Rice planting equipment with high enzyme activity and planting method thereof

Abstract

The invention relates to the technical field of high-enzyme-activity rice planting data processing, and provides high-enzyme-activity rice planting equipment and a planting method thereof.The high-enzyme-activity rice planting equipment integrates a sensor network, a control device, a data acquisition terminal and an enzyme activity detection device, soil and environment parameters are acquired in real time, and the data of the soil and the environment are acquired; a planting strategy is optimized by using a data analysis algorithm, and the rice planting equipment with high enzyme activity can dynamically adjust the fertilization amount, the irrigation frequency and the planting density according to the rice growth condition, so that accurate management is realized. Seeding and fertilization are iteratively optimized through a genetic algorithm, so that the rice growth is close to expectation. Partition management and enzyme activity detection realize precise fertilization, optimize soil enzyme activity, improve rice yield and quality, reduce resource waste and environmental pollution, and effectively improve rice planting efficiency and benefits.

Description

Technical Field

[0001] The invention relates to the technical field of rice planting data processing with high enzyme activity, and in particular to rice planting equipment with high enzyme activity and a planting method thereof. Background Art

[0002] The enzyme activity inside rice seeds has a direct impact on germination rate and growth health. For example, by sunning seeds and soaking seeds with chemicals, the respiration of seeds and the activity of enzymes can be improved, thereby improving the germination rate and germination potential. In addition, compound biological enzymes, as a naturally occurring substance, are widely used in rice cultivation. High enzyme activity can activate microbial activity in the soil, improve the soil microecological environment, enhance rice disease resistance, promote root development, and improve nutrient absorption and utilization efficiency, thereby significantly improving rice yield and quality. Therefore, in rice cultivation, maintaining and enhancing enzyme activity is one of the key measures to increase yield.

[0003] When processing data, rice planting equipment with high enzyme activity collects environmental parameters such as soil moisture, temperature, pH value, and enzyme activity in real time through an integrated sensor network, and the data is transmitted to the central processor in real time. Using advanced bioinformatics and data analysis algorithms, through machine learning models such as neural networks or support vector machines, the complex relationship between enzyme activity and rice growth conditions is analyzed to identify the optimal enzyme activity range and corresponding planting strategies. Finally, based on the analysis results, the equipment automatically adjusts the parameters of fertilizer application, irrigation frequency, and planting density to achieve precision agricultural management to maximize rice yield and quality while reducing resource waste and environmental pollution.

[0004] Rice planting equipment with high enzyme activity has the following technical pain points when processing data. The existing rice planting cannot dynamically adjust the sowing method and fertilization, which results in the inability to maximize the release of enzyme activity in the soil, causing the rice planting yield to fail to meet expectations. Summary of the invention

[0005] In view of the shortcomings of the existing technology, the present invention provides a rice planting equipment with high enzyme activity and a planting method thereof, which solves the problem that the existing rice planting cannot dynamically adjust the sowing method and fertilization, thereby resulting in the inability to maximize the release of the enzyme activity in the soil, causing the rice planting yield to fail to reach the expected level.

[0006] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows: In a first aspect, the present invention provides a rice planting device with high enzyme activity, comprising: a control device, a data acquisition terminal, an enzyme activity detection device, an inspection device, a fertilization device, a sowing device and a data acquisition terminal, wherein the control device establishes communication connections with the inspection device, the enzyme activity detection device, the fertilization device, the sowing device and the fertilization device respectively, and the control device receives data collected by the data acquisition terminal and the enzyme activity detection device, and the control device outputs a rice planting control command according to the data collected by the data acquisition terminal, and sends the rice planting control command to the inspection device, the fertilization device, the sowing device and the fertilization device, and the control device comprises: A data acquisition module is used to acquire soil parameter data, soil enzyme activity history data, enzyme activity data, environmental parameters, rice growth data, fertilizer use history data and rice planting equipment control model; A dynamic monitoring module is used to receive rice planting tasks, the rice planting tasks include rice planting location data, expected rice planting yield, rice fertilization standards and expected rice planting time information, substitute the rice planting tasks into a preset rice planting equipment control model, and obtain expected rice planting control commands, the expected rice planting control commands include expected rice seed quantity, expected rice fertilizer amount, expected rice growth data, expected rice fertilization data, expected rice sowing tasks, expected rice fertilization tasks and expected rice inspection tasks; A model optimization module is used to load rice seeds in a sowing device according to an expected number of rice seeds, load fertilizers in a fertilizing device according to an expected amount of rice fertilizer, send an expected rice inspection task to the inspection device, receive inspection data collected by the inspection device after the sowing device performs the expected rice sowing task and the fertilizing device performs the expected rice fertilizing task, obtain real-time inspection data, compare the real-time inspection data with the expected rice growth data, obtain rice growth error data, if the rice growth error data exceeds a preset rice growth error range value, compare the expected rice fertilization data with the historical data of the fertilizing device, if the comparison results of the expected rice fertilization data and the historical data of the fertilizing device are consistent, the rice fertilization is normal, obtain the historical data of the sowing device, use the rice growth error data, the expected rice growth data and the historical data of the sowing device to optimize the rice planting equipment control model using a genetic algorithm, and obtain an optimized rice planting equipment control model; The rice planting monitoring module is used to collect the real-time regional data of rice planting, group the real-time regional data of rice planting, obtain the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area, establish an inspection task for the first rice planting area, obtain the rice planting task, substitute the rice planting task into the optimized rice planting equipment control model, and output the optimized expected rice growth data; The rice fertilization optimization module is used to transmit the inspection tasks of the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area to the inspection device, obtain the enzyme activity data of the partition to be processed, substitute the enzyme activity data of the partition to be processed into the preset enzyme activity adjustment model, and output the real-time fertilization adjustment amount.

[0007] Furthermore, in the rice planting equipment with high enzyme activity of the present invention, the model optimization module is also used for: Collating rice growth error data, which includes the difference between the actual observed rice growth and the expected rice growth data; Expected rice growth data, used to reflect the growth state that rice should achieve based on the preliminary prediction of the rice planting task and the rice planting equipment control model; Obtaining historical data of the sowing device, including historical sowing records, seed quality, sowing time, etc. The historical data of the sowing device is used to analyze the impact of the sowing process on rice growth; Receive and set the optimization goal, and set the optimization goal to minimize the rice growth error, even if the actual rice growth data is close to the expected rice growth data, and use the sowing density and seed variety as adjustment parameters in the optimization process; Designing a chromosome structure of a genetic algorithm, each chromosome represents a set of sowing parameter combinations, the sowing parameter combinations include sowing density, seed variety, sowing frequency of a sowing device, and sowing speed of a sowing device; Define the fitness function for evaluating each set of sowing parameters based on the rice growth error data, that is, the quality of each chromosome. The higher the fitness, the closer the rice growth under this set of sowing parameters is to the expectation. Set and configure the parameters of the genetic algorithm, including population size, number of iterations, crossover probability, and mutation probability; Initialize the population and generate a set of random seeding parameter combinations as the initial solution; Calculate the fitness value of each chromosome in the current population; According to the fitness value, excellent chromosomes are selected for reproduction and crossover to generate new chromosome offspring; Perform mutation operations on the newly generated chromosomes, update the population, and replace some old chromosomes with the newly generated chromosomes; Repeat the iterative process until the preset number of iterations is reached or the fitness value meets certain conditions; The chromosome with the highest fitness is selected from the final population as the optimized seeding parameter combination.

[0008] Furthermore, the rice planting equipment with high enzyme activity of the present invention and the rice planting monitoring module are also used for: Collect real-time regional data of rice planting, group the real-time regional data of rice planting to obtain the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area, establish an inspection task for the first rice planting area to obtain the first rice planting area inspection task, establish an inspection task for the second rice planting area to obtain the second rice planting area inspection task, establish an inspection task for the third rice planting area to obtain the third rice planting area inspection task, establish an inspection task for the fourth rice planting area to obtain the fourth rice planting area inspection task, combine the first rice planting area inspection task, the second rice planting area inspection task, the third rice planting area inspection task and the fourth rice planting area inspection task into a rice planting task, substitute the rice planting task into the optimized rice planting equipment control model, and output the optimized expected rice growth data.

[0009] Furthermore, the rice planting equipment with high enzyme activity of the present invention and the rice fertilization optimization module are also used for: The first rice planting area inspection task, the second rice planting area inspection task, the third rice planting area inspection task and the fourth rice planting area inspection task are transmitted to the inspection device, and the inspection data of the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area fed back by the inspection device are received to obtain the partition real-time inspection data, and the partition real-time inspection data is compared with the optimized expected rice growth data to obtain the partition rice growth comparison result. If there is a rice planting area whose growth data is lower than the optimized expected rice growth data in the partition real-time inspection data, then the rice planting area whose growth data is lower than the optimized expected rice growth data is obtained. The historical fertilization data of the domain is obtained, and the enzyme activity detection device is used to detect the enzyme activity of the rice planting area below the optimized expected rice growth data to obtain the enzyme activity data of the partition to be processed, the enzyme activity data of the partition to be processed is substituted into the preset enzyme activity adjustment model, the real-time fertilization adjustment amount is output, the real-time fertilization adjustment amount is sent to the fertilization device, the fertilization device fertilizes according to the real-time fertilization adjustment amount, and uses a genetic algorithm to optimize the real-time fertilization adjustment amount until there is no rice planting area below the optimized expected rice growth data in the real-time inspection data of the partition or the final iteration time and the maximum number of iterations are met, and the real-time fertilization adjustment amount is stopped for optimization.

[0010] In a second aspect, the present invention provides a method for planting rice with high enzyme activity, which is applied to the rice planting equipment with high enzyme activity, comprising: Step S101, obtaining soil parameter data, soil enzyme activity history data, enzyme activity data, environmental parameters, rice growth data, fertilization use history data and rice planting equipment control model; Step S102, receiving a rice planting task, the rice planting task includes rice planting location data, expected rice planting yield, rice fertilization standard and expected rice planting time information, substituting the rice planting task into a preset rice planting equipment control model to obtain an expected rice planting control command, the expected rice planting control command includes an expected number of rice seeds, an expected amount of rice fertilizer, expected rice growth data, expected rice fertilization data, an expected rice sowing task, an expected rice fertilization task and an expected rice inspection task; Step S103, according to the expected number of rice seeds, rice seeds are loaded in the sowing device, according to the expected amount of rice fertilizer, fertilizers are loaded in the fertilizing device, the expected rice inspection task is sent to the inspection device, the inspection data collected by the inspection device after the sowing device performs the expected rice sowing task and the fertilizing device performs the expected rice fertilizing task are received, and real-time inspection data are obtained, and the real-time inspection data is compared with the expected rice growth data to obtain rice growth error data. If the rice growth error data exceeds the preset rice growth error range value, the expected rice fertilization data is compared with the historical data of the fertilizing device. If the comparison result of the expected rice fertilization data and the historical data of the fertilizing device is consistent, the rice fertilization is normal, and the historical data of the sowing device is obtained. The rice growth error data, the expected rice growth data and the historical data of the sowing device are used to optimize the rice planting equipment control model using a genetic algorithm to obtain the optimized rice planting equipment control model; Step S104, collecting real-time rice planting area data, grouping the real-time rice planting area data to obtain a first rice planting area, a second rice planting area, a third rice planting area and a fourth rice planting area, establishing an inspection task for the first rice planting area, obtaining a rice planting task, substituting the rice planting task into the optimized rice planting equipment control model, and outputting the optimized expected rice growth data; Step S105 is used to transmit the first rice-growing area inspection task, the second rice-growing area inspection task, the third rice-growing area inspection task and the fourth rice-growing area inspection task to the inspection device, obtain the enzyme activity data of the partition to be processed, substitute the enzyme activity data of the partition to be processed into the preset enzyme activity adjustment model, and output the real-time fertilization adjustment amount.

[0011] Furthermore, the rice planting method with high enzyme activity of the present invention is characterized in that the step S103 further comprises: Collating rice growth error data, which includes the difference between the actual observed rice growth and the expected rice growth data; Expected rice growth data, used to reflect the growth state that rice should achieve based on the preliminary prediction of the rice planting task and the rice planting equipment control model; Obtaining historical data of the sowing device, including historical sowing records, seed quality, sowing time, etc. The historical data of the sowing device is used to analyze the impact of the sowing process on rice growth; Receive and set the optimization goal, and set the optimization goal to minimize the rice growth error, even if the actual rice growth data is close to the expected rice growth data, and use the sowing density and seed variety as adjustment parameters in the optimization process; Designing a chromosome structure of a genetic algorithm, each chromosome represents a set of sowing parameter combinations, the sowing parameter combinations include sowing density, seed variety, sowing frequency of a sowing device, and sowing speed of a sowing device; Define the fitness function for evaluating each set of sowing parameters based on the rice growth error data, that is, the quality of each chromosome. The higher the fitness, the closer the rice growth under this set of sowing parameters is to the expectation. Set and configure the parameters of the genetic algorithm, including population size, number of iterations, crossover probability, and mutation probability; Initialize the population and generate a set of random seeding parameter combinations as the initial solution; Calculate the fitness value of each chromosome in the current population; According to the fitness value, excellent chromosomes are selected for reproduction and crossover to generate new chromosome offspring; Perform mutation operations on the newly generated chromosomes, update the population, and replace some old chromosomes with the newly generated chromosomes; Repeat the iterative process until the preset number of iterations is reached or the fitness value meets certain conditions; The chromosome with the highest fitness is selected from the final population as the optimized seeding parameter combination.

[0012] Furthermore, in the rice planting method with high enzyme activity of the present invention, the step S104 further includes: Collect real-time regional data of rice planting, group the real-time regional data of rice planting to obtain the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area, establish an inspection task for the first rice planting area to obtain the first rice planting area inspection task, establish an inspection task for the second rice planting area to obtain the second rice planting area inspection task, establish an inspection task for the third rice planting area to obtain the third rice planting area inspection task, establish an inspection task for the fourth rice planting area to obtain the fourth rice planting area inspection task, combine the first rice planting area inspection task, the second rice planting area inspection task, the third rice planting area inspection task and the fourth rice planting area inspection task into a rice planting task, substitute the rice planting task into the optimized rice planting equipment control model, and output the optimized expected rice growth data.

[0013] Furthermore, in the rice planting method with high enzyme activity of the present invention, the step S105 further includes: The first rice planting area inspection task, the second rice planting area inspection task, the third rice planting area inspection task and the fourth rice planting area inspection task are transmitted to the inspection device, and the inspection data of the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area fed back by the inspection device are received to obtain the partition real-time inspection data, and the partition real-time inspection data is compared with the optimized expected rice growth data to obtain the partition rice growth comparison result. If there is a rice planting area whose growth data is lower than the optimized expected rice growth data in the partition real-time inspection data, then the rice planting area whose growth data is lower than the optimized expected rice growth data is obtained. The historical fertilization data of the domain is obtained, and the enzyme activity detection device is used to detect the enzyme activity of the rice planting area below the optimized expected rice growth data to obtain the enzyme activity data of the partition to be processed, the enzyme activity data of the partition to be processed is substituted into the preset enzyme activity adjustment model, the real-time fertilization adjustment amount is output, the real-time fertilization adjustment amount is sent to the fertilization device, the fertilization device fertilizes according to the real-time fertilization adjustment amount, and uses a genetic algorithm to optimize the real-time fertilization adjustment amount until there is no rice planting area below the optimized expected rice growth data in the real-time inspection data of the partition or the final iteration time and the maximum number of iterations are met, and the real-time fertilization adjustment amount is stopped for optimization.

[0014] Beneficial effects of the present invention: The present invention maintains and enhances enzyme activity, activates microbial activity in the soil, improves soil microecological environment, and thus significantly improves rice yield and quality, bringing higher economic benefits to farmers. The integrated sensor network is used to collect environmental parameters such as soil moisture, temperature, pH value and enzyme activity in real time, combined with advanced bioinformatics and data analysis algorithms, to achieve dynamic adjustment of fertilizer application, irrigation frequency and planting density, ensuring the optimization of the rice growth environment.

[0015] Through precise management, we can avoid excessive fertilization and irrigation, effectively reduce resource waste, and reduce the pollution of fertilizers and pesticides to the environment, thus protecting the ecological environment. We can use genetic algorithms to iteratively optimize the sowing parameters, find the optimal sowing density and seed variety combination, improve the germination rate and growth health of rice, and lay the foundation for high yield and high quality of rice.

[0016] According to the real-time inspection data and enzyme activity test results, the amount of fertilizer is dynamically adjusted to ensure that the soil enzyme activity remains in the optimal range, promote the healthy growth of rice, and improve the effect of fertilization. Automated and intelligent planting equipment and methods reduce human intervention, improve planting efficiency, reduce labor costs, and provide strong support for the scale and intensification of agricultural production.

[0017] The present invention can be adjusted and optimized according to the rice planting needs of different regions and different soil conditions, has strong adaptability and promotion value, and provides customized solutions for agricultural production in different regions. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on the drawings without paying any creative labor.

[0019] Figure 1 This is a schematic diagram of the functional modules in the rice planting equipment with high enzyme activity provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. 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. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0021] In order to better understand the purpose of the present invention, the present invention is described in further detail below.

[0022] In a first aspect, the present invention provides a rice planting device with high enzyme activity, comprising: a control device, a data acquisition terminal, an enzyme activity detection device, an inspection device, a fertilization device, a sowing device and a data acquisition terminal, wherein the control device establishes communication connections with the inspection device, the enzyme activity detection device, the fertilization device, the sowing device and the fertilization device respectively, and the control device receives data collected by the data acquisition terminal and the enzyme activity detection device, and the control device outputs a rice planting control command according to the data collected by the data acquisition terminal, and sends the rice planting control command to the inspection device, the fertilization device, the sowing device and the fertilization device, and the control device comprises: A data acquisition module is used to acquire soil parameter data, soil enzyme activity history data, enzyme activity data, environmental parameters, rice growth data, fertilizer use history data and rice planting equipment control model; The data acquisition module is responsible for acquiring the following data in the rice planting equipment and providing input for the rice planting equipment control model: Soil parameter data: including soil moisture, temperature, pH value, etc. These data are the basis for evaluating the soil environment and formulating planting strategies.

[0023] Historical data of soil enzyme activity: Recording the historical changes in soil enzyme activity helps to understand enzyme activity trends and predict future levels.

[0024] Enzyme activity data: reflects the current enzyme activity level in the soil and is an important basis for adjusting planting parameters and optimizing planting strategies.

[0025] Environmental parameters: such as light intensity, temperature, humidity, etc. These factors directly affect the growth of rice and are factors that cannot be ignored in planting decisions.

[0026] Rice growth data: including plant height, leaf area, biomass, etc., used to evaluate the growth status of rice and adjust planting strategies in a timely manner.

[0027] Fertilization usage historical data: record the type, amount, time of fertilizer application in the past, etc., to provide data support for formulating a more reasonable fertilization plan.

[0028] The data is collected in real time through the integrated sensor network and transmitted to the data acquisition module for processing and analysis. Subsequently, the data is input into the rice planting equipment control model, which generates planting control commands based on the data to guide the equipment to perform precision agricultural management, so that various parameters in the rice planting process can be dynamically adjusted, maximizing the release of soil enzyme activity and improving the yield and quality of rice planting.

[0029] A dynamic monitoring module is used to receive rice planting tasks, the rice planting tasks include rice planting location data, expected rice planting yield, rice fertilization standards and expected rice planting time information, substitute the rice planting tasks into a preset rice planting equipment control model, and obtain expected rice planting control commands, the expected rice planting control commands include expected rice seed quantity, expected rice fertilizer amount, expected rice growth data, expected rice fertilization data, expected rice sowing tasks, expected rice fertilization tasks and expected rice inspection tasks; The dynamic monitoring module is a component of the rice planting equipment with high enzyme activity. Its main functions and effects are as follows: The dynamic monitoring module is responsible for receiving planting tasks including information such as rice planting location, expected yield, fertilization standards and expected planting time.

[0030] The received planting task is substituted into the preset rice planting equipment control model to generate a series of specific control commands.

[0031] The expected rice planting control commands include the expected number of rice seeds, fertilizer amount, growth data, fertilizer data, sowing tasks, fertilization tasks and inspection tasks, etc. These commands specify in detail the parameters and tasks in the rice planting process.

[0032] Through the dynamic monitoring module, planting tasks can be automatically parsed and converted into specific control commands to improve planting efficiency and accuracy. Based on the prediction and dynamic monitoring of the dynamic monitoring module, resources such as seeds and fertilizers can be rationally allocated to avoid waste. Through precise control and management, the healthy growth of rice can be ensured, the survival rate and yield can be increased, and the quality of rice can be improved.

[0033] In summary, the dynamic monitoring module provides strong support for the precise planting and management of rice through accurate analysis of rice planting tasks and generation of expected control commands.

[0034] A model optimization module is used to load rice seeds in a sowing device according to an expected number of rice seeds, load fertilizers in a fertilizing device according to an expected amount of rice fertilizer, send an expected rice inspection task to the inspection device, receive inspection data collected by the inspection device after the sowing device performs the expected rice sowing task and the fertilizing device performs the expected rice fertilizing task, obtain real-time inspection data, compare the real-time inspection data with the expected rice growth data, obtain rice growth error data, if the rice growth error data exceeds a preset rice growth error range value, compare the expected rice fertilization data with the historical data of the fertilizing device, if the comparison results of the expected rice fertilization data and the historical data of the fertilizing device are consistent, the rice fertilization is normal, obtain the historical data of the sowing device, use the rice growth error data, the expected rice growth data and the historical data of the sowing device to optimize the rice planting equipment control model using a genetic algorithm, and obtain an optimized rice planting equipment control model; The main functions and optimization processes of the model optimization module in rice planting equipment are as follows: According to the expected number of rice seeds, accurately load rice seeds in the sowing device, and according to the expected amount of rice fertilizer, load the corresponding fertilizer in the fertilizing device. Send the expected rice inspection task to the inspection device, so that the inspection device performs the inspection work. Receive the real-time inspection data after sowing and fertilization collected by the inspection device. The inspection device can use drones or inspection robots to collect image data and analyze the growth data of rice through a preset image analysis model.

[0035] The real-time inspection data is compared with the expected rice growth data to calculate the rice growth error data. If the rice growth error data exceeds the preset range, the fertilization and sowing process is further analyzed.

[0036] Compare the expected rice fertilization data with the historical data of the fertilization device to confirm whether the fertilization operation is normal. If the fertilization is normal, obtain the historical data of the sowing device to analyze the impact of the sowing process on rice growth.

[0037] The optimization goal is to minimize the rice growth error and make the actual growth data close to the expected one.

[0038] Design genetic algorithm chromosome structure to represent seeding parameter combinations.

[0039] Define the fitness function and evaluate the sowing parameters based on the rice growth error data.

[0040] Set the genetic algorithm parameters, initialize the population, and generate random seeding parameter combinations as initial solutions.

[0041] Iterative optimization, including selection, crossover, and mutation operations, is performed until the optimization condition is reached.

[0042] The chromosome with the highest fitness is selected as the optimized seeding parameter combination.

[0043] The optimized sowing parameter combination is applied to the rice planting equipment control model.

[0044] Obtain an optimized rice planting equipment control model to improve rice growth efficiency and yield.

[0045] In summary, the model optimization module optimizes the control model of rice planting equipment through fine data collection, comparison and analysis, and the application of genetic algorithms, thereby improving the planting efficiency and yield of rice.

[0046] The rice planting monitoring module is used to collect the real-time regional data of rice planting, group the real-time regional data of rice planting, obtain the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area, establish an inspection task for the first rice planting area, obtain the rice planting task, substitute the rice planting task into the optimized rice planting equipment control model, and output the optimized expected rice growth data; The functions and effects of the rice planting monitoring module in the entire rice planting process are as follows: The rice planting monitoring module is responsible for collecting real-time regional data of rice planting and grouping these data.

[0047] The collected data are divided into four parts, namely the first rice-growing area, the second rice-growing area, the third rice-growing area and the fourth rice-growing area.

[0048] Establishment of inspection tasks: Establishment of inspection tasks for the first rice planting area, which is regarded as a specific rice planting task. Substitute the rice planting task into the optimized rice planting equipment control model.

[0049] The rice planting equipment control model will output optimized expected rice growth data, providing a basis for adjusting the planting strategy.

[0050] The rice planting monitoring module helps optimize rice planting strategies and predict rice growth conditions through real-time data collection and model analysis, thereby improving planting efficiency and yield.

[0051] The rice planting monitoring module collaborates with the data acquisition module, model optimization module, etc. to improve the accuracy of data during the rice growth process, and jointly provide strong support for improving rice yield and quality.

[0052] In summary, the rice planting monitoring module realizes accurate monitoring and optimized management of the rice planting process through functions such as real-time data collection, group processing, inspection task establishment, and model application and output, laying the foundation for improving rice yield and quality.

[0053] The rice fertilization optimization module is used to transmit the inspection tasks of the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area to the inspection device, obtain the enzyme activity data of the partition to be processed, substitute the enzyme activity data of the partition to be processed into the preset enzyme activity adjustment model, and output the real-time fertilization adjustment amount.

[0054] The rice fertilization optimization module is a rice planting equipment with the following functions and operation procedures: The rice fertilization optimization module aims to optimize the amount of fertilizer in different rice-growing areas and improve the growth quality and yield of rice by increasing soil enzyme activity.

[0055] The inspection tasks of the first, second, third and fourth rice planting areas are transmitted to the inspection device. The inspection data of the four planting areas fed back by the inspection device are received. These data contain soil enzyme activity information of each area and are called the partition enzyme activity data to be processed.

[0056] Substitute the enzyme activity data of the partition to be processed into the preset enzyme activity regulation model. This model calculates the real-time fertilization regulation amount based on the relationship between enzyme activity and rice growth requirements.

[0057] The enzyme activity regulation model outputs the real-time fertilizer adjustment amount for each area to guide the fertilization device to apply fertilizer accurately.

[0058] The fertilization device performs fertilization according to the real-time fertilization adjustment output. At the same time, the fertilization adjustment is continuously optimized using a genetic algorithm until the real-time inspection data of all areas reaches or exceeds the optimized expected rice growth data, or meets the preset number of iterations and time limits.

[0059] When the real-time inspection data of certain areas show that the rice growth is lower than expected, the module will obtain the historical fertilization data of these areas and detect the enzyme activity through the enzyme activity detection device. Combining the test results with the enzyme activity regulation model, the module calculates the new fertilization adjustment amount and uses the genetic algorithm to optimize again to ensure the accuracy and effectiveness of the fertilization strategy.

[0060] In summary, the rice fertilization optimization module achieves refined management of rice planting by real-time monitoring of soil enzyme activity, dynamic adjustment of fertilizer application, and combining intelligent optimization algorithms, aiming to promote the healthy growth of rice and increase yield.

[0061] The specific steps to build a rice planting equipment control model are as follows: Collect soil parameter data, soil enzyme activity historical data, enzyme activity data, environmental parameters, rice growth data, and fertilizer use historical data to provide basic data support for subsequent modeling.

[0062] Receive rice planting tasks, including rice planting location, yield expectations, fertilization standards, and expected planting time.

[0063] The rice planting task is substituted into the preset rice planting equipment control model to generate expected rice planting control commands, such as the expected number of rice seeds, amount of fertilizer, and growth data.

[0064] According to the expected number of rice seeds, a corresponding number of rice seeds are loaded into the sowing device.

[0065] Fertilizer is loaded in the fertilizer application device according to the expected amount of fertilizer to be applied to the rice.

[0066] The expected rice inspection tasks are sent to the inspection device to ensure real-time monitoring of rice growth.

[0067] The inspection data of the sowing device and the fertilizing device after performing the expected tasks collected by the inspection device are received to form real-time inspection data.

[0068] The real-time inspection data is compared with the expected rice growth data, and the rice growth error data is calculated to provide a basis for model optimization.

[0069] If the rice growth error data exceeds the preset range, the fertilization data needs to be verified.

[0070] Compare the expected rice fertilization data with the historical data of the fertilization device to confirm whether the fertilization is normal.

[0071] The historical data of the seeding device is obtained, combined with the rice growth error data, the expected rice growth data and the historical data of the seeding device, and the control model of the rice planting equipment is optimized through the genetic algorithm to obtain a more accurate control model.

[0072] Collect real-time regional data on rice planting and manage the data in groups to form multiple rice planting areas.

[0073] Inspection tasks are established for each area, and the inspection tasks are substituted into the optimized rice planting equipment control model to output the optimized expected rice growth data to provide guidance for regional management.

[0074] The inspection tasks of each rice-growing area are transmitted to the inspection device to obtain the enzyme activity data of each area.

[0075] Substitute the enzyme activity data into the preset enzyme activity regulation model, calculate the real-time fertilization adjustment amount, and perform precise fertilization based on the adjustment amount.

[0076] Genetic algorithms are used to continuously optimize the real-time fertilizer adjustment amount until the stopping condition is met (such as the rice growth data in all areas reaches the expectation or the maximum number of iterations is reached) to ensure the best fertilization effect.

[0077] Through this series of steps, an efficient and accurate rice planting equipment control model can be constructed to achieve comprehensive monitoring and dynamic adjustment of the rice planting process, thereby improving rice yield and quality.

[0078] Specific steps to construct an enzyme activity regulation model: Collect historical data on soil enzyme activity and record changes in enzyme activity during rice growth under different soil conditions.

[0079] Record the growth data of rice at different enzyme activity levels, including growth rate, health status, etc., to provide basic data for model training.

[0080] Identify key factors affecting enzyme activity as input variables, such as soil moisture, temperature, pH, fertilizer type and amount, etc.

[0081] The enzyme activity level is used as the output variable, which can be measured in real time by an enzyme activity detection device.

[0082] According to the data characteristics and problem requirements, select a suitable mathematical model or machine learning algorithm to establish the relationship between enzyme activity and influencing factors. Possible models include linear regression, neural network, support vector machine, etc.

[0083] The selected model is trained using the collected data and the model parameters are adjusted to minimize the prediction error and improve the accuracy of the model.

[0084] Use cross-validation or other validation methods to evaluate the model to ensure that the model performs well on new, unseen data and has generalization ability.

[0085] The model was further adjusted and optimized based on the validation results to improve the prediction accuracy and stability of the model and ensure that the model could better reflect the relationship between enzyme activity and influencing factors.

[0086] The optimized enzyme activity regulation model is deployed in rice planting equipment to realize real-time reception of data from the enzyme activity detection device, and adjust the fertilization strategy according to the model output to optimize the rice growth environment.

[0087] After the model is deployed, rice growth and enzyme activity levels are continuously monitored, and new data are collected for model updating and optimization to ensure that the model can adapt to changing environmental conditions.

[0088] These steps constitute a complete enzyme activity regulation model construction process, which uses data analysis and machine learning technology to improve the level of enzyme activity management during rice cultivation, thereby improving rice yield and quality. Specifically, the rice planting equipment with high enzyme activity of the present invention, the model optimization module is also used for: Collating rice growth error data, which includes the difference between the actual observed rice growth and the expected rice growth data; Expected rice growth data, used to reflect the growth state that rice should achieve based on the preliminary prediction of the rice planting task and the rice planting equipment control model; Obtaining historical data of the sowing device, including historical sowing records, seed quality, sowing time, etc. The historical data of the sowing device is used to analyze the impact of the sowing process on rice growth; Receive and set the optimization goal, and set the optimization goal to minimize the rice growth error, even if the actual rice growth data is close to the expected rice growth data, and use the sowing density and seed variety as adjustment parameters in the optimization process; Designing a chromosome structure of a genetic algorithm, each chromosome represents a set of sowing parameter combinations, the sowing parameter combinations include sowing density, seed variety, sowing frequency of a sowing device, and sowing speed of a sowing device; Define the fitness function for evaluating each set of sowing parameters based on the rice growth error data, that is, the quality of each chromosome. The higher the fitness, the closer the rice growth under this set of sowing parameters is to the expectation. Set and configure the parameters of the genetic algorithm, including population size, number of iterations, crossover probability, and mutation probability; Initialize the population and generate a set of random seeding parameter combinations as the initial solution; Calculate the fitness value of each chromosome in the current population; According to the fitness value, excellent chromosomes are selected for reproduction and crossover to generate new chromosome offspring; Perform mutation operations on the newly generated chromosomes, update the population, and replace some old chromosomes with the newly generated chromosomes; Repeat the iterative process until the preset number of iterations is reached or the fitness value meets certain conditions; The chromosome with the highest fitness is selected from the final population as the optimized seeding parameter combination.

[0089] The model optimization module is responsible for sorting out the differences between the actual observed rice growth conditions and the expected rice growth data, providing a basis for subsequent optimization.

[0090] The expected rice growth data reflects the growth status that rice should achieve based on the preliminary prediction of rice planting tasks and rice planting equipment control models, providing a reference for evaluating the actual growth situation.

[0091] By collecting historical sowing records, seed quality, sowing time and other data, we analyze the impact of the sowing process on rice growth and provide a basis for optimizing sowing parameters.

[0092] The optimization goal was set to minimize the rice growth error, even if the actual rice growth data was close to the expected rice growth data, and the sowing density and seed variety were clearly used as adjustment parameters in the optimization process.

[0093] Design the chromosome structure of the genetic algorithm: Each chromosome represents a set of sowing parameter combinations, including sowing density, seed variety, sowing frequency of the sowing device, and sowing speed of the sowing device, providing a basic framework for the application of genetic algorithms.

[0094] Evaluate the fitness function for each set of seeding parameters: Definition: The quality of each set of sowing parameters is evaluated based on the rice growth error data. The higher the fitness, the closer the rice growth under this set of sowing parameters is to the expectation, providing a basis for selecting excellent chromosomes.

[0095] Set the parameters of the genetic algorithm: Including population size, number of iterations, crossover probability, and mutation probability, etc., to ensure the effective operation and convergence of the genetic algorithm.

[0096] Initialize the population: A set of random seeding parameter combinations are generated as initial solutions to provide a starting point for the iterative process of the genetic algorithm.

[0097] Calculate the fitness value of each chromosome in the current population: By comparing the actual observed data with the expected data, the advantages and disadvantages of each set of seeding parameters are evaluated, providing a basis for selecting excellent chromosomes for breeding crossover.

[0098] Select excellent chromosomes for breeding crossover: According to the fitness value, excellent chromosomes are selected for reproduction and crossover to generate new chromosome offspring and promote the inheritance of excellent genes.

[0099] Perform mutation operation on the newly generated chromosome: The population is updated through mutation operations to increase the diversity of the population and replace some old chromosomes with newly generated chromosomes.

[0100] Repeat the iterative process: The above process is repeated until the preset number of iterations is reached or the fitness value meets certain conditions to ensure the stability and accuracy of the optimization results.

[0101] Select the optimized sowing parameter combination: The chromosome with the highest fitness is selected from the final population as the optimized sowing parameter combination to provide the best sowing parameters for rice planting.

[0102] In summary, the model optimization module achieves precise optimization of sowing parameters through the application of genetic algorithms and a series of optimization processes, thereby minimizing rice growth errors and improving rice yield and quality.

[0103] Specifically, the rice planting equipment with high enzyme activity of the present invention and the rice planting monitoring module are also used for: Collect real-time regional data of rice planting, group the real-time regional data of rice planting to obtain the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area, establish an inspection task for the first rice planting area to obtain the first rice planting area inspection task, establish an inspection task for the second rice planting area to obtain the second rice planting area inspection task, establish an inspection task for the third rice planting area to obtain the third rice planting area inspection task, establish an inspection task for the fourth rice planting area to obtain the fourth rice planting area inspection task, combine the first rice planting area inspection task, the second rice planting area inspection task, the third rice planting area inspection task and the fourth rice planting area inspection task into a rice planting task, substitute the rice planting task into the optimized rice planting equipment control model, and output the optimized expected rice growth data.

[0104] The functions and effects of the rice planting monitoring module in rice planting equipment with high enzyme activity are as follows: Collect real-time regional data on rice planting: Collect data on rice planting areas in real time to ensure the latest planting status information and provide a basis for subsequent analysis and management.

[0105] Data grouping and management: The collected data is grouped into the first, second, third, and fourth rice planting areas. This grouping method helps to manage and analyze different areas separately and improve the precision of management.

[0106] Establish inspection tasks: Establish inspection tasks for each grouped rice planting area, including monitoring and evaluating the growth of rice in the area. This helps to find and solve problems in a timely manner and ensure the healthy growth of rice.

[0107] Form a comprehensive rice planting task: Combine the inspection tasks of each area to form a comprehensive rice planting task. This can achieve unified management of the entire planting area and improve management efficiency.

[0108] The model outputs the optimized expected rice growth data: the combined rice planting task is substituted into the optimized rice planting equipment control model, and the optimized expected rice growth data is output through the model calculation and analysis. These data provide growers with clear planting goals and management directions, which help to achieve more precise agricultural management.

[0109] In summary, the rice planting monitoring module provides comprehensive monitoring and management support for rice planting through functions and roles such as real-time data collection, group management, establishment of inspection tasks, composition of comprehensive planting tasks, and model output optimization data, which helps to optimize planting strategies and improve yield and quality.

[0110] Specifically, the rice planting equipment with high enzyme activity of the present invention and the rice fertilization optimization module are also used for: The first rice planting area inspection task, the second rice planting area inspection task, the third rice planting area inspection task and the fourth rice planting area inspection task are transmitted to the inspection device, and the inspection data of the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area fed back by the inspection device are received to obtain the partition real-time inspection data, and the partition real-time inspection data is compared with the optimized expected rice growth data to obtain the partition rice growth comparison result. If there is a rice planting area whose growth data is lower than the optimized expected rice growth data in the partition real-time inspection data, then the rice planting area whose growth data is lower than the optimized expected rice growth data is obtained. The historical fertilization data of the domain is obtained, and the enzyme activity detection device is used to detect the enzyme activity of the rice planting area below the optimized expected rice growth data to obtain the enzyme activity data of the partition to be processed, the enzyme activity data of the partition to be processed is substituted into the preset enzyme activity adjustment model, the real-time fertilization adjustment amount is output, the real-time fertilization adjustment amount is sent to the fertilization device, the fertilization device fertilizes according to the real-time fertilization adjustment amount, and uses a genetic algorithm to optimize the real-time fertilization adjustment amount until there is no rice planting area below the optimized expected rice growth data in the real-time inspection data of the partition or the final iteration time and the maximum number of iterations are met, and the real-time fertilization adjustment amount is stopped for optimization.

[0111] The functions and effects of the rice fertilization optimization module in rice planting equipment with high enzyme activity are as follows: Transmit inspection tasks: Transmit the inspection tasks of the first, second, third and fourth rice planting areas to the inspection device to ensure that each area is monitored in a timely and effective manner.

[0112] Receive inspection data: Receive inspection data of each rice planting area fed back by the inspection device to form real-time inspection data of each zone, providing a basis for subsequent analysis.

[0113] Compare growth data: Compare the real-time inspection data of each zone with the optimized expected rice growth data to evaluate the growth status of rice in each area.

[0114] Detect enzyme activity: If a rice-growing area whose rice growth data is lower than the expected optimized rice growth data is found in the real-time inspection data of the partition, the historical fertilization data of the area is obtained, and the enzyme activity is detected by an enzyme activity detection device to obtain the enzyme activity data of the partition to be processed.

[0115] Calculate the fertilizer adjustment amount: Substitute the enzyme activity data of the partition to be processed into the preset enzyme activity adjustment model to calculate the real-time fertilizer adjustment amount, providing a basis for precise fertilization.

[0116] Send fertilizer adjustment amount: Send the real-time fertilizer adjustment amount to the fertilization device to ensure that the fertilization device can fertilize according to the optimized fertilizer amount.

[0117] Execute fertilization operation: The fertilization device performs fertilization operation according to the received real-time fertilization adjustment amount to achieve precise fertilization.

[0118] Optimize the fertilizer adjustment amount: Use a genetic algorithm to continuously optimize the real-time fertilizer adjustment amount until there is no rice planting area with growth data lower than the expected rice growth data after optimization in the real-time inspection data of the partition, or stop the optimization when the final iteration time and the maximum number of iterations are met.

[0119] The rice fertilization optimization module can dynamically adjust the amount of fertilizer during rice planting, optimize soil enzyme activity, and thus improve rice growth and yield.

[0120] In a second aspect, the present invention provides a method for planting rice with high enzyme activity, which is applied to the rice planting equipment with high enzyme activity, comprising: Step S101, obtaining soil parameter data, soil enzyme activity history data, enzyme activity data, environmental parameters, rice growth data, fertilization use history data and rice planting equipment control model; Step S102, receiving a rice planting task, the rice planting task includes rice planting location data, expected rice planting yield, rice fertilization standard and expected rice planting time information, substituting the rice planting task into a preset rice planting equipment control model to obtain an expected rice planting control command, the expected rice planting control command includes an expected number of rice seeds, an expected amount of rice fertilizer, expected rice growth data, expected rice fertilization data, an expected rice sowing task, an expected rice fertilization task and an expected rice inspection task; Step S103, according to the expected number of rice seeds, rice seeds are loaded in the sowing device, according to the expected amount of rice fertilizer, fertilizers are loaded in the fertilizing device, the expected rice inspection task is sent to the inspection device, the inspection data collected by the inspection device after the sowing device performs the expected rice sowing task and the fertilizing device performs the expected rice fertilizing task are received, and real-time inspection data are obtained, and the real-time inspection data is compared with the expected rice growth data to obtain rice growth error data. If the rice growth error data exceeds the preset rice growth error range value, the expected rice fertilization data is compared with the historical data of the fertilizing device. If the comparison result of the expected rice fertilization data and the historical data of the fertilizing device is consistent, the rice fertilization is normal, and the historical data of the sowing device is obtained. The rice growth error data, the expected rice growth data and the historical data of the sowing device are used to optimize the rice planting equipment control model using a genetic algorithm to obtain the optimized rice planting equipment control model; Step S104, collecting real-time rice planting area data, grouping the real-time rice planting area data to obtain a first rice planting area, a second rice planting area, a third rice planting area and a fourth rice planting area, establishing an inspection task for the first rice planting area, obtaining a rice planting task, substituting the rice planting task into the optimized rice planting equipment control model, and outputting the optimized expected rice growth data; Step S105 is used to transmit the first rice-growing area inspection task, the second rice-growing area inspection task, the third rice-growing area inspection task and the fourth rice-growing area inspection task to the inspection device, obtain the enzyme activity data of the partition to be processed, substitute the enzyme activity data of the partition to be processed into the preset enzyme activity adjustment model, and output the real-time fertilization adjustment amount.

[0121] Specifically, the rice planting method with high enzyme activity of the present invention is characterized in that the step S103 further comprises: Collating rice growth error data, which includes the difference between the actual observed rice growth and the expected rice growth data; Expected rice growth data, used to reflect the growth state that rice should achieve based on the preliminary prediction of the rice planting task and the rice planting equipment control model; Obtaining historical data of the sowing device, including historical sowing records, seed quality, sowing time, etc. The historical data of the sowing device is used to analyze the impact of the sowing process on rice growth; Receive and set the optimization goal, and set the optimization goal to minimize the rice growth error, even if the actual rice growth data is close to the expected rice growth data, and use the sowing density and seed variety as adjustment parameters in the optimization process; Designing a chromosome structure of a genetic algorithm, each chromosome represents a set of sowing parameter combinations, the sowing parameter combinations include sowing density, seed variety, sowing frequency of a sowing device, and sowing speed of a sowing device; Define the fitness function for evaluating each set of sowing parameters based on the rice growth error data, that is, the quality of each chromosome. The higher the fitness, the closer the rice growth under this set of sowing parameters is to the expectation. Set and configure the parameters of the genetic algorithm, including population size, number of iterations, crossover probability, and mutation probability; Initialize the population and generate a set of random seeding parameter combinations as the initial solution; Calculate the fitness value of each chromosome in the current population; According to the fitness value, excellent chromosomes are selected for reproduction and crossover to generate new chromosome offspring; Perform mutation operations on the newly generated chromosomes, update the population, and replace some old chromosomes with the newly generated chromosomes; Repeat the iterative process until the preset number of iterations is reached or the fitness value meets certain conditions; The chromosome with the highest fitness is selected from the final population as the optimized seeding parameter combination.

[0122] Specifically, the method for growing rice with high enzyme activity according to the present invention, the step S104 further includes: Collect real-time regional data of rice planting, group the real-time regional data of rice planting to obtain the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area, establish an inspection task for the first rice planting area to obtain the first rice planting area inspection task, establish an inspection task for the second rice planting area to obtain the second rice planting area inspection task, establish an inspection task for the third rice planting area to obtain the third rice planting area inspection task, establish an inspection task for the fourth rice planting area to obtain the fourth rice planting area inspection task, combine the first rice planting area inspection task, the second rice planting area inspection task, the third rice planting area inspection task and the fourth rice planting area inspection task into a rice planting task, substitute the rice planting task into the optimized rice planting equipment control model, and output the optimized expected rice growth data.

[0123] Specifically, the method for growing rice with high enzyme activity according to the present invention, the step S105 further comprises: The first rice planting area inspection task, the second rice planting area inspection task, the third rice planting area inspection task and the fourth rice planting area inspection task are transmitted to the inspection device, and the inspection data of the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area fed back by the inspection device are received to obtain the partition real-time inspection data, and the partition real-time inspection data is compared with the optimized expected rice growth data to obtain the partition rice growth comparison result. If there is a rice planting area whose growth data is lower than the optimized expected rice growth data in the partition real-time inspection data, then the rice planting area whose growth data is lower than the optimized expected rice growth data is obtained. The historical fertilization data of the domain is obtained, and the enzyme activity detection device is used to detect the enzyme activity of the rice planting area below the optimized expected rice growth data to obtain the enzyme activity data of the partition to be processed, the enzyme activity data of the partition to be processed is substituted into the preset enzyme activity adjustment model, the real-time fertilization adjustment amount is output, the real-time fertilization adjustment amount is sent to the fertilization device, the fertilization device fertilizes according to the real-time fertilization adjustment amount, and uses a genetic algorithm to optimize the real-time fertilization adjustment amount until there is no rice planting area below the optimized expected rice growth data in the real-time inspection data of the partition or the final iteration time and the maximum number of iterations are met, and the real-time fertilization adjustment amount is stopped for optimization.

[0124] The present invention provides a rice planting device with high enzyme activity and a planting method thereof. The technical solution aims to solve the problem that the sowing method and fertilization cannot be dynamically adjusted in the existing rice planting process, so as to maximize the release of enzyme activity in the soil and increase the rice planting yield. Specific solutions include: The rice planting equipment with high enzyme activity integrates multiple components such as control devices, data acquisition terminals, enzyme activity detection devices, etc. to achieve comprehensive monitoring and control. The dynamic monitoring module receives data in real time, compares it with the expected rice growth data, and uses genetic algorithms to optimize the control model to reduce errors. According to the real-time inspection data, the rice planting areas are grouped and managed, combined with the enzyme activity data, and the real-time fertilizer adjustment amount is output through the preset model to achieve precise fertilization.

[0125] In the optimization process, genetic algorithms are used to iteratively optimize the sowing parameters and fertilizer application amount to find the optimal solution and ensure that the rice growth is close to expectations. Combining sensor networks, bioinformatics and data analysis algorithms, precision agricultural management is achieved to maximize rice yield and quality while reducing resource waste.

[0126] The technical solution of the present invention effectively solves the problem that the sowing method and fertilization in rice planting cannot be dynamically adjusted, optimizes soil enzyme activity, and improves the yield and quality of rice planting.

Claims

1. A rice planting device with high enzyme activity, characterized in that: include: A control device, a data acquisition terminal, an enzyme activity detection device, an inspection device, a fertilization device, a sowing device and a data acquisition terminal. The control device establishes communication connections with the inspection device, the enzyme activity detection device, the fertilization device, the sowing device and the fertilization device respectively. The control device receives data collected by the data acquisition terminal and the enzyme activity detection device. The control device outputs a rice planting control command according to the data collected by the data acquisition terminal, and sends the rice planting control command to the inspection device, the fertilization device, the sowing device and the fertilization device. The control device includes: A data acquisition module is used to acquire soil parameter data, soil enzyme activity history data, enzyme activity data, environmental parameters, rice growth data, fertilizer use history data and rice planting equipment control model; A dynamic monitoring module is used to receive rice planting tasks, the rice planting tasks include rice planting location data, expected rice planting yield, rice fertilization standards and expected rice planting time information, substitute the rice planting tasks into a preset rice planting equipment control model, and obtain expected rice planting control commands, the expected rice planting control commands include expected rice seed quantity, expected rice fertilizer amount, expected rice growth data, expected rice fertilization data, expected rice sowing tasks, expected rice fertilization tasks and expected rice inspection tasks; A model optimization module is used to load rice seeds in a sowing device according to an expected number of rice seeds, load fertilizers in a fertilizing device according to an expected amount of rice fertilizer, send an expected rice inspection task to the inspection device, receive inspection data collected by the inspection device after the sowing device performs the expected rice sowing task and the fertilizing device performs the expected rice fertilizing task, obtain real-time inspection data, compare the real-time inspection data with the expected rice growth data, obtain rice growth error data, if the rice growth error data exceeds a preset rice growth error range value, compare the expected rice fertilization data with the historical data of the fertilizing device, if the comparison results of the expected rice fertilization data and the historical data of the fertilizing device are consistent, the rice fertilization is normal, obtain the historical data of the sowing device, use the rice growth error data, the expected rice growth data and the historical data of the sowing device to optimize the rice planting equipment control model using a genetic algorithm, and obtain an optimized rice planting equipment control model; The rice planting monitoring module is used to collect the real-time regional data of rice planting, group the real-time regional data of rice planting, obtain the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area, establish an inspection task for the first rice planting area, obtain the rice planting task, substitute the rice planting task into the optimized rice planting equipment control model, and output the optimized expected rice growth data; The rice fertilization optimization module is used to transmit the inspection tasks of the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area to the inspection device, obtain the enzyme activity data of the partition to be processed, substitute the enzyme activity data of the partition to be processed into the preset enzyme activity adjustment model, and output the real-time fertilization adjustment amount.

2. The rice planting equipment with high enzyme activity as claimed in claim 1, characterized in that: The model optimization module is also used for: Collating rice growth error data, which includes the difference between the actual observed rice growth and the expected rice growth data; Expected rice growth data, used to reflect the growth state that rice should achieve based on the preliminary prediction of the rice planting task and the rice planting equipment control model; Obtaining historical data of the sowing device, which includes historical sowing records, seed quality and sowing time, and is used to analyze the impact of the sowing process on rice growth; Receive and set the optimization goal, and set the optimization goal to minimize the rice growth error, even if the actual rice growth data is close to the expected rice growth data, and use the sowing density and seed variety as adjustment parameters in the optimization process; Designing a chromosome structure of a genetic algorithm, each chromosome represents a set of sowing parameter combinations, the sowing parameter combinations include sowing density, seed variety, sowing frequency of a sowing device, and sowing speed of a sowing device; Define the fitness function for evaluating each set of sowing parameters based on the rice growth error data, that is, the quality of each chromosome. The higher the fitness, the closer the rice growth under this set of sowing parameters is to the expectation. Set and configure the parameters of the genetic algorithm, including population size, number of iterations, crossover probability, and mutation probability; Initialize the population and generate a set of random seeding parameter combinations as the initial solution; Calculate the fitness value of each chromosome in the current population; According to the fitness value, excellent chromosomes are selected for reproduction and crossover to generate new chromosome offspring; Perform mutation operations on the newly generated chromosomes, update the population, and replace some old chromosomes with the newly generated chromosomes; Repeat the iterative process until the preset number of iterations is reached or the fitness value meets certain conditions; The chromosome with the highest fitness is selected from the final population as the optimized seeding parameter combination.

3. The rice planting equipment with high enzyme activity as claimed in claim 1, characterized in that: The rice planting monitoring module is also used for: Collect real-time regional data of rice planting, group the real-time regional data of rice planting to obtain the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area, establish an inspection task for the first rice planting area to obtain the first rice planting area inspection task, establish an inspection task for the second rice planting area to obtain the second rice planting area inspection task, establish an inspection task for the third rice planting area to obtain the third rice planting area inspection task, establish an inspection task for the fourth rice planting area to obtain the fourth rice planting area inspection task, combine the first rice planting area inspection task, the second rice planting area inspection task, the third rice planting area inspection task and the fourth rice planting area inspection task into a rice planting task, substitute the rice planting task into the optimized rice planting equipment control model, and output the optimized expected rice growth data.

4. The rice planting equipment with high enzyme activity as claimed in claim 1, characterized in that: The rice fertilization optimization module is also used for: The first rice planting area inspection task, the second rice planting area inspection task, the third rice planting area inspection task and the fourth rice planting area inspection task are transmitted to the inspection device, and the inspection data of the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area fed back by the inspection device are received to obtain the partition real-time inspection data, and the partition real-time inspection data is compared with the optimized expected rice growth data to obtain the partition rice growth comparison result. If there is a rice planting area whose growth data is lower than the optimized expected rice growth data in the partition real-time inspection data, then the rice planting area whose growth data is lower than the optimized expected rice growth data is obtained. The historical fertilization data of the domain is obtained, and the enzyme activity detection device is used to detect the enzyme activity of the rice planting area below the optimized expected rice growth data to obtain the enzyme activity data of the partition to be processed, the enzyme activity data of the partition to be processed is substituted into the preset enzyme activity adjustment model, the real-time fertilization adjustment amount is output, the real-time fertilization adjustment amount is sent to the fertilization device, the fertilization device fertilizes according to the real-time fertilization adjustment amount, and uses a genetic algorithm to optimize the real-time fertilization adjustment amount until there is no rice planting area below the optimized expected rice growth data in the real-time inspection data of the partition or the final iteration time and the maximum number of iterations are met, and the real-time fertilization adjustment amount is stopped for optimization.

5. A method for planting rice with high enzyme activity, applied to the rice planting equipment with high enzyme activity as claimed in claims 1 to 4, characterized in that: include: Step S101, obtaining soil parameter data, soil enzyme activity history data, enzyme activity data, environmental parameters, rice growth data, fertilization use history data and rice planting equipment control model; Step S102, receiving a rice planting task, the rice planting task includes rice planting location data, expected rice planting yield, rice fertilization standard and expected rice planting time information, substituting the rice planting task into a preset rice planting equipment control model to obtain an expected rice planting control command, the expected rice planting control command includes an expected number of rice seeds, an expected amount of rice fertilizer, expected rice growth data, expected rice fertilization data, an expected rice sowing task, an expected rice fertilization task and an expected rice inspection task; Step S103, according to the expected number of rice seeds, rice seeds are loaded in the sowing device, according to the expected amount of rice fertilizer, fertilizers are loaded in the fertilizing device, the expected rice inspection task is sent to the inspection device, the inspection data collected by the inspection device after the sowing device performs the expected rice sowing task and the fertilizing device performs the expected rice fertilizing task are received, and real-time inspection data are obtained, and the real-time inspection data is compared with the expected rice growth data to obtain rice growth error data. If the rice growth error data exceeds the preset rice growth error range value, the expected rice fertilization data is compared with the historical data of the fertilizing device. If the comparison result of the expected rice fertilization data and the historical data of the fertilizing device is consistent, the rice fertilization is normal, and the historical data of the sowing device is obtained. The rice growth error data, the expected rice growth data and the historical data of the sowing device are used to optimize the rice planting equipment control model using a genetic algorithm to obtain the optimized rice planting equipment control model; Step S104, collecting real-time rice planting area data, grouping the real-time rice planting area data to obtain a first rice planting area, a second rice planting area, a third rice planting area and a fourth rice planting area, establishing an inspection task for the first rice planting area, obtaining a rice planting task, substituting the rice planting task into the optimized rice planting equipment control model, and outputting the optimized expected rice growth data; Step S105 is used to transmit the first rice-growing area inspection task, the second rice-growing area inspection task, the third rice-growing area inspection task and the fourth rice-growing area inspection task to the inspection device, obtain the enzyme activity data of the partition to be processed, substitute the enzyme activity data of the partition to be processed into the preset enzyme activity adjustment model, and output the real-time fertilization adjustment amount.

6. The method for growing rice with high enzyme activity according to claim 5, characterized in that: The step S103 further includes: Collating rice growth error data, which includes the difference between the actual observed rice growth and the expected rice growth data; Expected rice growth data, used to reflect the growth state that rice should achieve based on the preliminary prediction of the rice planting task and the rice planting equipment control model; Obtaining historical data of the sowing device, which includes historical sowing records, seed quality and sowing time, and is used to analyze the impact of the sowing process on rice growth; Receive and set the optimization goal, and set the optimization goal to minimize the rice growth error, even if the actual rice growth data is close to the expected rice growth data, and use the sowing density and seed variety as adjustment parameters in the optimization process; Designing a chromosome structure of a genetic algorithm, each chromosome represents a set of sowing parameter combinations, the sowing parameter combinations include sowing density, seed variety, sowing frequency of a sowing device, and sowing speed of a sowing device; Define the fitness function for evaluating each set of sowing parameters based on the rice growth error data, that is, the quality of each chromosome. The higher the fitness, the closer the rice growth under this set of sowing parameters is to the expectation. Set and configure the parameters of the genetic algorithm, including population size, number of iterations, crossover probability, and mutation probability; Initialize the population and generate a set of random seeding parameter combinations as the initial solution; Calculate the fitness value of each chromosome in the current population; According to the fitness value, excellent chromosomes are selected for reproduction and crossover to generate new chromosome offspring; Perform mutation operations on the newly generated chromosomes, update the population, and replace some old chromosomes with the newly generated chromosomes; Repeat the iterative process until the preset number of iterations is reached or the fitness value meets certain conditions; The chromosome with the highest fitness is selected from the final population as the optimized seeding parameter combination.

7. The method for growing rice with high enzyme activity according to claim 5, characterized in that: The step S104 further includes: Collect real-time regional data of rice planting, group the real-time regional data of rice planting to obtain the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area, establish an inspection task for the first rice planting area to obtain the first rice planting area inspection task, establish an inspection task for the second rice planting area to obtain the second rice planting area inspection task, establish an inspection task for the third rice planting area to obtain the third rice planting area inspection task, establish an inspection task for the fourth rice planting area to obtain the fourth rice planting area inspection task, combine the first rice planting area inspection task, the second rice planting area inspection task, the third rice planting area inspection task and the fourth rice planting area inspection task into a rice planting task, substitute the rice planting task into the optimized rice planting equipment control model, and output the optimized expected rice growth data.

8. The method for growing rice with high enzyme activity according to claim 5, characterized in that: The step S105 further includes: The first rice planting area inspection task, the second rice planting area inspection task, the third rice planting area inspection task and the fourth rice planting area inspection task are transmitted to the inspection device, and the inspection data of the first rice planting area, the second rice planting area, the third rice planting area and the fourth rice planting area fed back by the inspection device are received to obtain the partition real-time inspection data, and the partition real-time inspection data is compared with the optimized expected rice growth data to obtain the partition rice growth comparison result. If there is a rice planting area whose growth data is lower than the optimized expected rice growth data in the partition real-time inspection data, then the rice planting area whose growth data is lower than the optimized expected rice growth data is obtained. The historical fertilization data of the domain is obtained, and the enzyme activity detection device is used to detect the enzyme activity of the rice planting area below the optimized expected rice growth data to obtain the enzyme activity data of the partition to be processed, the enzyme activity data of the partition to be processed is substituted into the preset enzyme activity adjustment model, the real-time fertilization adjustment amount is output, the real-time fertilization adjustment amount is sent to the fertilization device, the fertilization device fertilizes according to the real-time fertilization adjustment amount, and uses a genetic algorithm to optimize the real-time fertilization adjustment amount until there is no rice planting area below the optimized expected rice growth data in the real-time inspection data of the partition or the final iteration time and the maximum number of iterations are met, and the real-time fertilization adjustment amount is stopped for optimization.

Images