth data to a database;

[0014] Deleting outliers in the multi-source crop growth data and supplementing missing values ​​to obtain first crop growth data;

[0015] The first crop growth data is normalized to obtain real-time crop growth data.

[0016] Furthermore, in the above-mentioned artificial intelligence-based crop growth monitoring method, the pre-trained BP crop state prediction model is established based on the BP neural network, and the parameters of the BP crop state prediction model are optimized using the SSA sparrow optimization algorithm to obtain the target BP crop state prediction model, including:

[0017] Establish a BP crop state prediction model based on BP neural network, and input the historical crop data in the database into the model;

[0018] Initialize the weights and thresholds of the BP crop state prediction model, and initialize the parameters of the SSA sparrow search algorithm;

[0019] The reverse learning strategy is used to initialize the population, the sine and cosine algorithms are introduced to update the discoverer position, and the l evy flight strategy is introduced to update the follower position;

[0020] According to the update results, the position of the sentinel is updated, and the optimal individual position is found according to the latest updated position;

[0021] The optimal individual position is set as the weight and threshold of the BP crop state prediction model to obtain the target BP crop state prediction model.

[0022] Furthermore, in the above-mentioned crop growth monitoring method based on artificial intelligence, the real-time crop growth data is input into the target BP crop state prediction model for training to obtain the crop growth state, including:

[0023] The target BP crop state prediction model is trained 1000 times, the learning rate is 0.01, the training target minimum error is 0.000001, and the momentum factor is 0.01;

[0024] The number of input layer nodes of the target BP crop state prediction model is set to 4, the number of output layer nodes is set to 1, and the number of hidden layer nodes is set to 9;

[0025] Set the number of sparrows in the sparrow search algorithm to 20, the proportion of discoverers to 0.7, the proportion of followers to 0.3, the proportion of vigilants to 0.2, and the warning value to 0.6;

[0026] The real-time crop growth data is input into the target BP crop state prediction model for training to obtain the crop growth state.

[0027] Furthermore, in the above-mentioned crop growth monitoring method based on artificial intelligence, the generation of the crop irrigation strategy and fertilization strategy according to the crop growth state, and the transmission of the irrigation strategy and fertilization strategy to the crop irrigation system and fertilization system, includes:

[0028] Based on the predicted crop growth status, irrigation and fertilization strategies are formulated using expert systems or rule engines, including irrigation water volume, fertilizer type, dosage, and time;

[0029] Generate PLC control instructions for irrigation system and fertilization system based on irrigation strategy and fertilization strategy;

[0030] The PLC control instructions are transmitted to the irrigation system and the fertilization system through the API interface or the Internet of Things control system, and the system irrigates and fertilizes the soil of the crops according to the PLC control instructions.

[0031] Furthermore, in the above-mentioned crop growth monitoring method based on artificial intelligence, the step of obtaining target crop growth data of crops after irrigation and fertilization, and adjusting the irrigation strategy and fertilization strategy according to the target crop growth data, includes:

[0032] After irrigation and fertilization, the growth data of crops are collected again, including growth rate, leaf color change, and soil moisture content, to obtain the growth data of target crops;

[0033] The target crop growth data is input into the target BP crop state prediction model for training after data preprocessing to obtain the target crop growth state;

[0034] The irrigation strategy and the fertilization strategy are adjusted according to the growth status of the target crops, and the crops are irrigated and fertilized according to the adjusted irrigation strategy and fertilization strategy.

[0035] Furthermore, in an artificial intelligence-based crop growth monitoring system, the crop growth monitoring system includes the following modules:

[0036] A data acquisition module, used to acquire multi-source crop growth data based on sensors, transmit the multi-source crop growth data to a database using wireless communication technology, and perform data preprocessing on the multi-source crop growth data to obtain real-time crop growth data;

[0037] A model building module is used to build a pre-trained BP crop state prediction model based on a BP neural network, and optimize the parameters of the BP crop state prediction model using an SSA sparrow optimization algorithm to obtain a target BP crop state prediction model;

[0038] A state prediction module, used for inputting the real-time crop growth data into the target BP crop state prediction model for training to obtain the crop growth state;

[0039] A strategy generation module, used for generating an irrigation strategy and a fertilization strategy for the crops according to the growth status of the crops, and transmitting the irrigation strategy and the fertilization strategy to the crop irrigation system and the fertilization system;

[0040] The target adjustment module is used to obtain target crop growth data of crops after irrigation and fertilization, and adjust the irrigation strategy and fertilization strategy according to the target crop growth data.

[0041] Furthermore, in an artificial intelligence-based crop growth monitoring system, the data acquisition module includes the following submodules:

[0042] A submodule is provided, which is used to provide sensors in the soil of crops, wherein the sensors at least include a soil moisture sensor, a soil temperature and humidity meter, a light intensity meter, a chlorophyll content sensor and a meteorological sensor;

[0043] The acquisition submodule is used to acquire crop data in crop soil once every 5 hours through sensors to obtain multi-source crop growth data;

[0044] A transmission submodule, used for transmitting the multi-source crop growth data to a database using Zigbee wireless communication technology;

[0045] A processing submodule, configured to delete abnormal values ​​in the multi-source crop growth data and supplement missing values ​​to obtain first crop growth data;

[0046] The obtaining submodule is used to normalize the first crop growth data to obtain real-time crop growth data.

[0047] Furthermore, in an artificial intelligence-based crop growth monitoring system, the model building module includes the following submodules:

[0048] Establish a submodule for establishing a BP crop state prediction model based on a BP neural network, and input the historical crop data in the database into the model;

[0049] The initialization submodule is used to initialize the weights and thresholds of the BP crop state prediction model and the parameters of the SSA sparrow search algorithm;

[0050] Introduce a submodule to initialize the population using the reverse learning strategy, introduce the sine-cosine algorithm to update the discoverer position, and introduce the l evy flight strategy to update the follower position;

[0051] The update submodule is used to update the position of the sentinel according to the update result and find the optimal individual position according to the latest updated position;

[0052] A submodule is obtained, which is used to set the optimal individual position as the weight and threshold of the BP crop state prediction model to obtain the target BP crop state prediction model.

[0053] Its beneficial effects are that, based on sensors, multi-source crop growth data is obtained, the multi-source crop growth data is transmitted to a database using wireless communication technology, and the multi-source crop growth data is preprocessed to obtain real-time crop growth data; a pre-trained BP crop state prediction model is established based on a BP neural network, and the parameters of the BP crop state prediction model are optimized using an SSA sparrow optimization algorithm to obtain a target BP crop state prediction model; the real-time crop growth data is input into the target BP crop state prediction model for training to obtain crop growth status; irrigation strategies and fertilization strategies for crops are generated according to the crop growth status, and the irrigation strategies and fertilization strategies are transmitted to the crop irrigation system and fertilization system; target crop growth data of crops after irrigation and fertilization are obtained, and the irrigation strategies and fertilization strategies are adjusted according to the target crop growth data. By collecting crop growth environment data, crop state parameters and other information in real time, the system can quickly identify abnormal conditions in the crop growth process, such as pests and diseases, malnutrition, etc., and automatically issue an early warning. At the same time, combining historical data and current conditions, the system can predict future crop growth trends and provide farmers with scientific and reasonable irrigation and fertilization recommendations and management strategies, thereby optimizing resource allocation and improving crop yield and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the following detailed description of the preferred embodiment.The drawings are only for the purpose of illustrating the preferred embodiments and are not to be construed as limiting the invention.

[0055] Figure 1 This is a schematic diagram of a first embodiment of a crop growth monitoring method based on artificial intelligence in an embodiment of the present invention;

[0056] Figure 2 Schematic diagram of a second embodiment of a crop growth monitoring method based on artificial intelligence in an embodiment of the present invention;

[0057] Figure 3 Schematic diagram of a first embodiment of an artificial intelligence-based crop growth monitoring system in an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0060] The present invention will be described in detail below in conjunction with the accompanying drawings. Figure 1 As shown, a crop growth monitoring method based on artificial intelligence includes the following steps:

[0061] Step 101: acquiring multi-source crop growth data based on sensors, transmitting the multi-source crop growth data to a database using wireless communication technology, and performing data preprocessing on the multi-source crop growth data to obtain real-time crop growth data;

[0062] Specifically, in this embodiment, sensors are set in the soil of crops, and the sensors include at least a soil moisture sensor, a soil thermometer and humidity meter, a light intensity meter, a chlorophyll content sensor and a meteorological sensor; the crop data in the crop soil is obtained once every 5 hours by the sensor to obtain multi-source crop growth data; the multi-source crop growth data is transmitted to a database by using Zigbee wireless communication technology; the abnormal values ​​in the multi-source crop growth data are deleted and the missing values ​​are supplemented to obtain first crop growth data; the first crop growth data is normalized to obtain real-time crop growth data.

[0063] Step 102: establishing a pre-trained BP crop state prediction model based on the BP neural network, optimizing the parameters of the BP crop state prediction model using the SSA sparrow optimization algorithm, and obtaining a target BP crop state prediction model;

[0064] Specifically, in this embodiment, a BP crop state prediction model is established based on a BP neural network, and historical crop data in a database is input into the model; the weights and thresholds of the BP crop state prediction model are initialized, and the parameters of the SSA sparrow search algorithm are initialized; the population is initialized using a reverse learning strategy, and a sine-cosine algorithm is introduced to update the discoverer position, while a l evy flight strategy is introduced to update the follower position; based on the update result, the sentinel position is updated, and the optimal individual position is found based on the latest updated position; the optimal individual position is set as the weight and threshold of the BP crop state prediction model to obtain a target BP crop state prediction model.

[0065] Step 103: input the real-time crop growth data into the target BP crop state prediction model for training to obtain the crop growth state;

[0066] Specifically, in this embodiment, the training times of the target BP crop state prediction model are set to 1000 times, the learning rate is 0.01, the training target minimum error is 0.000001, and the momentum factor is 0.01; the number of input layer nodes of the target BP crop state prediction model is set to 4, the number of output layer nodes is 1, and the number of hidden layer nodes is 9; the number of sparrow populations in the sparrow search algorithm is set to 20, the number of discoverers is 0.7, the number of followers is 0.3, the number of alerts is 0.2, and the alert value is 0.6; the real-time crop growth data is input into the target BP crop state prediction model for training to obtain the crop growth status.

[0067] Step 104: Generate an irrigation strategy and a fertilization strategy for the crops according to the growth status of the crops, and transmit the irrigation strategy and the fertilization strategy to the crop irrigation system and the fertilization system;

[0068] Specifically, in this embodiment, based on the predicted growth status of crops, an expert system or a rule engine is used to formulate an irrigation strategy and a fertilization strategy, including the amount of irrigation water, the type of fertilizer, the dosage, and the time; based on the irrigation strategy and the fertilization strategy, PLC control instructions for the irrigation system and the fertilization system are generated; the PLC control instructions are transmitted to the irrigation system and the fertilization system through an API interface or an Internet of Things control system, and the system irrigates and fertilizes the soil of crops according to the PLC control instructions.

[0069] Step 105: Obtain target crop growth data of the crops after irrigation and fertilization, and adjust the irrigation strategy and fertilization strategy according to the target crop growth data.

[0070] Specifically, in this embodiment, after implementing irrigation and fertilization, the growth data of crops are collected again, including growth rate, leaf color change, and soil moisture content, to obtain target crop growth data; the target crop growth data is input into the target BP crop state prediction model for training after data preprocessing to obtain the growth state of the target crop; the irrigation strategy and fertilization strategy are adjusted according to the growth state of the target crop, and the crops are irrigated and fertilized according to the adjusted irrigation strategy and fertilization strategy.

[0071] Its beneficial effects are that it obtains multi-source crop growth data based on sensors, transmits multi-source crop growth data to a database using wireless communication technology, performs data preprocessing on multi-source crop growth data, and obtains real-time crop growth data; establishes a pre-trained BP crop state prediction model based on a BP neural network, optimizes the parameters of the BP crop state prediction model using the SSA sparrow optimization algorithm, and obtains a target BP crop state prediction model; inputs real-time crop growth data into the target BP crop state prediction model for training to obtain crop growth status; generates irrigation strategies and fertilization strategies for crops according to crop growth status, and transmits the irrigation strategies and fertilization strategies to crop irrigation systems and fertilization systems; obtains target crop growth data of crops after irrigation and fertilization, and adjusts the irrigation strategies and fertilization strategies according to the target crop growth data. By collecting crop growth environment data, crop state parameters and other information in real time, the system can quickly identify abnormal conditions in the crop growth process, such as pests and diseases, malnutrition, etc., and automatically issues warnings. At the same time, combining historical data and current conditions, the system can predict future crop growth trends and provide farmers with scientific and reasonable irrigation and fertilization recommendations and management strategies, thereby optimizing resource allocation and improving crop yield and quality.

[0072] See also Figure 2 In a crop growth monitoring method based on artificial intelligence, a pre-trained BP crop state prediction model is established based on a BP neural network, and the parameters of the BP crop state prediction model are optimized using an SSA sparrow optimization algorithm to obtain a target BP crop state prediction model, including the following steps:

[0073] Step 201, establishing a BP crop state prediction model based on a BP neural network, and inputting historical crop data in a database into the model;

[0074] Step 202, initializing the weight and threshold of the BP crop state prediction model, and initializing the parameters of the SSA sparrow search algorithm;

[0075] Step 203: Initialize the population using the reverse learning strategy, introduce the sine-cosine algorithm to update the discoverer position, and introduce the l evy flight strategy to update the follower position;

[0076] Step 204: Update the position of the sentinel according to the update result, and find the optimal individual position according to the latest updated position;

[0077] Step 205: Set the optimal individual position as the weight and threshold of the BP crop state prediction model to obtain the target BP crop state prediction model.

[0078] The above is an introduction to an embodiment of a crop growth monitoring method based on artificial intelligence of the present invention. Figure 2 In a crop growth monitoring system based on artificial intelligence, the crop growth monitoring system includes the following modules:

[0079] A data acquisition module is used to acquire multi-source crop growth data based on sensors, transmit the multi-source crop growth data to a database using wireless communication technology, perform data preprocessing on the multi-source crop growth data, and obtain real-time crop growth data;

[0080] A model building module is used to build a pre-trained BP crop state prediction model based on a BP neural network, and optimize the parameters of the BP crop state prediction model using an SSA sparrow optimization algorithm to obtain a target BP crop state prediction model;

[0081] The state prediction module is used to input the real-time crop growth data into the target BP crop state prediction model for training to obtain the crop growth state;

[0082] A strategy generation module is used to generate an irrigation strategy and a fertilization strategy for crops according to the growth status of crops, and transmit the irrigation strategy and the fertilization strategy to the crop irrigation system and the fertilization system;

[0083] The target adjustment module is used to obtain target crop growth data of crops after irrigation and fertilization, and adjust the irrigation strategy and fertilization strategy according to the target crop growth data.

[0084] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A crop growth monitoring method based on artificial intelligence, characterized in that: The crop growth monitoring comprises the following steps: Acquire multi-source crop growth data based on sensors, transmit the multi-source crop growth data to a database using wireless communication technology, and perform data preprocessing on the multi-source crop growth data to obtain real-time crop growth data; A pre-trained BP crop state prediction model is established based on a BP neural network, and the parameters of the BP crop state prediction model are optimized using an SSA sparrow optimization algorithm to obtain a target BP crop state prediction model; Inputting the real-time crop growth data into the target BP crop state prediction model for training to obtain the crop growth state; Generate an irrigation strategy and a fertilization strategy for the crops according to the growth status of the crops, and transmit the irrigation strategy and the fertilization strategy to the crop irrigation system and the fertilization system; Obtain target crop growth data of crops after irrigation and fertilization, and adjust irrigation strategies and fertilization strategies according to the target crop growth data.

2. The method for monitoring crop growth based on artificial intelligence according to claim 1, characterized in that: The method of acquiring multi-source crop growth data based on sensors, transmitting the multi-source crop growth data to a database using wireless communication technology, and performing data preprocessing on the multi-source crop growth data to obtain real-time crop growth data includes: Sensors are arranged in the soil of crops, wherein the sensors include at least a soil moisture sensor, a soil temperature and humidity meter, a light intensity meter, a chlorophyll content sensor and a meteorological sensor; The sensor acquires crop data in the crop soil every 5 hours to obtain multi-source crop growth data; Using Zigbee wireless communication technology to transmit the multi-source crop growth data to a database; Deleting outliers in the multi-source crop growth data and supplementing missing values ​​to obtain first crop growth data; The first crop growth data is normalized to obtain real-time crop growth data.

3. The crop growth monitoring method based on artificial intelligence as claimed in claim 1, characterized in that: The method of establishing a pre-trained BP crop state prediction model based on a BP neural network and optimizing the parameters of the BP crop state prediction model using an SSA sparrow optimization algorithm to obtain a target BP crop state prediction model includes: Establish a BP crop state prediction model based on BP neural network, and input the historical crop data in the database into the model; Initialize the weights and thresholds of the BP crop state prediction model, and initialize the parameters of the SSA sparrow search algorithm; The reverse learning strategy is used to initialize the population, the sine and cosine algorithms are introduced to update the discoverer position, and the l evy flight strategy is introduced to update the follower position; According to the update results, the position of the sentinel is updated, and the optimal individual position is found according to the latest updated position; The optimal individual position is set as the weight and threshold of the BP crop state prediction model to obtain the target BP crop state prediction model.

4. The method for monitoring crop growth based on artificial intelligence according to claim 1, characterized in that: The step of inputting the real-time crop growth data into the target BP crop state prediction model for training to obtain the crop growth state includes: The target BP crop state prediction model is trained 1000 times, the learning rate is 0.01, the training target minimum error is 0.000001, and the momentum factor is 0.01; The number of input layer nodes of the target BP crop state prediction model is set to 4, the number of output layer nodes is set to 1, and the number of hidden layer nodes is set to 9; Set the number of sparrows in the sparrow search algorithm to 20, the proportion of discoverers to 0.7, the proportion of followers to 0.3, the proportion of vigilants to 0.2, and the warning value to 0.6; The real-time crop growth data is input into the target BP crop state prediction model for training to obtain the crop growth state.

5. The method for monitoring crop growth based on artificial intelligence according to claim 1, characterized in that: The method of generating an irrigation strategy and a fertilization strategy for the crops according to the growth status of the crops, and transmitting the irrigation strategy and the fertilization strategy to the crop irrigation system and the fertilization system, comprises: Based on the predicted crop growth status, irrigation and fertilization strategies are formulated using expert systems or rule engines, including irrigation water volume, fertilizer type, dosage, and time; Generate PLC control instructions for irrigation system and fertilization system based on irrigation strategy and fertilization strategy; The PLC control instructions are transmitted to the irrigation system and the fertilization system through the API interface or the Internet of Things control system, and the system irrigates and fertilizes the soil of the crops according to the PLC control instructions.

6. The method for monitoring crop growth based on artificial intelligence according to claim 1, characterized in that: The step of obtaining target crop growth data of crops after irrigation and fertilization, and adjusting the irrigation strategy and fertilization strategy according to the target crop growth data, includes: After implementing irrigation and fertilization, the growth data of crops are collected again, including growth rate, leaf color change, and soil moisture content, to obtain the growth data of target crops; The target crop growth data is input into the target BP crop state prediction model for training after data preprocessing to obtain the target crop growth state; The irrigation strategy and the fertilization strategy are adjusted according to the growth status of the target crops, and the crops are irrigated and fertilized according to the adjusted irrigation strategy and fertilization strategy.

7. A crop growth monitoring system based on artificial intelligence, characterized in that: The crop growth monitoring system includes the following modules: A data acquisition module, used to acquire multi-source crop growth data based on sensors, transmit the multi-source crop growth data to a database using wireless communication technology, and perform data preprocessing on the multi-source crop growth data to obtain real-time crop growth data; A model building module is used to build a pre-trained BP crop state prediction model based on a BP neural network, and optimize the parameters of the BP crop state prediction model using an SSA sparrow optimization algorithm to obtain a target BP crop state prediction model; A state prediction module, used for inputting the real-time crop growth data into the target BP crop state prediction model for training to obtain the crop growth state; A strategy generation module, used for generating an irrigation strategy and a fertilization strategy for the crops according to the growth status of the crops, and transmitting the irrigation strategy and the fertilization strategy to the crop irrigation system and the fertilization system; The target adjustment module is used to obtain target crop growth data of crops after irrigation and fertilization, and adjust the irrigation strategy and fertilization strategy according to the target crop growth data.

8. The crop growth monitoring system based on artificial intelligence as claimed in claim 7, characterized in that: The data acquisition module includes the following submodules: A submodule is provided, which is used to provide sensors in the soil of crops, wherein the sensors at least include a soil moisture sensor, a soil temperature and humidity meter, a light intensity meter, a chlorophyll content sensor and a meteorological sensor; The acquisition submodule is used to acquire crop data in crop soil once every 5 hours through sensors to obtain multi-source crop growth data; A transmission submodule, used for transmitting the multi-source crop growth data to a database using Zigbee wireless communication technology; A processing submodule, configured to delete abnormal values ​​in the multi-source crop growth data and supplement missing values ​​to obtain first crop growth data; The obtaining submodule is used to normalize the first crop growth data to obtain real-time crop growth data.

9. The crop growth monitoring system based on artificial intelligence as claimed in claim 7, characterized in that: The model building module includes the following submodules: Establish a submodule for establishing a BP crop state prediction model based on a BP neural network, and input the historical crop data in the database into the model; The initialization submodule is used to initialize the weights and thresholds of the BP crop state prediction model and the parameters of the SSA sparrow search algorithm; Introduce a submodule to initialize the population using the reverse learning strategy, introduce the sine and cosine algorithms to update the discoverer position, and introduce the levy flight strategy to update the follower position; The update submodule is used to update the position of the sentinel according to the update result and find the optimal individual position according to the latest updated position; A submodule is obtained, which is used to set the optimal individual position as the weight and threshold of the BP crop state prediction model to obtain the target BP crop state prediction model.

Images