Planting method for increasing corn yield based on chemical control agent regulation

Abstract

The invention discloses a planting method for improving corn yield based on chemical control agent regulation, and belongs to the technical field of corn planting, and the method comprises the following steps: S1, collecting real-time data of corn planting growth state; s2, cleaning and normalizing the real-time data of the corn planting and growing state; s3, integrating and storing the standardized real-time data of the corn planting and growing state; s4, analyzing the real-time data of the corn planting growth state, and determining a corn planting growth stage analysis result; and S5, formulating a corn planting chemical control agent application scheme, and carrying out automatic adjustment and real-time tracking on the chemical control agent according to different corn planting growth stages. The problems that in the prior art, the application condition of a chemical control agent cannot be adjusted in the corn planting process, the growth state of corn cannot be adapted, and the corn yield is low are solved. According to the method, the application condition of the chemical control agent can be adjusted in the corn planting process, the growth state of corn can be well adapted, and the corn yield can be increased.

Description

Technical Field

[0001] The present invention relates to the technical field of corn planting, and in particular to a planting method for increasing corn yield based on regulation of chemical control agents. Background Art

[0002] In agricultural production, increasing crop yields has always been one of the hot issues that farmers are concerned about. As an important food crop, corn yield is directly related to my country's food security and social stability. However, due to environmental factors, genetic variation and other reasons, crop yields may not meet expectations in some cases. Among them, the use of chemical control agents to regulate crop growth and development is a common method.

[0003] The Chinese patent with the publication number CN119302193A discloses a rotation planting method of fresh glutinous corn for use in the northeast region, including two modes of planting one ridge and two ridges with empty space and single row planting or planting one ridge and three ridges with empty space and double row planting; planting one ridge and two ridges with empty space and single row planting, and planting one ridge and three ridges with empty space and double row planting, and planting two rows in each ridge; when the first crop of corn is about to ear, planting in a single row on the second crop planting ridge, after the first crop of corn is harvested 80-90 days after planting, the corn stalks are crushed and laid down, and then the first crop of corn planting area is sorted out and transplanted to other economic crops; fully utilizing land resources, increasing planting density, while ensuring that the planted corn ridges are at the edge of the field and every corn is in the side row; combined with integrated water and fertilizer drip irrigation management, the planting amount is 180%-350% higher than the existing planting method; however, the patent has the following defects: The existing technology cannot adjust the application of chemical control agents during corn planting, resulting in an inability to adapt to the growth state of corn and low corn yield. Summary of the invention

[0004] The purpose of the present invention is to provide a planting method for increasing corn yield based on chemical control agent regulation, which can adjust the application of chemical control agents during the corn planting process, can better adapt to the growth state of corn, can increase corn yield, and solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: The planting method for increasing corn yield based on chemical control agent regulation includes the following steps: S1: Collect plant type, physiological and biochemical, soil, environmental and stress resistance data during corn planting, and determine the real-time data of corn planting and growth status based on the Internet of Things; S2: Clean and normalize the real-time data of corn planting and growth status based on the Internet of Things to determine standardized real-time data of corn planting and growth status; S3: Integrate and store the standardized real-time data of corn planting and growth status, so that the real-time data of corn planting and growth status can be stored and backed up; S4: Analyze the real-time data of corn planting and growth status, determine the corn planting and growth stage, and determine the analysis results of the corn planting and growth stage; S5: Develop a plan for applying chemical control agents to corn planting, and automatically adjust and track the chemical control agents in real time according to different corn planting growth stages.

[0006] Preferably, in S1, determining the real-time data of corn planting growth status based on the Internet of Things includes: Based on intelligent data collection equipment, the height, leaf shape, leaf size and leaf color of corn plants are monitored and collected in real time during corn planting to determine the corn planting plant type data; Based on intelligent collection equipment, real-time monitoring and collection of cell activity, enzyme activity and hormone content during corn planting process are carried out to determine the physiological and biochemical data of corn planting; Based on intelligent collection equipment, the soil pH, organic matter content and mineral nutrition during corn planting are monitored and collected in real time to determine the soil data for corn planting; Based on intelligent data collection equipment, the temperature, humidity, light intensity, wind speed and precipitation in the corn planting process are monitored and collected in real time to determine the corn planting environment data; Based on intelligent data collection equipment, real-time monitoring and collection of corn's resistance to pests and diseases, lodging resistance, and drought resistance during planting are carried out to determine corn planting stress resistance data; Among them, based on corn planting plant type data, corn planting physiological and biochemical data, corn planting soil data, corn planting environment data and corn planting stress resistance data, the real-time data of corn planting growth status based on the Internet of Things is determined.

[0007] Preferably, in S2, the real-time data of corn planting and growth status based on the Internet of Things is cleaned and normalized, including: Clean the real-time data of corn planting and growth status based on the Internet of Things based on data cleaning tools, and remove duplicate values, missing values ​​and abnormal values ​​that are useless for improving corn yield in the real-time data of corn planting and growth status based on the Internet of Things; Based on the Z-score standardization, the real-time data of corn planting growth status based on the Internet of Things is normalized, the dimensional differences between the real-time data of corn planting growth status based on the Internet of Things are removed, and the standardized real-time data of corn planting growth status is determined.

[0008] Preferably, in S3, the standardized real-time data of corn planting growth status is integrated and stored, including: Based on the ETL tool, the standardized real-time data of corn planting and growth status are integrated, and the standardized real-time data of corn planting and growth status from different sources are integrated into a unified data view to form the real-time data of corn planting and growth status in a unified data view; Verify the real-time data on the corn planting and growth status of the unified data view, compare and analyze the real-time data on the corn planting and growth status of the unified data view with the standardized real-time data on the corn planting and growth status before integration, check whether there are omissions in the real-time data on the corn planting and growth status of the unified data view, and after the data verification is qualified, store and back up the real-time data on the corn planting and growth status of the unified data view.

[0009] Preferably, in S4, analyzing the real-time data of corn planting growth status includes: According to the planting demand for increasing corn yield based on chemical control agent regulation, standard data on corn planting and growth status are pre-set to provide a reference basis for real-time data analysis of corn planting and growth status; Based on the standard data of corn planting and growth status, the real-time data of corn planting and growth status is analyzed to judge the corn planting and growth stage and determine the analysis results of the corn planting and growth stage.

[0010] Preferably, in S4, determining the corn planting growth stage includes: Compare and analyze the real-time data of corn planting growth status with the standard data of corn planting growth status one by one, wherein the standard data of corn planting growth status includes standard data of corn planting seedling stage, standard data of corn planting vegetative growth stage, standard data of corn planting reproductive growth stage, standard data of corn planting flowering and pollination stage, and standard data of corn planting filling and fruiting stage; When the real-time data of corn planting growth status is within the standard data range of corn planting seedling stage, the corn planting growth stage analysis result is that corn planting is in the seedling stage; When the real-time data of corn planting growth status is within the standard data range of corn planting vegetative growth stage, the corn planting growth stage analysis result is that corn planting is in the vegetative growth stage; When the real-time data of corn planting growth status is within the standard data range of corn planting reproductive growth stage, the corn planting growth stage analysis result is that corn planting is in the reproductive growth stage; When the real-time data of corn planting growth status is within the standard data range of corn planting flowering and pollination stage, the corn planting growth stage analysis result is that corn planting is in the flowering and pollination stage; When the real-time data of corn planting growth status is within the standard data range of the corn planting grain filling and fruiting stage, the corn planting growth stage analysis result is that the corn planting is in the grain filling and fruiting stage.

[0011] Preferably, in S5, formulating a plan for applying chemical control agents for corn planting includes: Obtain the analysis results of corn planting growth stages, analyze the real-time data of corn planting growth status based on the analysis results of corn planting growth stages, formulate a plan for applying chemical control agents for corn planting, and automatically adjust the chemical control agents according to different corn planting growth stages to increase corn yield; Among them, the application scheme of chemical control agents for corn planting includes: According to different corn planting and growth stages, different types, dosages and concentrations of chemical control agents are applied to meet the growth and development needs of different corn planting and growth stages; According to the environment and soil conditions at different corn planting and growth stages, different days and times for applying chemical control agents are formulated to achieve the best effect of chemical control agents; According to the planting density at different corn growth stages, choose different methods of applying chemical control agents, including spraying and root irrigation.

[0012] Preferably, in S5, real-time tracking of chemical control agents according to different corn planting growth stages includes: After applying chemical control agents during the corn planting process, the corn growth is tracked in real time, and the corn growth feedback after the application of chemical control agents is obtained in time. The applied chemical control agents are adjusted in time according to the corn growth feedback, and the adjustment situation is recorded in real time.

[0013] Preferably, in S5, analyzing the real-time data of corn planting growth status includes: The reflectance spectrum data of corn leaves in different bands collected by a multispectral camera; Collect corn leaf samples at different growth stages and different fertilization levels, conduct chemical analysis, and determine the actual nitrogen content of the corn leaf samples as training data; Extracting spectral features related to nitrogen content from reflectance spectral data; A neural network machine learning algorithm was used to establish the mapping relationship between spectral features and the nitrogen content of corn leaves, and a prediction model for the nitrogen content of corn leaves was obtained through training. At the corn planting site, a multispectral camera is used to detect corn leaves in real time to obtain real-time corn leaf spectral data; The real-time corn leaf spectral data obtained by the detection is input into the trained nitrogen content prediction model, and the nitrogen content of the corn leaf at that time is obtained by prediction output; Generate and provide a corn fertilization plan based on the predicted output of corn leaf nitrogen content, combined with the corresponding fertility requirements and soil fertility conditions of the corn growth stage; After the corn fertilization plan is implemented, after the preset absorption time, the implementation effect is evaluated and fed back based on the multi-spectral camera detection combined with the nitrogen content prediction model prediction results. The model parameters of the nitrogen content prediction model are adjusted according to the changes in the actual nitrogen content of the corn leaves.

[0014] Preferably, the planting method further comprises: Regularly collect status images of corn plants through drones or smart cameras, and pre-process the status images, including denoising and enhancement processing; The preprocessed state image is normalized using the following formula: ; in, is the normalized state image parameter, is the state image parameter after preprocessing, is the parameter mean of the state image, is the standard deviation of the state image parameters; Construct a convolutional neural network (CNN) model for identifying corn pests and diseases and growth status. The structure of the convolutional neural network model includes convolutional layers, pooling layers, and fully connected layers. The convolutional layer calculates the output data using the following formula: ; in, Output position for the convolutional layer The output data, is the weight of the convolution kernel, is the position of the convolution kernel, Input data for convolution, that is The regional image of the position, b is the bias parameter; The normalized state image is input into the convolutional neural network model. Based on the growth state contained in the recognition result of the normalized state image by the convolutional neural network model and the chemical control agent application effect data in the application effect database, an accurate application plan for chemical control agents is formulated; according to the type and severity of the pests and diseases, the type, dosage and application method of the chemical control agents are automatically adjusted.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention determines the real-time data of corn planting growth status based on the Internet of Things by collecting plant type, physiological and biochemical, soil, environmental and stress resistance data in the corn planting process, determines the standardized real-time data of corn planting growth status by cleaning and normalizing the real-time data of corn planting growth status based on the Internet of Things, integrates and stores the standardized real-time data of corn planting growth status, stores and backs up the real-time data of corn planting growth status, analyzes the real-time data of corn planting growth status, judges the corn planting growth stage, determines the analysis result of the corn planting growth stage, formulates the application plan of chemical control agents for corn planting, automatically adjusts and tracks the chemical control agents in real time according to different corn planting growth stages, can adjust the application of chemical control agents during corn planting, can better adapt to the growth state of corn, and can increase corn yield. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The present invention is a flow chart of a planting method for increasing corn yield based on chemical control agent regulation. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] In order to solve the existing problem that the application of chemical control agents cannot be adjusted during corn planting, resulting in poor adaptation to the growth state of corn and low corn yield, please refer to Figure 1 , this embodiment provides the following technical solutions: The planting method for increasing corn yield based on chemical control agent regulation includes the following steps: S1: Collect plant type, physiological and biochemical, soil, environmental and stress resistance data during corn planting, and determine the real-time data of corn planting and growth status based on the Internet of Things; In this embodiment, determining the real-time data of corn planting growth status based on the Internet of Things includes: Based on intelligent data collection equipment, the height, leaf shape, leaf size and leaf color of corn plants are monitored and collected in real time during corn planting to determine the corn planting plant type data; It should be noted that the plant height, leaf shape, leaf size and leaf color will affect the efficiency of photosynthesis, and thus affect the photosynthetic rate and total biomass accumulation of corn.

[0019] Based on intelligent collection equipment, real-time monitoring and collection of cell activity, enzyme activity and hormone content during corn planting process are carried out to determine the physiological and biochemical data of corn planting; It should be noted that cell activity, enzyme activity and hormone content can reflect the health of corn growth.

[0020] Based on intelligent collection equipment, the soil pH, organic matter content and mineral nutrition during corn planting are monitored and collected in real time to determine the soil data for corn planting; It should be noted that soil pH, organic matter content and mineral nutrition will affect the development and function of the root system, and thus affect the growth of corn.

[0021] Based on intelligent data collection equipment, the temperature, humidity, light intensity, wind speed and precipitation in the corn planting process are monitored and collected in real time to determine the corn planting environment data; It should be noted that temperature, humidity, light intensity, wind speed and precipitation will have an important impact on the growth of corn.

[0022] Based on intelligent data collection equipment, real-time monitoring and collection of corn's resistance to pests and diseases, lodging resistance, and drought resistance during planting are carried out to determine corn planting stress resistance data; It should be noted that disease and pest resistance, lodging resistance and drought resistance will be affected by plant morphology and physiological and biochemical indicators.

[0023] Among them, based on corn planting plant type data, corn planting physiological and biochemical data, corn planting soil data, corn planting environment data and corn planting stress resistance data, the real-time data of corn planting growth status based on the Internet of Things is determined.

[0024] S2: Clean and normalize the real-time data of corn planting and growth status based on the Internet of Things to determine standardized real-time data of corn planting and growth status; In this embodiment, the real-time data of corn planting growth status based on the Internet of Things is cleaned and normalized, including: Clean the real-time data of corn planting and growth status based on the Internet of Things based on data cleaning tools, and remove duplicate values, missing values ​​and abnormal values ​​that are useless for improving corn yield in the real-time data of corn planting and growth status based on the Internet of Things; Based on the Z-score standardization, the real-time data of corn planting growth status based on the Internet of Things is normalized, the dimensional differences between the real-time data of corn planting growth status based on the Internet of Things are removed, and the standardized real-time data of corn planting growth status is determined.

[0025] S3: Integrate and store the standardized real-time data of corn planting and growth status, so that the real-time data of corn planting and growth status can be stored and backed up; In this embodiment, standardized real-time data of corn planting growth status is integrated and stored, including: Based on the ETL tool, the standardized real-time data of corn planting and growth status are integrated, and the standardized real-time data of corn planting and growth status from different sources are integrated into a unified data view to form the real-time data of corn planting and growth status in a unified data view; Verify the real-time data on the corn planting and growth status of the unified data view, compare and analyze the real-time data on the corn planting and growth status of the unified data view with the standardized real-time data on the corn planting and growth status before integration, check whether there are omissions in the real-time data on the corn planting and growth status of the unified data view, and after the data verification is qualified, store and back up the real-time data on the corn planting and growth status of the unified data view.

[0026] S4: Analyze the real-time data of corn planting and growth status, determine the corn planting and growth stage, and determine the analysis results of the corn planting and growth stage; In this embodiment, the real-time data of corn planting and growth status is analyzed, including: According to the planting demand for increasing corn yield based on chemical control agent regulation, standard data on corn planting and growth status are pre-set to provide a reference basis for real-time data analysis of corn planting and growth status; Based on the standard data of corn planting and growth status, the real-time data of corn planting and growth status is analyzed to judge the corn planting and growth stage and determine the analysis results of the corn planting and growth stage.

[0027] In this embodiment, determining the corn planting growth stage includes: Compare and analyze the real-time data of corn planting growth status with the standard data of corn planting growth status one by one, wherein the standard data of corn planting growth status includes standard data of corn planting seedling stage, standard data of corn planting vegetative growth stage, standard data of corn planting reproductive growth stage, standard data of corn planting flowering and pollination stage, and standard data of corn planting filling and fruiting stage; When the real-time data of corn planting growth status is within the standard data range of corn planting seedling stage, the corn planting growth stage analysis result is that corn planting is in the seedling stage; It should be noted that sufficient sunlight, water and nutrition supply need to be ensured in the seedling stage to promote the normal growth and development of corn seedlings. Therefore, it is particularly important to apply chemical control agents and adjust them in the seedling stage.

[0028] When the real-time data of corn planting growth status is within the standard data range of corn planting vegetative growth stage, the corn planting growth stage analysis result is that corn planting is in the vegetative growth stage; It should be noted that the main characteristics of the vegetative growth stage are accelerated vegetative growth rate and rapid growth of plant height. Corn at this stage requires sufficient water, nutrient ions, good aeration and appropriate environmental conditions. Therefore, it is particularly important to apply chemical control agents and adjust them during the vegetative growth stage.

[0029] When the real-time data of corn planting growth status is within the standard data range of corn planting reproductive growth stage, the corn planting growth stage analysis result is that corn planting is in the reproductive growth stage; It should be noted that the reproductive growth stage is a critical period for the formation of corn ears and seeds. It requires maintaining high light intensity, sufficient water, adequate nutrient supply, moderate fertilizer supply, and good ventilation and humidity conditions. Therefore, it is particularly important to apply chemical control agents and adjust them during the reproductive growth stage.

[0030] When the real-time data of corn planting growth status is within the standard data range of corn planting flowering and pollination stage, the corn planting growth stage analysis result is that corn planting is in the flowering and pollination stage; It should be noted that the main characteristics of the flowering and pollination stage are that the inflorescence begins to open, the filaments and anthers gradually elongate, the pollen tube begins to grow, and the stamens and pistils begin to secrete pollen. It is necessary to maintain sufficient water and sufficient nutrient supply. Therefore, it is particularly important to apply chemical control agents and adjust the chemical control agents during the flowering and pollination stage.

[0031] When the real-time data of corn planting growth status is within the standard data range of the corn planting grain filling and fruiting stage, the corn planting growth stage analysis result is that the corn planting is in the grain filling and fruiting stage.

[0032] It should be noted that the grain filling stage is mainly the grain filling process, which requires sufficient water and nutrient supply. Therefore, it is particularly important to apply and adjust chemical control agents during the grain filling stage.

[0033] S5: Develop a plan for applying chemical control agents to corn planting, and automatically adjust and track the chemical control agents in real time according to different corn planting growth stages.

[0034] In this embodiment, a corn planting chemical control agent application plan is formulated, including: Obtain the analysis results of corn planting growth stages, analyze the real-time data of corn planting growth status based on the analysis results of corn planting growth stages, formulate a plan for applying chemical control agents for corn planting, and automatically adjust the chemical control agents according to different corn planting growth stages to increase corn yield; Among them, the application scheme of chemical control agents for corn planting includes: According to different corn planting and growth stages, different types, dosages and concentrations of chemical control agents are applied to meet the growth and development needs of different corn planting and growth stages; According to the environment and soil conditions at different corn planting and growth stages, different days and times for applying chemical control agents are formulated to achieve the best effect of chemical control agents; According to the planting density at different corn growth stages, choose different chemical control agent application methods, including spraying and root irrigation, to improve the absorption and utilization efficiency of corn.

[0035] In this embodiment, the chemical control agent is tracked in real time according to different corn planting growth stages, including: After applying chemical control agents during the corn planting process, the corn growth is tracked in real time, and the corn growth feedback after the application of chemical control agents is obtained in time. The applied chemical control agents are adjusted in time according to the corn growth feedback, and the adjustment situation is recorded in real time.

[0036] Based on the above embodiment, in S5, the real-time data of corn planting growth status is analyzed, including: The reflectance spectrum data of corn leaves in different bands collected by a multispectral camera; Collect corn leaf samples at different growth stages and different fertilization levels, conduct chemical analysis, and determine the actual nitrogen content of the corn leaf samples as training data; Extracting spectral features related to nitrogen content from reflectance spectral data; A neural network machine learning algorithm was used to establish the mapping relationship between spectral features and the nitrogen content of corn leaves, and a prediction model for the nitrogen content of corn leaves was obtained through training. At the corn planting site, a multispectral camera is used to detect corn leaves in real time to obtain real-time corn leaf spectral data; The real-time corn leaf spectral data obtained by the detection is input into the trained nitrogen content prediction model, and the nitrogen content of the corn leaf at that time is obtained by prediction output; Generate and provide a corn fertilization plan based on the predicted output of corn leaf nitrogen content, combined with the corresponding fertility requirements and soil fertility conditions of the corn growth stage; After the corn fertilization plan is implemented, after the preset absorption time, the implementation effect is evaluated and fed back based on the multi-spectral camera detection combined with the nitrogen content prediction model prediction results. The model parameters of the nitrogen content prediction model are adjusted according to the changes in the actual nitrogen content of the corn leaves.

[0037] In this embodiment, the reflectance spectrum data obtained by multi-spectral detection is combined with the actual nitrogen content of the corn leaf samples obtained synchronously to construct and train a prediction model for the nitrogen content of the corn leaves; on this basis, the real-time corn leaf spectrum data detected in real time at the corn planting site is used as the input data of the nitrogen content prediction model, and the nitrogen content predicted for the corn leaves at that time is obtained by performing calculation processing, and then the fertility demand and soil fertility status corresponding to the corn growth stage are combined. The fertility demand of the corn at the growth stage is fine-tuned by the nitrogen content, and the fertility demand after fine-tuning is compared with the soil fertility status. If the soil fertility status does not meet the fertility demand of the fine-tuned corn, the fertility deviation value of the two is calculated, and the fertility deviation value is used as the main content of the corn fertilization plan. After fertilization is implemented according to the plan, the absorption time determined by the absorption characteristics of the corn is considered, and the corn growth state is tracked, and whether additional fertilization is needed is determined according to the tracking situation; in addition, the accuracy of the nitrogen content predicted by the corn leaves can be reflected to a certain extent according to the tracking situation, and the model parameters of the nitrogen content prediction model are adjusted accordingly, so that the nitrogen content prediction model is continuously learned and improved, and the tracking accuracy of the nitrogen content of corn growth is further improved.

[0038] Based on the above embodiment, the planting method further includes: Regularly collect status images of corn plants through drones or smart cameras, and pre-process the status images, including denoising and enhancement processing; The preprocessed state image is normalized using the following formula: ; in, is the normalized state image parameter, is the state image parameter after preprocessing, is the parameter mean of the state image, is the standard deviation of the state image parameters; Construct a convolutional neural network (CNN) model for identifying corn pests and diseases and growth status. The structure of the convolutional neural network model includes convolutional layers, pooling layers, and fully connected layers. The convolutional layer calculates the output data using the following formula: ; in, Output position for the convolutional layer The output data, is the weight of the convolution kernel, is the position of the convolution kernel, Input data for convolution, that is The regional image of the position, b is the bias parameter; The normalized state image is input into the convolutional neural network model. Based on the growth state contained in the recognition result of the normalized state image by the convolutional neural network model and the chemical control agent application effect data in the application effect database, an accurate application plan for chemical control agents is formulated; according to the type and severity of the pests and diseases, the type, dosage and application method of the chemical control agents are automatically adjusted.

[0039] In this embodiment, the state images of corn plants are taken regularly, and after preprocessing and normalization, the convolutional neural network (CNN) model for identifying corn pests and diseases and growth status is used to identify corn pests and diseases and growth status. The identified growth status is combined with the chemical control agent application effect data in the application effect database to determine the demand for chemical control agents and formulate a precise application plan for chemical control agents; in addition, the type, dosage and application method of chemical control agents are automatically adjusted according to the type and severity of the identified pests and diseases. The convolutional neural network model of this solution uses a deep learning algorithm, and the convolution layer uses an algorithm formula to quickly realize data processing and output, which can realize rapid and accurate identification of pests and diseases, and issue early warnings in a timely manner, providing strong support for timely prevention and control measures, helping to reduce the impact of pests and diseases on corn yield and quality, and ensuring the economic benefits of corn planting.

[0040] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0041] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A planting method for increasing corn yield based on chemical control agent regulation, characterized in that: The steps include: S1: Collect plant type, physiological and biochemical, soil, environmental and stress resistance data during corn planting, and determine the real-time data of corn planting and growth status based on the Internet of Things; S2: Clean and normalize the real-time data of corn planting and growth status based on the Internet of Things to determine standardized real-time data of corn planting and growth status; S3: Integrate and store the standardized real-time data of corn planting and growth status, so that the real-time data of corn planting and growth status can be stored and backed up; S4: Analyze the real-time data of corn planting and growth status, determine the corn planting and growth stage, and determine the analysis results of the corn planting and growth stage; S5: Develop a plan for applying chemical control agents to corn planting, and automatically adjust and track the chemical control agents in real time according to different corn planting growth stages.

2. The planting method for increasing corn yield based on chemical control agent regulation according to claim 1, characterized in that: In S1, determining the real-time data of corn planting growth status based on the Internet of Things includes: Based on intelligent data collection equipment, the height, leaf shape, leaf size and leaf color of corn plants are monitored and collected in real time during corn planting to determine the corn planting plant type data; Based on intelligent collection equipment, real-time monitoring and collection of cell activity, enzyme activity and hormone content during corn planting process are carried out to determine the physiological and biochemical data of corn planting; Based on intelligent collection equipment, the soil pH, organic matter content and mineral nutrition during corn planting are monitored and collected in real time to determine the soil data for corn planting; Based on intelligent data collection equipment, the temperature, humidity, light intensity, wind speed and precipitation in the corn planting process are monitored and collected in real time to determine the corn planting environment data; Based on intelligent data collection equipment, real-time monitoring and collection of corn's resistance to pests and diseases, lodging resistance, and drought resistance during planting are carried out to determine corn planting stress resistance data; Among them, based on corn planting plant type data, corn planting physiological and biochemical data, corn planting soil data, corn planting environment data and corn planting stress resistance data, the real-time data of corn planting growth status based on the Internet of Things is determined.

3. The planting method for increasing corn yield based on chemical control agent regulation according to claim 2, characterized in that: In S2, the real-time data of corn planting and growth status based on the Internet of Things is cleaned and normalized, including: Clean the real-time data of corn planting and growth status based on the Internet of Things based on data cleaning tools, and remove duplicate values, missing values ​​and abnormal values ​​that are useless for improving corn yield in the real-time data of corn planting and growth status based on the Internet of Things; Based on the Z-score standardization, the real-time data of corn planting growth status based on the Internet of Things is normalized, the dimensional differences between the real-time data of corn planting growth status based on the Internet of Things are removed, and the standardized real-time data of corn planting growth status is determined.

4. The planting method for increasing corn yield based on chemical control agent regulation according to claim 3, characterized in that: In the S3, standardized real-time data of corn planting and growth status are integrated and stored, including: Based on the ETL tool, the standardized real-time data of corn planting and growth status are integrated, and the standardized real-time data of corn planting and growth status from different sources are integrated into a unified data view to form the real-time data of corn planting and growth status in a unified data view; Verify the real-time data on the corn planting and growth status of the unified data view, compare and analyze the real-time data on the corn planting and growth status of the unified data view with the standardized real-time data on the corn planting and growth status before integration, check whether there are omissions in the real-time data on the corn planting and growth status of the unified data view, and after the data verification is qualified, store and back up the real-time data on the corn planting and growth status of the unified data view.

5. The planting method for increasing corn yield based on chemical control agent regulation according to claim 4, characterized in that: In S4, the real-time data of corn planting and growth status is analyzed, including: According to the planting demand for increasing corn yield based on chemical control agent regulation, standard data on corn planting and growth status are pre-set to provide a reference basis for real-time data analysis of corn planting and growth status; Based on the standard data of corn planting and growth status, the real-time data of corn planting and growth status is analyzed to judge the corn planting and growth stage and determine the analysis results of the corn planting and growth stage.

6. The planting method for increasing corn yield based on chemical control agent regulation according to claim 5, characterized in that: In S4, determining the corn planting growth stage includes: Compare and analyze the real-time data of corn planting growth status with the standard data of corn planting growth status one by one, wherein the standard data of corn planting growth status includes standard data of corn planting seedling stage, standard data of corn planting vegetative growth stage, standard data of corn planting reproductive growth stage, standard data of corn planting flowering and pollination stage, and standard data of corn planting filling and fruiting stage; When the real-time data of corn planting growth status is within the standard data range of corn planting seedling stage, the corn planting growth stage analysis result is that corn planting is in the seedling stage; When the real-time data of corn planting growth status is within the standard data range of corn planting vegetative growth stage, the corn planting growth stage analysis result is that corn planting is in the vegetative growth stage; When the real-time data of corn planting growth status is within the standard data range of corn planting reproductive growth stage, the corn planting growth stage analysis result is that corn planting is in the reproductive growth stage; When the real-time data of corn planting growth status is within the standard data range of corn planting flowering and pollination stage, the corn planting growth stage analysis result is that corn planting is in the flowering and pollination stage; When the real-time data of corn planting growth status is within the standard data range of the corn planting grain filling and fruiting stage, the corn planting growth stage analysis result is that the corn planting is in the grain filling and fruiting stage.

7. The planting method for increasing corn yield based on chemical control agent regulation according to claim 6, characterized in that: In S5, a plan for applying chemical control agents for corn planting is formulated, including: Obtain the analysis results of corn planting growth stages, analyze the real-time data of corn planting growth status based on the analysis results of corn planting growth stages, formulate a plan for applying chemical control agents for corn planting, and automatically adjust the chemical control agents according to different corn planting growth stages to increase corn yield; Among them, the application scheme of chemical control agents for corn planting includes: According to different corn planting and growth stages, different types, dosages and concentrations of chemical control agents are applied to meet the growth and development needs of different corn planting and growth stages; According to the environment and soil conditions at different corn planting and growth stages, different days and times for applying chemical control agents are formulated to achieve the best effect of chemical control agents; According to the planting density at different corn growth stages, choose different methods of applying chemical control agents, including spraying and root irrigation.

8. The planting method for increasing corn yield based on chemical control agent regulation according to claim 7, characterized in that: In S5, the chemical control agent is tracked in real time according to different corn planting growth stages, including: After applying chemical control agents during the corn planting process, the corn growth is tracked in real time, and the corn growth feedback after the application of chemical control agents is obtained in time. The applied chemical control agents are adjusted in time according to the corn growth feedback, and the adjustment situation is recorded in real time.

9. The planting method for increasing corn yield based on chemical control agent regulation according to claim 7, characterized in that: In S5, the real-time data of corn planting and growth status is analyzed, including: The reflectance spectrum data of corn leaves in different bands collected by a multispectral camera; Collect corn leaf samples at different growth stages and different fertilization levels, conduct chemical analysis, and determine the actual nitrogen content of the corn leaf samples as training data; Extracting spectral features related to nitrogen content from reflectance spectral data; A neural network machine learning algorithm was used to establish the mapping relationship between spectral features and the nitrogen content of corn leaves, and a prediction model for the nitrogen content of corn leaves was obtained through training. At the corn planting site, a multispectral camera is used to detect corn leaves in real time to obtain real-time corn leaf spectral data; The real-time corn leaf spectral data obtained by the detection is input into the trained nitrogen content prediction model, and the nitrogen content of the corn leaf at that time is obtained by prediction output; Generate and provide a corn fertilization plan based on the predicted output of corn leaf nitrogen content, combined with the corresponding fertility requirements and soil fertility conditions of the corn growth stage; After the corn fertilization plan is implemented, after the preset absorption time, the implementation effect is evaluated and fed back based on the multi-spectral camera detection combined with the nitrogen content prediction model prediction results. The model parameters of the nitrogen content prediction model are adjusted according to the changes in the actual nitrogen content of the corn leaves.

10. The planting method for increasing corn yield based on chemical control agent regulation according to any one of claims 1 to 9, characterized in that: Also includes: Regularly collect status images of corn plants through drones or smart cameras, and pre-process the status images, including denoising and enhancement processing; The preprocessed state image is normalized using the following formula: ； in, is the normalized state image parameter, is the state image parameter after preprocessing, is the parameter mean of the state image, is the standard deviation of the state image parameters; Construct a convolutional neural network (CNN) model for identifying corn pests and diseases and growth status. The structure of the convolutional neural network model includes convolutional layers, pooling layers, and fully connected layers. The convolutional layer calculates the output data using the following formula: ； in, Output position for the convolutional layer The output data, is the weight of the convolution kernel, is the position of the convolution kernel, Input data for convolution, that is The regional image of the position, b is the bias parameter; The normalized state image is input into the convolutional neural network model. Based on the growth state contained in the recognition result of the normalized state image by the convolutional neural network model and the chemical control agent application effect data in the application effect database, an accurate application plan for chemical control agents is formulated; according to the type and severity of the pests and diseases, the type, dosage and application method of the chemical control agents are automatically adjusted.

Images