Agricultural product production process intelligent supervision system and method based on big data analysis

Abstract

The invention provides an agricultural product production process intelligent supervision system and method based on big data analysis. The system comprises a data acquisition assembly, a data analysis assembly and a management planning assembly. The method comprises the following steps: deploying various sensors in a field for automatically collecting target data, and uploading the target data to a data analysis component in real time; analyzing the target data by using the collected target data through an agricultural product production data analysis algorithm to obtain the change trend of the soil nutrient content, and predicting when to apply fertilizer and the amount of the fertilizer; meanwhile, pest and disease damage is predicted, and a corresponding prevention and control scheme is provided; suggestions are provided for irrigation according to historical data and current environmental conditions; the analysis result is applied to an agricultural product planting area; the agricultural product planting area plans the planting layout of agricultural products by means of satellite remote sensing and a geographic information system. The agricultural production efficiency and economic benefits are improved, and powerful technical support is provided for agricultural sustainable development.

Description

Technical Field

[0001] The present invention relates to the technical field of big data analysis, and particularly to an intelligent supervision system and method for the agricultural product production process based on big data analysis. Background Art

[0002] The intelligent supervision of the agricultural product production process refers to the use of modern information technology and intelligent technology to monitor and manage all aspects of agricultural production in real time, so as to improve agricultural production efficiency, reduce costs, and ensure the quality and safety of agricultural products, thereby realizing the intelligence, precision, and traceability of agricultural production. Its background art mainly involves: Internet of Things technology (IoT), data technology, cloud computing technology, artificial intelligence (AI) technology, geographic information system (GIS) and remote sensing technology, intelligent robots and automation equipment, blockchain technology, and mobile Internet technology, etc.

[0003] Prior Art One, Application No.: CN202010979248.2 discloses an intelligent agricultural management system based on the Internet of Things, which includes an intelligent terminal, a cloud service system, and a user terminal. The intelligent terminal is installed on agricultural operation equipment to collect various working data of agricultural machinery equipment and upload them to the cloud service system. The cloud service system is a big data system composed of a service-oriented modular system architecture. After registering and logging in through the user terminal, the user can access the cloud service system. Although it is based on an intelligent terminal with Internet of Things technology as the core and cloud technology as the technical means, and combines all parties involved in agricultural production to establish a management system for intelligent agricultural machinery, realizing the intelligent control of machinery, precision agricultural production, and pesticide supervision, tracking the agricultural product production process, and forming an active community-style platform with high credibility; however, its data collection technical features are relatively single, and the collection of passing data is not realized, resulting in inaccurate management results and unable to accurately control agriculture.

[0004] Prior Art Two, Application No.: CN202110499242.X discloses a traceable self-feedback learning urban plant factory, which includes an application layer, a contract layer, and a service layer; the application layer includes a number of independent soilless cultivation systems and a traceability platform; the contract layer receives the data collected by the application layer through the Internet of Things interface and executes the contract; the service layer includes an artificial intelligence platform, a big data platform, and a blockchain platform. The artificial intelligence platform includes a model training unit and a model storage unit, and the model storage unit is used to store the plant growth model and the production parameter optimization model. Although it can perform real-time statistics and analysis on the plants from the initial seedling stage to flowering and fruiting, and conduct plant growth research in an automatic self-feedback manner. At the same time, with the help of blockchain technology, it improves the quality supervision and service level of agricultural products through information means, and realizes the goal of "production process recordable, product flow traceable, storage and transportation information queryable, and quality problems traceable" in agricultural product quality management; however, it is overly dependent on the accuracy of sample data, resulting in a relatively long cycle for real-time statistics and analysis.

[0005] Prior Art Three, Application No.: CN202410202067.7 discloses a greenhouse crop growth monitoring and management system and method based on data analysis, which includes a sensor module, an intelligent control module, and a feedback loop module. The sensor module includes a temperature sensor, a humidity sensor, a light sensor, a CO 2 concentration sensor, a soil temperature and humidity sensor, and an imaging sensor. The intelligent control module includes a crop growth model sub-module, a data reception and analysis sub-module, an environment control sub-module, an image analysis and status evaluation sub-module, an automatic control sub-module, a data recording and strategy adjustment sub-module, and an anomaly detection and warning sub-module. The feedback loop module feeds back the actual crop performance to the system for improving the prediction model and control strategy, thereby realizing intelligent closed-loop production process control. Although it is data-based and realizes efficient and resource-saving greenhouse agricultural production through intelligent environment control and crop management, which helps to meet the growing demand for agricultural products and promote sustainable agricultural development; however, its data processing method is single and does not perform fusion processing on multiple data, making the accuracy of monitoring and management results need to be further improved.

[0006] Currently, there are problems in Prior Art One, Prior Art Two, and Prior Art Three, such as data transmission delay near the data collection points, slow system response speed, and the need to further improve the automation level of the operation of supervision equipment. Therefore, the present invention provides an intelligent supervision system and method for the agricultural product production process based on big data analysis. Summary of the Invention

[0007] In order to solve the above technical problems, the present invention provides an intelligent supervision system for the agricultural product production process based on big data analysis, which includes:

[0008] The data acquisition component is responsible for deploying various sensors in the field to automatically collect target data on soil moisture, nutrient content, and meteorological conditions, and upload the target data to the data analysis component in real time;

[0009] The data analysis component is responsible for analyzing the target data collected using the agricultural product production data analysis algorithm to obtain the change trend of soil nutrient content, predict when fertilization is required and the amount of fertilizer; at the same time, predict the occurrence of pests and diseases and propose corresponding prevention and control plans; provide suggestions for irrigation based on historical data and current environmental conditions;

[0010] The management and planning component is responsible for implementing the analysis results of the data analysis component in the agricultural product planting area; the agricultural product planting area uses satellite remote sensing and geographic information systems to plan the planting layout of agricultural products.

[0011] Optionally, the data acquisition component includes:

[0012] The sensor deployment module is responsible for obtaining the types of sensors to be deployed in the field according to the types of target data, constructing all sensors into a wireless sensor network, obtaining the number of sensor nodes and the size of the deployment area from the wireless sensor network, getting the location of the sensor node aggregation node, and randomly pre-deploying all sensor nodes in the deployment area;

[0013] The utility value calculation module is responsible for setting up a coordinate system in the deployment area, recording the coordinate set of sensor nodes after random pre-deployment, and recording the coordinates of all deployed sensor nodes in the wireless sensor network as the deployment strategy set; calculating the utility value of each sensor according to the sensing coverage rate of each sensor node under each deployment strategy in the deployment strategy set;

[0014] The coordinate set update module is responsible for screening the deployment strategy corresponding to the maximum utility value of the sensor node, that is, the coordinates of the sensor node, updating the coordinates of the current sensor node in the current sensor node coordinate set at this time, and sequentially updating the coordinates of the first sensor node to the last sensor node based on the utility value to obtain the updated sensor node coordinate set.

[0015] Optionally, among them, the expression for calculating the utility value U i is:

[0016]

[0017] In the formula, f(S i ) represents the sensing coverage rate optimization function, ρ i represents the density of the sensor; S idenotes the perceived coverage contribution; α represents the adjustment factor, which is a function that decreases as density increases; β represents a positive constant; i represents a sensor; g(E i ,P max ) represents the energy consumption weighting function; E i denotes the energy consumed by the sensor; P max represents the maximum energy; M i represents the sensor operating mode; U i ′ represents the task urgency; γ and δ are positive coefficients used to adjust the influence of the operating mode and task urgency; h(C i ,D max ,F max ) represents the communication cost dynamic adjustment function; C i denotes the communication cost; D max represents the maximum communication distance; F max represents the maximum communication frequency; ∈ represents the communication distance attenuation exponent; ζ represents the frequency attenuation exponent; D i and F i are the actual communication distance and frequency respectively; k(I i ,N total ) represents the environmental interference response function; I i denotes the interference index; N total represents the total number of interference types, and different types of interference are represented by I i,j , where j ranges from 1 to N total , and the weight of each interference type is represented by w j .

[0018] Optionally, the data analysis component includes:

[0019] The data acquisition module is responsible for acquiring target data, screening soil moisture, nutrient content, and meteorological conditions from the target data; at the same time, acquiring soil type and crop growth data according to the field area, and the crop growth data includes the growth stage and growth rate;

[0020] The feature extraction module is responsible for cleaning the target data, soil type, and crop growth data to remove outliers; at the same time, extracting target features, including the change rate of nutrient content and seasonal influence;

[0021] The content calculation module is responsible for inputting the target features into the agricultural product production data analysis algorithm, identifying the change trend of soil nutrient content based on time series analysis, and predicting the timing and quantity of fertilization.

[0022] Optionally, the feature extraction module includes:

[0023] The anomaly judgment sub-module is responsible for using box plots to check for outliers in the target data; checking whether there are entries of soil types that do not conform to the actual situation for soil types; for crop growth data, checking whether there are data points that do not conform to the growth pattern.

[0024] The anomaly handling sub-module is responsible for, after determining the outliers, selecting to delete, replace or retain according to the specific situation; correcting the classification for soil type data; for crop growth data, correcting or deleting.

[0025] The index calculation sub-module is responsible for comprehensively considering the changes in soil nutrient content, the influence of meteorological conditions, and the changes in crop growth rate, and calculating the characteristic index of the change rate of nutrient content; using seasonal influence feature extraction to calculate the seasonal influence characteristic index.

[0026] Optionally, the anomaly handling sub-module includes:

[0027] The data collection unit is responsible for collecting the initial soil type values, determining the ideal or reference values of the soil type; calculating the diversity index of the current soil type, determining the ideal or reference soil type diversity index; collecting the actually measured crop growth data, determining the standardized or expected values of crop growth; obtaining the comprehensive score of the current meteorological conditions, determining the ideal or reference values of the meteorological conditions.

[0028] The numerical correction unit is responsible for calculating the corrected soil type values using the correction formula, checking whether the difference between the crop growth data and its standard value is less than the threshold; if the difference is within the threshold, calculating the adjusted crop growth data using the correction formula; if the difference is too large, deleting the data point.

[0029] The numerical analysis unit is responsible for analyzing the corrected soil type values to evaluate the degree of closeness to the ideal state; analyzing the adjusted crop growth data to evaluate the influence of meteorological conditions on crop growth; if a data point is deleted, evaluating the reason for deletion and considering whether further data collection is required.

[0030] Optionally, the content calculation module includes:

[0031] The data summarization sub-module is responsible for collecting data on various factors affecting the timing and quantity of fertilization, including soil humidity, soil nutrient content, comprehensive score of meteorological conditions, and crop growth rate score.

[0032] The parameter determination sub-module is responsible for determining various parameters, including the ideal or reference values of soil humidity, nutrient content, crop growth rate, meteorological conditions, and the adjustment coefficient.

[0033] The model optimization sub-module is responsible for validating and optimizing the constructed model, including training and testing the model using historical data, evaluating the accuracy of the model; and adjusting the model parameters according to the test results.

[0034] Optionally, the data analysis component further includes:

[0035] The probability judgment module is responsible for collecting environmental data and historical data related to plant diseases and pests, including the current time node, environmental humidity, vegetation biomass index, and climate characteristics of the geographical location; judging the occurrence probability of plant diseases and pests by analyzing the occurrence trend function in the historical data;

[0036] The analysis and quantification module is responsible for quantitatively analyzing the potential risks of plant diseases and pests by comprehensively considering disease factors, environmental correction factors, and disaster adjustment coefficients, and obtaining a risk index for judging whether immediate prevention and control measures need to be taken;

[0037] The plan generation module is responsible for dynamically adjusting the plan according to specific parameters and generating a preliminary prevention and control plan when the risk index of plant diseases and pests exceeds a predetermined threshold.

[0038] Optionally, the management and planning component includes:

[0039] The spatial analysis module is responsible for obtaining image data of the target area through satellite remote sensing technology to reveal the ecological characteristics of the target area; fusing and analyzing the remote sensing image data with geographical data such as terrain, climate, and soil type, and generating a series of thematic maps based on spatial analysis with the help of a geographic information system;

[0040] The deep matching module is responsible for quantitatively analyzing the planting suitability of the area according to the growth characteristics and requirements of crops, generating an adaptability score for each area; and performing deep matching between the land and the crops;

[0041] The layout confirmation module is responsible for planning the optimal planting layout using the spatial analysis tool of the geographic information system after completing the adaptability score; determining the planting area and rotation pattern through hotspot analysis.

[0042] An intelligent supervision method for the agricultural product production process based on big data analysis provided by the present invention includes the following steps:

[0043] Deploy various sensors in the field to automatically collect target data such as soil humidity, nutrient content, and meteorological conditions, and the target data is uploaded to the data analysis component in real time;

[0044] Using the collected target data, through the agricultural product production data analysis algorithm, analyze the target data to obtain the change trend of soil nutrient content, predict when fertilization is needed and the amount of fertilizer; at the same time, predict the occurrence of pests and diseases and propose corresponding prevention and control plans; provide suggestions for irrigation according to historical data and current environmental conditions;

[0045] Implement the analysis results of the data analysis component to the agricultural product planting area; the agricultural product planting area uses satellite remote sensing and geographic information system to plan the planting layout of agricultural products.

[0046] The data collection component of the present invention collects target data such as soil humidity, nutrient content and meteorological conditions in the field through various sensors. The target data can more accurately grasp the farmland environment and the growth status of crops, providing a solid foundation for data analysis and decision-making. The data analysis component uses algorithms to deeply analyze the collected data, predict the change trend of soil nutrients, determine the best timing and amount of fertilization, prevent pests and diseases, and provide scientific suggestions for irrigation; through scientific data analysis and prediction, agricultural production management can be carried out more accurately, reducing resource waste and improving the yield and quality of crops. The significance lies in realizing the intelligence and automation of agricultural production, reducing human dependence, and improving agricultural production efficiency and economic benefits. The management planning component implements the analysis results of the data analysis component to the actual agricultural product planting area and uses satellite remote sensing and geographic information system to plan the planting layout of agricultural products; guiding actual agricultural production activities through accurate data analysis results to achieve precision agriculture. Its significance lies in that it can help farmers better plan and manage crop planting, optimize resource allocation, improve land utilization rate, and ultimately achieve sustainable agricultural development.

[0047] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the written specification and the drawings.

[0048] The technical solutions of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0049] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0050] Figure 1 It is a block diagram of an intelligent supervision system for agricultural product production process based on big data analysis in Embodiment 1 of the present invention;

[0051] Figure 2It is the block diagram of the data acquisition component in Embodiment 2 of the present invention;

[0052] Figure 3 It is the block diagram of the data analysis component in Embodiment 3 of the present invention Figure 1 ;

[0053] Figure 4 It is the block diagram of the feature extraction module in Embodiment 4 of the present invention;

[0054] Figure 5 It is the block diagram of the exception handling sub-module in Embodiment 5 of the present invention;

[0055] Figure 6 It is the block diagram of the content calculation module in Embodiment 6 of the present invention;

[0056] Figure 7 It is the block diagram of the data analysis component in Embodiment 7 of the present invention Figure 2 ;

[0057] Figure 8 It is the block diagram of the management planning component in Embodiment 8 of the present invention;

[0058] Figure 9 It is the flowchart of the intelligent supervision method for the agricultural product production process based on big data analysis in Embodiment 9 of the present invention. Detailed implementation manners

[0059] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only for explaining and illustrating the present invention, and are not used to limit the present invention.

[0060] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the embodiments of the present application. The singular forms "a", "the" and "said" used in the embodiments of the present application are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0061] When the following description relates to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are only examples of devices and methods consistent with some aspects of the present application. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and do not have to be used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0062] Example 1: As Figure 1 shown, an embodiment of the present invention provides an intelligent supervision system for the agricultural product production process based on big data analysis, including:

[0063] A data collection component, responsible for deploying various sensors in the field to automatically collect target data such as soil humidity, nutrient content, and meteorological conditions (such as temperature, humidity, light, etc.), and the target data is uploaded to the data analysis component in real time;

[0064] A data analysis component, responsible for using the collected target data, through the agricultural product production data analysis algorithm, to analyze the target data, obtain the change trend of soil nutrient content, predict when fertilization is needed and the amount of fertilization; at the same time, predict the occurrence of pests and diseases and propose corresponding prevention and control plans; provide suggestions for irrigation according to historical data and current environmental conditions;

[0065] A management and planning component, responsible for implementing the analysis results of the data analysis component to the agricultural product planting area; the agricultural product planting area plans the planting layout of agricultural products with the help of satellite remote sensing and geographic information systems.

[0066] The working principle and beneficial effects of the above technical solution are as follows: The data acquisition component in this embodiment deploys various sensors in the field to automatically collect target data such as soil humidity, nutrient content, and meteorological conditions (such as temperature, humidity, light, etc.). The target data is uploaded to the data analysis component in real time. The data analysis component uses the collected target data and, through the agricultural product production data analysis algorithm, analyzes the target data to obtain the change trend of soil nutrient content, predicts when fertilization is needed and the amount of fertilization, predicts the occurrence of pests and diseases at the same time, and proposes corresponding prevention and control plans. According to historical data and current environmental conditions, it provides suggestions for irrigation. The management and planning component implements the analysis results of the data analysis component to the agricultural product planting area. The agricultural product planting area plans the planting layout of agricultural products with the help of satellite remote sensing and geographic information system. The data acquisition component in the above solution collects target data such as soil humidity, nutrient content, and meteorological conditions in the field through various sensors. The target data can more accurately grasp the farmland environment and the growth status of crops, providing a solid foundation for data analysis and decision-making. The data analysis component uses algorithms to deeply analyze the collected data, predicts the change trend of soil nutrients, determines the best timing and amount of fertilization, prevents pests and diseases, and provides scientific suggestions for irrigation. Through scientific data analysis and prediction, agricultural production management can be carried out more accurately, resource waste can be reduced, and the yield and quality of crops can be improved. The significance lies in realizing the intellectualization and automation of agricultural production, reducing human dependence, and improving agricultural production efficiency and economic benefits. The management and planning component implements the analysis results of the data analysis component to the actual agricultural product planting area and plans the planting layout of agricultural products with the help of satellite remote sensing and geographic information system. Guided by accurate data analysis results, actual agricultural production activities are carried out to achieve precision agriculture. Its significance lies in that it can help farmers better plan and manage crop planting, optimize resource allocation, improve land utilization rate, and ultimately achieve sustainable agricultural development.

[0067] In summary, through the collaborative work of each component in this embodiment, the digital, intelligent, and precise management of agricultural production is realized, which not only improves agricultural production efficiency and economic benefits, but also provides strong technical support for the sustainable development of agriculture.

[0068] Embodiment 2: As Figure 2 shown, on the basis of Embodiment 1, the data acquisition component provided by the embodiment of the present invention includes:

[0069] The sensor deployment module is responsible for obtaining the types of sensors that need to be deployed in the field according to the types of target data, constructing all sensors into a wireless sensor network, obtaining the number of sensor nodes and the size of the deployment area from the wireless sensor network, getting the positions of the sensor node aggregation nodes, and randomly pre-deploying all sensor nodes within the deployment area;

[0070] The utility value calculation module is responsible for setting up a coordinate system in the deployment area, recording the coordinate set of sensor nodes after random pre-deployment, and denoting the coordinates of all deployed sensor nodes in the wireless sensor network as the deployment policy set; calculating the utility value of each sensor according to the sensing coverage rate of each sensor node under each deployment policy in the deployment policy set.

[0071] Among them, the expression for calculating the utility value U of each sensor i is:

[0072]

[0073] In the formula, f(S i ) represents the sensing coverage rate optimization function, ρ i represents the density of the sensor; S i represents the contribution of the sensing coverage rate; α represents the adjustment factor, which is a function that decreases as the density increases; β represents a positive constant; i represents the sensor; g(E i , P max ) represents the energy consumption weighting function; E i represents the energy consumed by the sensor; P max represents the maximum energy; M i represents the working mode of the sensor; U i ′ represents the task urgency; γ and δ are positive coefficients used to adjust the influence of the working mode and task urgency; h(C i , D max , F max ) represents the communication cost dynamic adjustment function; C i represents the communication cost; D max represents the maximum communication distance; F max represents the maximum communication frequency; ∈ represents the communication distance attenuation exponent; ζ represents the frequency attenuation exponent; D i and F i are the actual communication distance and frequency respectively; k(I i , N total ) represents the environmental interference response function; I i represents the interference index; N total represents the total number of interference types, and different types of interference are represented by I i,j , j ranges from 1 to N total , and the weight of each interference type is represented by w j ;

[0074] The coordinate set update module is responsible for screening the deployment strategy corresponding to the maximum utility value of the sensor node, that is, the coordinates of the sensor node, updating the coordinates of the current sensor node in the current sensor node coordinate set at this time, and updating the coordinates of the first sensor node to the last sensor node in sequence based on the utility value to obtain the updated sensor node coordinate set.

[0075] The working principle and beneficial effects of the above technical solution are as follows: The sensor deployment module in this embodiment obtains the types of sensors that need to be deployed in the field according to the type of target data, constructs all sensors into a wireless sensor network, obtains the number of sensor nodes and the size of the deployment area from the wireless sensor network, and gets the positions of the sensor node sink nodes, and randomly pre-deploys all sensor nodes within the deployment area; The utility value calculation module sets up a coordinate system in the deployment area, records the sensor node coordinate set after random pre-deployment, and the coordinates of all deployed sensor nodes in the wireless sensor network are recorded as the deployment strategy set; calculates the utility value of each sensor according to the sensing coverage rate of each sensor node under each deployment strategy in the deployment strategy set; The coordinate set update module screens the deployment strategy corresponding to the maximum utility value of the sensor node, that is, the coordinates of the sensor node, updates the coordinates of the current sensor node in the current sensor node coordinate set at this time, and updates the coordinates of the first sensor node to the last sensor node in sequence based on the utility value to obtain the updated sensor node coordinate set. The sensor deployment module of the above solution can flexibly adapt to the changing environment and ensure the comprehensiveness of data collection. Its technical effects are reflected in being able to quickly deploy sensors according to actual needs and form a widely covered network; it can monitor the growth status of crops in real time, improve crop yield and quality. The utility value calculation module helps to understand the value and importance of each sensor in the network; it can optimize the deployment strategy of sensor nodes to ensure the efficient operation of the network; through optimization of the deployment, it can improve the accuracy and reliability of data collection, thereby enhancing the overall agricultural production efficiency. The coordinate set update module can dynamically adjust the layout of sensors to adapt to environmental changes and data collection requirements; dynamic adjustment is crucial for realizing precision agriculture because it helps to improve resource utilization efficiency, reduce waste, and can better respond to situations such as pests and diseases.

[0076] In summary, the three modules in this embodiment jointly constitute an intelligent data collection system, collaborating with each other, not only improving the efficiency and accuracy of data collection, but also playing an important role in promoting the intelligent and precise management of agriculture; it can better understand and manage agricultural production, and improve the yield and quality of crops.

[0077] Embodiment 3: As Figure 3 shown, on the basis of Embodiment 1, the data analysis component provided by the embodiment of the present invention includes:

[0078] A data acquisition module, responsible for acquiring target data, screening soil humidity, nutrient content, and meteorological conditions from the target data; at the same time, obtaining soil type and crop growth data according to the region where the field is located, and the crop growth data includes growth stage, growth rate, etc.;

[0079] Among them, the expression of the overall data acquisition score of the data acquisition module is:

[0080]

[0081] In the formula, F total represents the overall data acquisition score, which is used to measure the integrity and accuracy of data acquisition, and can more accurately reflect the comprehensive processing ability of the data acquisition module for target data; S h represents the soil humidity value; N n represents the soil nutrient content; M m represents the comprehensive score of meteorological conditions, which can be a comprehensive score based on multiple meteorological factors such as temperature and rainfall; T t represents the soil type score, which is scored according to the impact of soil type on crop growth; S s represents the crop growth rate score; C c represents the crop growth stage score, considering the differences in nutrient and water requirements at different growth stages; A h represents the ideal value or reference value of soil humidity; A n represents the ideal value or reference value of soil nutrient content; B s represents the ideal value or reference value of crop growth rate; e is the base of the natural logarithm, approximately equal to 2.71828;

[0082] A feature extraction module, responsible for cleaning the target data, soil type, and crop growth data to remove outliers; at the same time, extracting target features, including the change rate of nutrient content and seasonal influence, etc.;

[0083] A content calculation module, responsible for inputting the target features into the agricultural product production data analysis algorithm, identifying the change trend of soil nutrient content based on time series analysis, and predicting the timing and quantity of fertilization.

[0084] The working principle and beneficial effects of the above technical solution are as follows: The data acquisition module in this embodiment acquires target data, and filters out soil humidity, nutrient content, and meteorological conditions from the target data. At the same time, according to the region where the field is located, it acquires soil type and crop growth data, and the crop growth data includes growth stage, growth rate, etc. The feature extraction module performs data cleaning on the target table data, soil type, and crop growth data to remove outliers. At the same time, it extracts target features, including the change rate of nutrient content and seasonal influence, etc. The content calculation module inputs the target features into the agricultural product production data analysis algorithm, and based on time series analysis, identifies the change trend of soil nutrient content, and predicts the timing and quantity of fertilization. The data acquisition module of the above solution can comprehensively understand the environment for crop growth, which is crucial for formulating field management measures such as irrigation and fertilization. The feature extraction module extracts important features from the data, such as the change rate of nutrient content and seasonal influence. Through feature extraction, the key factors affecting crop growth can be identified, which has important guiding significance for predicting crop yields and formulating scientific field management strategies. The content calculation module inputs the extracted features into the data analysis algorithm, and uses methods such as time series analysis to identify the change trend of soil nutrient content, and predicts the best timing and quantity of fertilization. By predicting the change trend of soil nutrient content, fertilization can be managed more precisely, avoiding over-fertilization or under-fertilization, thereby improving the yield and quality of crops, while reducing resource waste and environmental pollution.

[0085] In summary, this embodiment can better understand the environment and conditions for crop growth, predict and optimize field management measures, and ultimately achieve the purpose of improving crop yield and quality, reducing costs and environmental impacts. It not only has direct economic significance for agricultural producers, but also has a profound impact on environmental protection and sustainable development.

[0086] Example 4: As Figure 4 shown, on the basis of Example 3, the feature extraction module provided by the embodiment of the present invention includes:

[0087] The outlier judgment sub-module is responsible for using box plots to check whether there are outliers in the target data; checking whether there are entries of soil types that do not conform to the actual situation for the soil type; for the crop growth data, checking whether there are data points that do not conform to the growth law.

[0088] The outlier processing sub-module is responsible for, after determining the outliers, selecting to delete, replace, or retain according to the specific situation; correcting the classification for the soil type data; correcting or deleting the crop growth data.

[0089] The index calculation sub-module is responsible for comprehensively considering the changes in soil nutrient content, the impact of meteorological conditions, and the changes in crop growth rate, calculating the characteristic index of the change rate of nutrient content; using seasonal impact feature extraction to calculate the seasonal impact characteristic index.

[0090] Among them, the formula for extracting the nutrient change rate characteristics in the index calculation sub-module is:

[0091]

[0092] In the formula, F nutrient_change represents the characteristic index of the change rate of nutrient content; N n represents the current soil nutrient content; represents the soil nutrient content of the previous season; T season represents the time span of one season; A n represents the ideal value or reference value of soil nutrients; M m represents the comprehensive score of meteorological conditions; A m represents the ideal value or reference value of meteorological conditions; S s represents the crop growth rate score; B s represents the ideal value or reference value of crop growth rate; comprehensively considering the changes in soil nutrient content, the impact of meteorological conditions, and the changes in crop growth rate to calculate the change rate characteristics of nutrient content;

[0093] The formula for extracting seasonal impact characteristics is:

[0094]

[0095] In the formula, F seasonal_impact represents the seasonal impact characteristic index; T t represents the soil type score; A t represents the ideal value or reference value of soil type; combining the soil type, crop growth rate, change rate of nutrient content, and non-linear relationship to reflect the impact of seasonal factors on soil nutrient content.

[0096] The working principle and beneficial effects of the above technical solution are as follows: The anomaly judgment sub-module in this embodiment uses box plots to check for outliers in the target data; checks whether there are entries of soil types that do not conform to the actual situation for soil types; for crop growth data, checks whether there are data points that do not conform to the growth pattern. After the anomaly handling sub-module determines the outliers, it selects to delete, replace, or retain them according to the specific situation; corrects the classification for soil type data; for crop growth data, it corrects or deletes them. The index calculation sub-module synthesizes the changes in soil nutrient content, the influence of meteorological conditions, and the changes in crop growth rate, and calculates the characteristic index of the change rate of nutrient content; uses seasonal influence feature extraction to calculate the seasonal influence characteristic index. The anomaly judgment sub-module in the above solution identifies outliers in the data through methods such as box plots, entry checks, and growth pattern checks. Outliers may have a serious impact on data analysis and model training results. Correctly identifying and handling these outliers can improve data quality, thereby enhancing the accuracy and robustness of the model. The anomaly handling sub-module's reasonable handling of outliers can reduce the noise in the data, ensure the consistency and authenticity of the data set, and provide a more reliable data basis for data analysis. The indexes calculated by the index calculation sub-module can be used as features to be input into machine learning models to help understand the relationship between soil nutrients, meteorological conditions, and crop growth, as well as the impact of seasonal changes on crop growth. The characteristic indexes have important guiding significance for predicting crop yields and guiding agricultural production.

[0097] In summary, the feature extraction module in this embodiment improves data quality and extracts key information, and its significance lies in providing an accurate and reliable data basis for data analysis, thereby improving the prediction ability and practical application value.

[0098] Example 5: As Figure 5 shown, based on Example 4, the anomaly handling sub-module provided by the embodiment of the present invention includes:

[0099] The data collection unit is responsible for collecting the initial soil type values, determining the ideal or reference values of the soil types; calculating the diversity index of the current soil type, determining the ideal or reference soil type diversity index; collecting the actually measured crop growth data, determining the standardized or expected values of crop growth; obtaining the comprehensive score of the current meteorological conditions, determining the ideal or reference values of the meteorological conditions;

[0100] The numerical correction unit is responsible for calculating the corrected soil type values using the correction formula, and checking whether the difference between the crop growth data and its standard value is less than the threshold; if the difference is within the threshold, calculating the adjusted crop growth data using the correction formula; if the difference is too large, deleting the data point;

[0101] A numerical analysis unit responsible for analyzing the corrected soil type values to evaluate the proximity to the ideal state; analyzing the adjusted crop growth data to evaluate the impact of meteorological conditions on crop growth; if a data point is deleted, evaluating the reason for deletion and considering whether further data collection is required.

[0102] Among them, the soil type data correction formula:

[0103]

[0104] In the formula: C corrected represents the corrected soil type value; C initial represents the initial soil type value; C ideal represents the ideal or reference value of the soil type; D soil represents the diversity index of the current soil type; D ideal represents the ideal or reference soil type diversity index; the formula takes into account the difference between the soil type value and its ideal value and combines the diversity index of the soil type to non-linearly adjust the soil type value to make it closer to the ideal state;

[0105] Crop growth data correction or deletion formula:

[0106]

[0107] In the formula: G adjusted represents the adjusted crop growth data; G measured represents the actually measured crop growth data; G norm represents the standardized or expected value of crop growth; E climate represents the comprehensive score of the current meteorological conditions; E norm represents the ideal or reference value of the meteorological conditions; θ is a threshold used to determine whether the data needs to be adjusted or deleted; the formula first checks whether the difference between the crop growth data and its standard value is within an acceptable range; if the difference is within the threshold, it will non-linearly adjust the data according to the impact of the meteorological conditions; if the difference is too large, the data value will be directly set to, that is, the data point is deleted.

[0108] The working principle and beneficial effects of the above technical solution are as follows: The data collection unit in this embodiment collects the initial soil type value and determines the ideal or reference value of the soil type; calculates the diversity index of the current soil type and determines the ideal or reference soil type diversity index; collects the actually measured crop growth data and determines the standardized or expected value of crop growth; obtains the comprehensive score of the current meteorological conditions and determines the ideal or reference value of the meteorological conditions; the numerical correction unit uses the correction formula to calculate the corrected soil type value and checks whether the difference between the crop growth data and its standard value is less than the threshold; if the difference is within the threshold, uses the correction formula to calculate the adjusted crop growth data; if the difference is too large, deletes the data point; the numerical analysis unit analyzes the corrected soil type value to evaluate the degree of proximity to the ideal state; analyzes the adjusted crop growth data to evaluate the impact of meteorological conditions on crop growth; if a data point is deleted, evaluates the reason for deletion and considers whether further data collection is required. The data collection unit of the above solution establishes a comprehensive agricultural production data framework by collecting the comprehensive scores of soil type, diversity index, crop growth data and meteorological conditions, providing accurate baseline data for numerical correction and analysis; ensuring that all data related to agricultural production can be accurately recorded and compared, laying a solid foundation for data correction and analysis, helping agricultural managers to more accurately grasp the current situation of farmland, and thus making more scientific management decisions. The numerical correction unit uses the correction formula to correct the soil type value and compares the crop growth data with the standard value to determine the accuracy of the data; by comparing the gap between the crop growth data and the standard value, decides whether to adjust or delete the data to ensure the reliability and effectiveness of the data; through numerical correction, abnormal data can be eliminated or adjusted, avoiding the adverse impact of incorrect data on agricultural production decisions, thereby improving the accuracy and reliability of agricultural production. The numerical analysis unit analyzes the corrected soil type value and the adjusted crop growth data, evaluates the degree of proximity to the ideal state, and analyzes the impact of meteorological conditions on crop growth; if it is found that a data point is deleted, it is also necessary to evaluate the reason for deletion and consider whether further data collection is required; through in-depth analysis of the data, the correlation between soil type, crop growth data and meteorological conditions can be revealed, providing a more accurate optimization plan for agricultural production. At the same time, analyzing the reason for deleting data helps to identify possible problems in the data collection process, further optimize the data collection process, and improve data quality.

[0109] In summary, through scientific data processing and analysis, this embodiment can improve the efficiency and quality of agricultural production, reduce resource waste, enhance the stress resistance of crops, and provide technical support for the sustainable development of agriculture.

[0110] Example 6: As Figure 6As shown in the figure, on the basis of Embodiment 3, the content calculation module provided by the embodiment of the present invention includes:

[0111] A data summary sub-module, responsible for collecting data on various factors affecting fertilization timing and quantity, including soil humidity, soil nutrient content, comprehensive meteorological condition score, and crop growth rate score, etc.;

[0112] A parameter determination sub-module, responsible for determining various parameters, including the ideal value or reference value of soil humidity, the ideal value or reference value of nutrient content, the ideal value or reference value of crop growth rate, the ideal value or reference value of meteorological conditions, and adjustment coefficients;

[0113] A model optimization sub-module, responsible for validating and optimizing the constructed model, including training and testing the model using historical data, and evaluating the accuracy of the model; adjusting the model parameters according to the test results.

[0114] Among them, the fertilization timing prediction model:

[0115]

[0116] In the formula, T f represents the fertilization timing prediction score, used to measure when to fertilize; S h represents the soil humidity value; A h represents the ideal value or reference value of soil humidity; N n represents the soil nutrient content; A n represents the ideal value or reference value of soil nutrient content; S s represents the crop growth rate score; B s represents the ideal value or reference value of crop growth rate; C c represents the crop growth stage score; M m represents the comprehensive meteorological condition score; A m represents the ideal value or reference value of meteorological conditions; B h and B n respectively represent the adjustment coefficients of soil humidity and nutrient content; the model predicts the best timing of fertilization by comprehensively considering factors such as soil humidity, nutrient content, and growth rate;

[0117] The fertilization quantity prediction model:

[0118]

[0119] In the formula, Q f represents the fertilization quantity prediction score, used to measure the specific quantity of fertilization; the formula comprehensively considers multiple factors such as soil humidity, nutrient content, meteorological conditions, soil type, and crop growth stage, and predicts the timing and quantity of fertilization through complex mathematical operations to achieve the goal of precision agriculture.

[0120] The working principle and beneficial effects of the above technical solution are as follows: The data aggregation sub-module in this embodiment collects data on various factors affecting fertilization timing and quantity, including soil humidity, soil nutrient content, comprehensive score of meteorological conditions, and crop growth rate score, etc.; the parameter determination sub-module determines various parameters, including the ideal value or reference value of soil humidity, the ideal value or reference value of nutrient content, the ideal value or reference value of crop growth rate, the ideal value or reference value of meteorological conditions, and the adjustment coefficient; the model optimization sub-module verifies and optimizes the constructed model, including training and testing the model using historical data, and evaluating the accuracy of the model; according to the test results, adjusts the model parameters. The data aggregation sub-module of the above solution collects multi-dimensional data such as soil humidity, nutrient content, and meteorological conditions in real time, providing comprehensive information input for fertilization decision-making; integrating the crop growth rate score to quantify the crop growth status and providing a reference for fertilization timing; using sensors and Internet of Things technology to achieve real-time and dynamic data collection, improving the timeliness and accuracy of data. Significance: Multi-dimensional data fusion provides a scientific basis for precise fertilization, improving the pertinence and effectiveness of fertilization; real-time data collection makes fertilization decision-making more flexible and enables timely adjustment according to environmental changes; quantification and standardization of data provide a basis for model construction and parameter determination. The parameter determination sub-module determines the ideal value or reference value of each influencing factor, providing a reference standard for model construction; calculates the adjustment coefficient to quantify the influence degree of different factors on fertilization decision-making, providing a basis for model optimization; determines a reasonable parameter value range through expert experience and historical data analysis, improving the adaptability and robustness of the model. Significance: Parameter standardization enables the model to have better generalization ability in different environments and conditions; the introduction of the adjustment coefficient can quantify the influence weight of each factor, providing more refined guidance for fertilization decision-making; dynamic adjustment of parameters enables the model to adapt to environmental changes, improving the flexibility and adaptability of fertilization. The model optimization sub-module uses historical data to train and test the model, evaluating the accuracy and generalization ability of the model; according to the test results, dynamically adjusts the model parameters, optimizes the model structure, and improves the performance of the model. Significance: Model verification and optimization improve the scientificity and accuracy of fertilization decision-making, reducing resource waste caused by blind fertilization; dynamic parameter adjustment enables the model to adapt to different environments and conditions, improving the flexibility and adaptability of fertilization.

[0121] In summary, through the collaborative work of the three sub-modules of data aggregation, parameter determination, and model optimization, the content calculation module of this embodiment realizes real-time collection of multi-dimensional data, dynamic adjustment of parameters, and continuous optimization of the model, providing scientific, flexible, and refined technical support for precise fertilization, effectively improving the pertinence, effectiveness, and adaptability of fertilization, and being of great significance for improving crop yield and quality and reducing resource waste.

[0122] Example 7: As Figure 7 shown, on the basis of Example 1, the data analysis component provided by the embodiments of the present invention further includes:

[0123] A probability judgment module, responsible for collecting environmental data and historical data related to pests and diseases, including the current time node, environmental humidity, vegetation biomass index, and climate characteristics of the geographical location; judging the occurrence probability of pests and diseases by analyzing the occurrence trend function of pests and diseases in historical data;

[0124] An analysis and quantification module, responsible for quantitatively analyzing the potential risks of pests and diseases by comprehensively considering disease factors, environmental correction factors, and disaster adjustment coefficients, and obtaining a risk index for judging whether immediate prevention and control measures need to be taken;

[0125] A plan generation module, responsible for dynamically adjusting the plan according to specific parameters and generating a preliminary prevention and control plan when the pest and disease risk index exceeds a predetermined threshold.

[0126] Among them, the expression for quantitatively analyzing the potential risks of pests and diseases is:

[0127]

[0128] In the formula, R 1 represents the pest and disease risk index, the larger the value, the higher the risk; f represents the disease factor; s n (t d ) represents the occurrence trend function of pests and diseases in historical data; t d represents the current time node; h represents the relative humidity of the current environment; e(h) represents the environmental humidity logarithmic correction factor; d represents the vegetation biomass index; j 2 (h,t d ) represents the humidity and temperature interaction factor; m v (f) represents the disaster adjustment coefficient; k p (vh 2 ) represents the geographical environment characteristics.

[0129] The working principle and beneficial effects of the above technical solution are as follows: The probability judgment module of this embodiment collects environmental data and historical data related to plant diseases and insect pests, including the current time node, environmental humidity, vegetation biomass index, and climate characteristics of the geographical location; judges the occurrence probability of plant diseases and insect pests by analyzing the occurrence trend function of plant diseases and insect pests in historical data; the analysis and quantification module comprehensively considers disease factors, environmental correction factors, and disaster adjustment coefficients to quantitatively analyze the potential risks of plant diseases and insect pests, and obtains a risk index for judging whether immediate prevention and control measures need to be taken; when the plant disease and insect pest risk index exceeds a predetermined threshold, the solution generation module dynamically adjusts the solution according to specific parameters and generates a preliminary prevention and control solution. The probability judgment module of the above solution constructs an occurrence trend function of plant diseases and insect pests by collecting and integrating environmental data and historical plant disease and insect pest data, including time, humidity, vegetation biomass index, and climate characteristics; quantifies the occurrence law of plant diseases and insect pests through statistical analysis and modeling of historical data to form a high-precision prediction model; based on the current environmental dynamic data, calculates the occurrence probability of plant diseases and insect pests in real time, provides a reliable basis for decision-making; improves the accuracy and timeliness of prediction, helps to identify potential threats of plant diseases and insect pests in advance, and provides scientific support for subsequent measures. The sub-line quantification module comprehensively considers disease factors, environmental correction factors, and disaster adjustment coefficients to quantitatively analyze the potential risks of plant diseases and insect pests and generate a risk index; through multi-factor weight analysis, converts complex environmental and disease factors into quantifiable risk indicators; dynamically adjusts the risk index according to environmental changes to ensure the real-time and scientific nature of the evaluation; intuitively presents the risk level, provides a clear decision-making basis for whether to take prevention and control measures, and reduces the risk of misjudgment. The solution generation module generates highly targeted prevention and control measures according to different geographical locations, environmental conditions, and types of plant diseases and insect pests to ensure the accuracy and practicability of the solution; adjusts the solution parameters in real time to maximize the prevention and control effect while reducing the impact on the environment; realizes intelligent decision-making for plant disease and insect pest prevention and control, improves the response efficiency and resource utilization rate, and reduces losses in agricultural production.

[0130] In summary, each module of this embodiment constructs a complete plant disease and insect pest prevention and control system through data collection, analysis, and decision optimization; improves the accuracy of prediction, the controllability of risks, and the scientific nature of measures, provides strong technical support for agricultural production, and promotes the modernization and sustainable development of agriculture.

[0131] Embodiment 8: As Figure 8 shown, on the basis of Embodiment 1, the management and planning component provided by the embodiment of the present invention includes:

[0132] Spatial analysis module, responsible for obtaining image data of the target area through satellite remote sensing technology to reveal the ecological characteristics of the target area; integrating and analyzing the remote sensing image data with geographical data such as terrain, climate, and soil type, and generating a series of thematic maps based on spatial analysis with the help of a geographic information system, such as land use maps, vegetation cover maps, and soil fertility maps, etc.;

[0133] Deep matching module, responsible for quantitatively analyzing the planting suitability of the area according to the growth characteristics and requirements of crops, generating an adaptability score for each area; performing deep matching between land and crops;

[0134] Layout confirmation module, responsible for planning the optimal planting layout using the spatial analysis tools of the geographic information system after completing the adaptability score; determining the planting area and rotation pattern through hotspot analysis.

[0135] The working principle and beneficial effects of the above technical solution are as follows: The spatial analysis module of this embodiment obtains image data of the target area through satellite remote sensing technology to reveal the ecological characteristics of the target area; integrates and analyzes the remote sensing image data with geographical data such as terrain, climate, and soil type, and generates a series of thematic maps based on spatial analysis with the help of a geographic information system, such as land use maps, vegetation cover maps, and soil fertility maps, etc.; the deep matching module quantitatively analyzes the planting suitability of the area according to the growth characteristics and requirements of crops, generates an adaptability score for each area; performs deep matching between land and crops; the layout confirmation module plans the optimal planting layout using the spatial analysis tools of the geographic information system after completing the adaptability score; determines the planting area and rotation pattern through hotspot analysis. The spatial analysis module of the above solution provides high-precision spatial data support, laying a data foundation for agricultural planning; through visual thematic maps, it intuitively displays the regional ecological characteristics, assisting decision-makers to quickly master the regional resource endowment. The deep matching module realizes the deep matching between land and crops, comprehensively considering the adaptation degree between the regional environmental conditions and the physiological characteristics of crops; through quantitative analysis, accurately identifies the advantages and limiting factors of regional agricultural production; improves the use efficiency of land resources, and promotes the refined and personalized development of agricultural production. The layout confirmation module conducts multi-scenario simulation analysis on the planning results, evaluates the feasibility of the plan and its potential environmental impacts; realizes the precision and dynamic adjustment ability of agricultural production layout; enhances the regional coordination of agricultural production, promotes the sustainable use of land resources; provides scientific support for the formulation of agricultural development policies and plans, and promotes the process of agricultural modernization.

[0136] In summary, the spatial analysis module of this embodiment focuses on data acquisition and preliminary analysis; the deep matching module realizes the adaptation between land and crops through scientific evaluation, and the layout confirmation module is oriented towards the implementation of production; from data acquisition to spatial optimization.

[0137] Example 9: AsFigure 9 As shown, based on Embodiments 1 - 8, the intelligent supervision method for the agricultural product production process provided by the embodiments of the present invention includes the following steps:

[0138] S100: Deploy various sensors in the field to automatically collect target data such as soil humidity, nutrient content, and meteorological conditions (such as temperature, humidity, light, etc.), and the target data is uploaded to the data analysis component in real time;

[0139] S200: Utilize the collected target data, through the agricultural product production data analysis algorithm, analyze the target data to obtain the change trend of soil nutrient content, predict when fertilization is required and the amount of fertilization; at the same time, predict the occurrence of pests and diseases and propose corresponding prevention and control plans; provide suggestions for irrigation based on historical data and current environmental conditions;

[0140] S300: Implement the analysis results of the data analysis component to the agricultural product planting area; the agricultural product planting area plans the planting layout of agricultural products with the help of satellite remote sensing and geographic information systems.

[0141] The working principle and beneficial effects of the above technical solution are as follows: In this embodiment, various sensors are first deployed in the field to automatically collect target data such as soil humidity, nutrient content, and meteorological conditions (such as temperature, humidity, light, etc.), and the target data is uploaded to the data analysis component in real time; secondly, the collected target data is used to analyze the target data through the agricultural product production data analysis algorithm to obtain the change trend of soil nutrient content, predict when fertilization is required and the amount of fertilization; at the same time, predict the occurrence of pests and diseases and propose corresponding prevention and control plans; provide suggestions for irrigation based on historical data and current environmental conditions; finally, the analysis results of the data analysis component are implemented to the agricultural product planting area; the agricultural product planting area plans the planting layout of agricultural products with the help of satellite remote sensing and geographic information systems. The steps of the above solution realize the digital, intelligent, and precise management of agricultural production, not only improving agricultural production efficiency and economic benefits, but also providing strong technical support for the sustainable development of agriculture.

[0142] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the equivalent technology of the present invention, the present invention also intends to include these changes and modifications.

Claims

1. An intelligent monitoring system for agricultural product production process based on big data analysis, characterized in that: Include: The data acquisition component is responsible for deploying various sensors in the field to automatically collect target data such as soil moisture, nutrient content, and meteorological conditions. The target data is uploaded to the data analysis component in real time. The data analysis component is responsible for using the collected target data to analyze the target data through the agricultural product production data analysis algorithm, obtain the changing trend of soil nutrient content, predict when fertilizer is needed and the amount of fertilizer to be applied; predict the occurrence of pests and diseases and propose corresponding prevention and control plans; and provide suggestions for irrigation based on historical data and current environmental conditions; The management planning component is responsible for implementing the analysis results of the data analysis component to the agricultural product planting areas; the agricultural product planting areas use satellite remote sensing and geographic information systems to plan the planting layout of agricultural products.

2. The intelligent monitoring system for agricultural product production process based on big data analysis according to claim 1 is characterized in that: Data collection components, including: The sensor deployment module is responsible for obtaining the type of sensors that need to be deployed in the field according to the type of target data, building all sensors into a wireless sensor network, obtaining the number of sensor nodes and the size of the deployment area from the wireless sensor network, obtaining the location of the sensor node aggregation node, and randomly pre-deploying all sensor nodes in the deployment area; The utility value calculation module is responsible for setting the coordinate system in the deployment area and recording the coordinate set of the sensor nodes after random pre-deployment. The coordinates of all deployed sensor nodes in the wireless sensor network are marked as the deployment strategy set; the utility value of each sensor is calculated according to the sensing coverage of each sensor node under each deployment strategy in the deployment strategy set; The coordinate set update module is responsible for selecting the deployment strategy corresponding to the maximum utility value of the sensor node, that is, the sensor node coordinates, updating the coordinates of the current sensor node in the sensor node coordinate set at this time, and updating the coordinates of the first sensor node to the last sensor node in turn based on the utility value to obtain the updated sensor node coordinate set.

3. The intelligent monitoring system for agricultural product production process based on big data analysis according to claim 2 is characterized in that: in, Calculate the utility value U of each sensor i The expression is: In the formula, f(S i ) represents the perceptual coverage optimization function, ρ i Indicates the density of the sensor; S i represents the contribution of perceived coverage; α represents the adjustment factor, which is a function that decreases as the density increases; β represents a positive constant; i represents the sensor; g(E i ,P max ) represents the energy consumption weighting function; E i Indicates the energy consumed by the sensor; P max Indicates maximum energy; M i Indicates the sensor working mode; U′ i Indicates the task urgency; γ and δ are positive coefficients used to adjust the impact of work mode and task urgency; h(C i ,D max ,F max ) represents the communication cost dynamic adjustment function; C i represents the communication cost; D max Indicates the maximum communication distance; F max represents the maximum communication frequency; ∈ represents the communication distance attenuation index; ζ represents the frequency attenuation index; D i and F i are the actual communication distance and frequency respectively; k(I i ,N total ) represents the environmental disturbance response function; I i Represents the interference index; N total Indicates the total number of interference types, and different types of interference are represented by I i,j Indicates that j ranges from 1 to N total , the weight of each interference type is w j express.

4. The intelligent monitoring system for agricultural product production process based on big data analysis according to claim 1 is characterized in that: Data analysis components, including: The data acquisition module is responsible for acquiring target data and filtering out soil moisture, nutrient content and meteorological conditions from the target data; at the same time, it acquires soil type and crop growth data according to the area where the field is located. The crop growth data includes growth stage and growth rate; The feature extraction module is responsible for cleaning the target data, soil type and crop growth data to remove outliers; it also extracts target features, including the rate of change of nutrient content and seasonal effects; The content calculation module is responsible for inputting target features into the agricultural product production data analysis algorithm, identifying the changing trend of soil nutrient content based on time series analysis, and predicting the timing and amount of fertilization.

5. The intelligent monitoring system for agricultural product production process based on big data analysis according to claim 4 is characterized in that: Feature extraction module, including: The abnormal judgment submodule is responsible for using the box plot to check whether there are abnormal values ​​in the target data; for soil types, check whether there are any soil type entries that do not conform to the actual situation; for crop growth data, check whether there are any data points that do not conform to the growth law; The exception handling submodule is responsible for determining the outliers and choosing to delete, replace or retain them according to the specific situation; correcting the classification of soil type data; and correcting or deleting crop growth data; The indicator calculation submodule is responsible for comprehensively considering the changes in soil nutrient content, the impact of meteorological conditions, and the changes in crop growth rate to calculate the characteristic indicators of the rate of change of nutrient content; and uses seasonal impact feature extraction to calculate seasonal impact characteristic indicators.

6. The intelligent monitoring system for agricultural product production process based on big data analysis according to claim 5 is characterized in that: Exception handling submodule, including: The data collection unit is responsible for collecting the initial soil type value and determining the ideal or benchmark value of the soil type; calculating the diversity index of the current soil type and determining the ideal or benchmark soil type diversity index; collecting the actual measured crop growth data and determining the standardized or expected value of crop growth; obtaining the current comprehensive score of meteorological conditions and determining the ideal or benchmark value of meteorological conditions; The numerical correction unit is responsible for calculating the corrected soil type value using the correction formula and checking whether the difference between the crop growth data and its standard value is less than the threshold value; If the difference is within the threshold, the adjusted crop growth data is calculated using the correction formula; If the difference is too large, the data point is deleted; a numerical analysis unit, responsible for analyzing the corrected soil type values ​​to assess their proximity to the ideal state; Analyze the adjusted crop growth data to evaluate the impact of meteorological conditions on crop growth; if any data points are deleted, evaluate the reasons for the deletion and consider whether further data collection is needed.

7. The intelligent monitoring system for agricultural product production process based on big data analysis according to claim 4 is characterized in that: Content calculation module, including: The data aggregation submodule is responsible for collecting data on various factors that affect the timing and amount of fertilization, including soil moisture, soil nutrient content, comprehensive scores of meteorological conditions, and crop growth rate scores; The parameter determination submodule is responsible for determining various parameters, including the ideal value or benchmark value of soil moisture, the ideal value or benchmark value of nutrient content, the ideal value or benchmark value of crop growth rate, the ideal value or benchmark value of meteorological conditions, and adjustment coefficients; The model optimization submodule is responsible for verifying and optimizing the constructed model, including training and testing the model using historical data and evaluating the accuracy of the model; According to the test results, adjust the model parameters.

8. The intelligent monitoring system for agricultural product production process based on big data analysis according to claim 1 is characterized in that: The data analysis component also includes: The probability judgment module is responsible for collecting environmental data and historical data related to pests and diseases, including the current time node, environmental humidity, vegetation biomass indicators, and climate characteristics of the geographical location; By analyzing the pest and disease occurrence trend function in historical data, the probability of pest and disease occurrence can be determined; The analysis and quantification module is responsible for conducting quantitative analysis of the potential risks of pests and diseases by comprehensively considering disease factors, environmental correction factors and disaster adjustment coefficients, and obtaining a risk index to determine whether immediate prevention and control measures are needed; The plan generation module is responsible for dynamically adjusting the plan according to specific parameters and generating a preliminary prevention and control plan when the pest and disease risk index exceeds the preset threshold.

9. The intelligent monitoring system for agricultural product production process based on big data analysis according to claim 1, characterized in that: Management planning components, including: The spatial analysis module is responsible for obtaining image data of the target area through satellite remote sensing technology to reveal the ecological characteristics of the target area; integrating remote sensing image data with geographical data on terrain, climate and soil type, and generating a series of thematic maps based on spatial analysis with the help of geographic information system; The deep matching module is responsible for quantitatively analyzing the planting suitability of a region based on the growth characteristics and needs of the crop, generating an adaptability score for each region, and performing deep matching between land and crops; The layout confirmation module is responsible for planning the optimal planting layout using the spatial analysis tools of the geographic information system after completing the adaptability scoring; Determine planting areas and rotation patterns through hotspot analysis.

10. An intelligent supervision method for agricultural product production process based on big data analysis, characterized in that: The following steps are involved: Various sensors are deployed in the field to automatically collect target data on soil moisture, nutrient content and meteorological conditions, which are then uploaded to the data analysis component in real time; Utilize the collected target data and agricultural product production data analysis algorithms to analyze the target data, obtain the changing trend of soil nutrient content, predict when fertilizer is needed and the amount of fertilizer to be applied; predict the occurrence of pests and diseases and propose corresponding prevention and control plans; provide suggestions for irrigation based on historical data and current environmental conditions; The analysis results of the data analysis component are implemented in the agricultural product planting areas; the agricultural product planting areas plan the planting layout of agricultural products with the help of satellite remote sensing and geographic information systems.

Images