A smart agricultural management system based on the IoT cloud big model

Abstract

The invention discloses a smart agricultural management system based on a large model of the Internet of Things cloud, and relates to the technical field of smart agricultural management. The smart agricultural management system based on the large model of the Internet of Things cloud includes an irrigation intelligent control module, a pest and disease detection and early warning module, a user interface and a visualization module, obtains an irrigation monitoring and evaluation index based on real-time monitored crop irrigation related information, detects the current irrigation demand of crops, uses the irrigation monitoring and evaluation index to match the irrigation records stored in a database, and performs intelligent irrigation control on crops; performs real-time monitoring of the environment and growth conditions of crops that implement intelligent irrigation control, performs pest and disease detection and early warning on crops based on pest and disease related monitoring information obtained by real-time monitoring and pest and disease record information stored in a database; and automatically generates a smart agricultural management report based on the pest and disease detection and early warning results and irrigation intelligent control.

Description

Technical Field

[0001] The present invention relates to the technical field of smart agricultural management, and in particular to a smart agricultural management system based on a large model of the Internet of Things cloud. Background Art

[0002] As the global population grows, the demand for food is also increasing, which puts higher demands on agricultural production. Smart agricultural management systems can help improve agricultural production efficiency and meet the growing demand for food.

[0003] With the development and application of technologies such as the Internet of Things, big data, and artificial intelligence, a technical foundation and support have been provided for the realization of smart agricultural management systems. The application of these new technologies can make agricultural management more intelligent and efficient. The smart agricultural management system based on the IoT cloud big model is expected to promote the development of agricultural production towards intelligence and precision.

[0004] For example, the patent application with the publication number CN112101868B discloses an integrated IoT cloud control system based on smart agriculture, including a coding system, an IoT detection system, a supply chain system, and a background management system; the coding system encodes the agricultural product seeds one by one, and transmits the coding information to the background management system; the IoT detection system is used to collect various growth data information of the encoded seeds in the agricultural product planting area, and the collected growth information is transmitted to the background management system; the supply chain system is distributed to various places through logistics transmission, and the logistics transmission information is transmitted to the background management system for collecting the logistics information of agricultural products. By entering the information of agricultural product coding into the background management system, the basic information of agricultural products from the cultivated seeds can be realized, and the overall agricultural products can be monitored in real time through the background management system, so that the information between consumers and producers and sellers corresponds one by one, reducing the hidden dangers caused by food safety.

[0005] However, the above-mentioned integrated IoT cloud control system based on smart agriculture lacks objective data support and cannot use data processing technology to accurately simulate the smart agriculture management system.

[0006] Therefore, in response to the above problems, there is an urgent need for a smart agricultural management system based on the IoT cloud big model. Summary of the invention

[0007] In view of the shortcomings of the existing technology, the present invention provides a smart agricultural management system based on the Internet of Things cloud big model to solve the problems of excessive or insufficient irrigation water in traditional agriculture and the difficulty in real-time monitoring and diagnosis of pest and disease risks in the agricultural planting process.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a smart agricultural management system based on the Internet of Things cloud big model, including: an irrigation intelligent control module, a pest detection and early warning module, a user interface and a visualization module, wherein: the irrigation intelligent control module is used to obtain an irrigation monitoring and evaluation index based on real-time monitored crop irrigation related information, the irrigation monitoring and evaluation index is used to detect the current irrigation demand of crops, and the irrigation monitoring and evaluation index is used to match the irrigation records stored in the database to perform intelligent irrigation control on crops; the irrigation intelligent control module specifically includes: a crop irrigation related information collection unit, a crop irrigation related information analysis unit, and an irrigation matching execution unit, wherein: the crop irrigation related information collection unit is used to obtain crop irrigation related information based on the cognitive basis of crop types and varieties and on-site observations of crop planting sites, and pre-process the crop irrigation related information, the pre-processing includes filling missing values, deleting outliers, data normalization, and data integration, the crop irrigation related information specifically includes current crop and environmental humidity related information, crop growth information; the crop irrigation related information analysis unit is used to collect information about the current crop by analyzing the current crop irrigation information. The information related to crops and environmental humidity and crop growth information are analyzed to obtain an irrigation monitoring and evaluation index; the irrigation matching execution unit is used to match and analyze the irrigation monitoring and evaluation index with the previous irrigation data of crops stored in the database, automatically identify the irrigation water required for the current crops, and start the irrigation execution controller for automatic irrigation; the specific acquisition process of the irrigation monitoring and evaluation index is as follows: the information related to the current crops and environmental humidity specifically includes: the amount of rain during the last irrigation period, the current soil moisture, and the evaporation of crops; the crop growth information specifically includes: the average number of leaves of crops and the growth rate of crops; the irrigation monitoring and evaluation index is obtained by analyzing the amount of rain during the last irrigation period, the current soil moisture, the evaporation of crops, the average number of leaves of crops, and the growth rate of crops; the pest detection and early warning module is used to monitor the environment and growth conditions of crops that realize intelligent irrigation control in real time, and to detect and warn crops based on the pest related monitoring information obtained by real-time monitoring and the pest record information stored in the database; the user interface and visualization module is used to automatically generate a smart agriculture management report based on the pest detection and early warning results and irrigation intelligent control.

[0009] Furthermore, it also includes a database, which is used to store crop growth data, crop disease and insect pest record data, crop growth data at various stages, crop irrigation data, and crop pesticide usage data.

[0010] Furthermore, the calculation formula of the irrigation monitoring evaluation index is:

[0011] ; In the formula represents the irrigation monitoring and evaluation index, Indicates the amount of rainfall since the last irrigation period. Indicates the current soil moisture. represents the evaporation of crops, represents the average number of leaves of crops, Indicates the growth rate of crops. Indicates the reference value of the amount of rainfall during the irrigation period, represents the reference value of soil moisture, Indicates the reference value of crop evaporation, Indicates the reference value of the number of leaves of crops, A reference value indicating the growth rate of crops. Represents the weight factor of the current crop and environmental humidity related information, Represents the weight factor of crop growth information.

[0012] Furthermore, the pest and disease detection and early warning module specifically includes: a monitoring unit, a risk assessment unit, and a pest and disease detection and early warning unit, wherein: the monitoring unit is used to perform real-time monitoring of crops and obtain pest and disease related monitoring information based on real-time monitoring; the risk assessment unit is used to obtain a pest and disease risk detection deviation value by analyzing the pest and disease related monitoring information and the crop pest and disease record data stored in the database, and the pest and disease risk detection deviation value is used to numerically represent the difference between the current crop state and the crop state where pests and diseases occur; the pest and disease detection and early warning unit is used to detect whether there is a pest and disease risk in crops through pest and disease risk detection deviation value analysis, and then to provide early warning for the pest and disease risk.

[0013] Furthermore, the pest and disease related monitoring information specifically includes: crop survival related information, crop status information; the crop survival related information specifically includes: crop growth density, leaf moisture; the crop status information specifically includes: the average number of leaf patches, the average root corruption degree value, the average number of fruit gaps; the crop pest and disease record data specifically includes: historical pest and disease occurrence environment information, historical pest and disease occurrence crop status information; the historical pest and disease occurrence environment information specifically includes: pest and disease occurrence crop growth density, pest and disease occurrence leaf moisture; the historical pest and disease occurrence crop status information specifically includes: the average number of leaf patches, pest and disease occurrence root corruption degree value, pest and disease occurrence fruit gaps.

[0014] Furthermore, the specific steps of detecting whether crops have pest and disease risks are as follows: based on the analysis of crop pest and disease record data, a pest and disease risk detection deviation threshold is obtained; the pest and disease risk detection deviation value is compared and analyzed with the pest and disease risk detection deviation threshold; when the pest and disease risk detection deviation value is greater than the pest and disease risk detection deviation threshold, it is judged that the current crops do not have pest and disease risks, and the monitoring unit continues to monitor the living environment and growth conditions of the crops; when the pest and disease risk detection deviation value is less than or equal to the pest and disease risk detection deviation threshold, it is judged that the current crops have pest and disease risks, and an alarm mechanism is used to send a warning text message to prompt agricultural managers to carry out pest and disease prevention and control, and automatically provide agricultural managers with recommendations on the use of pesticides based on the crop pesticide usage data stored in the database.

[0015] Furthermore, the specific steps for obtaining the pest risk detection deviation value are as follows: by analyzing the crop growth density and leaf moisture, the environmental monitoring characteristic value is obtained; by analyzing the average number of leaf patches, the average root corruption degree value, and the average number of fruit gaps, the crop status monitoring characteristic value is obtained; by analyzing the growth density of pest-infested crops, the leaf moisture of pest-infested crops, the average number of leaf patches, the average root corruption degree value, and the average number of fruit gaps, the pest record characteristic value is obtained; the environmental monitoring characteristic value, the crop status monitoring characteristic value, and the pest record characteristic value are analyzed to obtain the pest risk detection deviation value, and the calculation formula of the pest risk detection deviation value is:

[0016] ; In the formula Indicates the pest risk detection deviation value, Indicates the sampling point number for crop environmental monitoring. , represents the total number of sampling points for crop environmental monitoring, Indicates The environmental monitoring characteristic values ​​of the crop environmental monitoring sampling points, Indicates The crop status monitoring characteristic value of each crop environment monitoring sampling point, Indicates the number of all records of crop diseases and insect pests. , Indicates the total number of records of crop pests and diseases, Indicates The characteristic value of the pest and disease record of the crop pest and disease record, represents the weight factor of the environmental monitoring characteristic value, Represents the weight factor of the crop status monitoring feature value.

[0017] Furthermore, the user interface and visualization module specifically include: a report survival unit, a message notification unit, and a user authority management unit, wherein: the report survival unit is used to automatically generate a smart agriculture management report based on the pest and disease detection and warning results and irrigation intelligent control, and the smart agriculture management report includes the current irrigation water required for crops and the current monitored pest and disease occurrence; the message notification unit is used to send irrigation reminder text messages and pest and disease reminder text messages; the user authority management unit is used to provide user identity authentication and authority management mechanism to ensure that only authorized personnel can access the user interface, and at the same time provide authorized users with a remote alarm marking function.

[0018] The present invention has the following beneficial effects:

[0019] (1) This intelligent agricultural management system based on the IoT cloud big model can accurately obtain the irrigation demand of crops through real-time monitoring of crop irrigation related information, and perform intelligent control according to the demand to avoid excessive irrigation and save water resources; real-time monitoring of the environment and growth status of crops can timely grasp the growth status of crops, combined with intelligent irrigation control, to ensure that crops get the right amount of water, improve yield and quality; the pest detection and early warning module can timely detect the pest and disease situation of crops based on real-time monitoring of pest and disease related information, and early detection and early warning can help farmers take control measures in time to prevent pests and diseases from spreading further and reduce crop losses; through automated irrigation intelligent control and pest and disease detection and early warning, the need for manual intervention is reduced and human resources are saved. The user interface and visualization module provides an intuitive operation interface and report generation function, enabling farmers to more conveniently manage agriculture.

[0020] (2) This smart agricultural management system based on the IoT cloud big model adopts data processing technology to control the irrigation water demand of crops in agricultural planting by combining comprehensive consideration of the current crop and environmental humidity related information and crop growth information; the pest risk detection deviation value calculated based on the pest and disease related monitoring information obtained by real-time monitoring and the pest and disease record information stored in the database can effectively show the gap between the current crop status and the pest and disease status, so that the pest and disease risk can be controlled and prevented in time, thereby improving the production efficiency of crops, reducing resource waste, and helping farmers to better manage agriculture, thereby bringing about the beneficial effects of saving costs and improving agricultural sustainability.

[0021] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1This is a structural diagram of a smart agricultural management system based on the IoT cloud big model of the present invention. DETAILED DESCRIPTION

[0023] The embodiments of the present application solve the problems of excessive or insufficient irrigation water in traditional agriculture and the difficulty in real-time monitoring and diagnosis of pest and disease risks in the agricultural planting process through a smart agricultural management system based on a large model of the Internet of Things cloud.

[0024] The overall idea of ​​the problem in the embodiment of this application is as follows:

[0025] By using IoT technology and big data analysis, a comprehensive intelligent platform is established in the cloud to provide comprehensive agricultural management services through real-time monitoring and data analysis. A sensor network is deployed to monitor farmland environmental parameters and crop growth status in real time. Based on the real-time monitored crop irrigation information, an irrigation monitoring and evaluation index is calculated and matched with the irrigation records stored in the database. Based on the matching results, intelligent irrigation control of crops is performed to ensure that crops receive an appropriate amount of water. Based on real-time monitoring data, it is possible to detect whether crops are affected by pests and diseases, and compare the pest and disease related information obtained from real-time monitoring with the pest and disease record information stored in the database, thereby realizing pest and disease detection and early warning. A user interface is provided so that farmers can easily view farmland monitoring data, irrigation conditions, and pest and disease early warning information.

[0026] See also Figure 1 The embodiment of the present invention provides a technical solution: a smart agricultural management system based on a large model of the Internet of Things cloud, including an irrigation intelligent control module, a pest and disease detection and early warning module, and a user interface and visualization module, wherein the irrigation intelligent control module is used to obtain an irrigation monitoring and evaluation index based on real-time monitored crop irrigation related information, and the irrigation monitoring and evaluation index is used to detect the current irrigation demand of crops, and the irrigation monitoring and evaluation index is matched with the irrigation records stored in a database to perform irrigation intelligent control on the crops; the pest and disease detection and early warning module performs real-time monitoring of the environment and growth conditions of the crops that implement intelligent irrigation control, and performs pest and disease detection and early warning on the crops based on the pest and disease related monitoring information obtained by real-time monitoring and the pest and disease record information stored in the database; the user interface and visualization module is used to automatically generate a smart agricultural management report based on the pest and disease detection and early warning results and the irrigation intelligent control.

[0027] Specifically, it also includes a database, which is used to store crop living environment data, crop growth data, crop disease and pest record data, crop growth data at various stages, crop fertilization data, crop irrigation data, and crop pesticide usage data.

[0028] In this implementation scheme, the database can store various types of agricultural data, which can be used to generate comprehensive crop growth reports to provide farmers with comprehensive production management decision support; the data stored in the database can be used to monitor the growth environment and status of crops in real time, and through connection with IoT devices, it can be fed back to the system in a timely manner to help users understand the real-time situation of the farmland and make corresponding adjustments. At the same time, it provides users with a historical record query function to help them understand past management conditions and provide experience for future agricultural production management.

[0029] Specifically, the irrigation intelligent control module includes: a crop irrigation related information collection unit, a crop irrigation related information analysis unit, and an irrigation matching execution unit, wherein the crop irrigation related information collection unit is used to obtain crop irrigation related information based on the cognitive basis of crop types and varieties and on-site observations of crop planting sites, and pre-process the crop irrigation related information, the pre-processing includes filling missing values, deleting outliers, data normalization, and data integration. The crop irrigation related information specifically includes current crop and environmental humidity related information, crop growth information; the crop irrigation related information analysis unit is used to obtain an irrigation monitoring and evaluation index by analyzing the current crop and environmental humidity related information, crop growth information; the irrigation matching execution unit is used to match and analyze the irrigation monitoring and evaluation index with the previous crop irrigation data stored in the database, automatically identify the irrigation water required for the current crop, and start the irrigation execution controller for automatic irrigation.

[0030] In this implementation scheme, the database stores the irrigation water volume of each irrigation and the irrigation assessment index of each irrigation, matches and compares the irrigation monitoring and assessment index obtained in real time with the irrigation assessment index of each irrigation, selects the irrigation record with the irrigation monitoring and assessment index obtained in real time closest to the irrigation assessment index of each irrigation as the reference irrigation for the real-time irrigation, obtains the irrigation water volume of the reference irrigation, and automatically irrigates the crops based on the irrigation water volume of the reference irrigation; by collecting and analyzing the irrigation demand information of the crops, the current irrigation demand of the farmland can be intelligently judged, thereby realizing intelligent irrigation decision-making and avoiding the waste or insufficiency that may be caused by the traditional timed and quantitative irrigation methods; the current crop and environmental humidity related information and growth information of the crops are collected in real time, combined with the historical irrigation data in the database for analysis, to realize real-time monitoring of the irrigation demand of the farmland, which is helpful to adjust the irrigation strategy in time; the connection with the irrigation execution controller can automatically identify the irrigation water volume required for the current crops, and start the irrigation execution controller for automatic irrigation, to realize the automation of the irrigation process and reduce the labor burden of farmers.

[0031] Specifically, in addition to obtaining the irrigation demand of crops and the environmental humidity conditions through professional institutions, the irrigation monitoring and evaluation index can also be obtained through calculation. The specific analysis process is as follows: the current crop and environmental humidity related information specifically includes: the amount of rain since the last irrigation, the current soil moisture, and the evaporation of crops; the crop growth information specifically includes: the average number of crop leaves and the growth rate of crops; by analyzing the amount of rain since the last irrigation, the current soil moisture, the evaporation of crops, the average number of crop leaves, and the growth rate of crops, the irrigation monitoring and evaluation index is obtained. The calculation formula of the irrigation monitoring and evaluation index is:

[0032] ; In the formula represents the irrigation monitoring and evaluation index, Indicates the amount of rainfall since the last irrigation period. Indicates the current soil moisture. represents the evaporation of crops, represents the average number of leaves of crops, Indicates the growth rate of crops. Indicates the reference value of the amount of rainfall during the irrigation period, represents the reference value of soil moisture, Indicates the reference value of crop evaporation, Indicates the reference value of the number of leaves of crops, A reference value indicating the growth rate of crops. Represents the weight factor of the current crop and environmental humidity related information, Represents the weight factor of crop growth information.

[0033] In this implementation scheme, combining multiple factors for analysis can more accurately determine the current water demand of crops, avoiding the errors that may exist in single indicator analysis. Each factor provides specific information about the water demand of crops. Comprehensive consideration of these factors can result in a more accurate irrigation water volume. Taking into account the time since the last irrigation, the amount of rainfall and other real-time conditions, the irrigation strategy can be adjusted more timely to meet the current water demand of crops, which helps to avoid excessive or insufficient irrigation due to weather changes or changes in soil conditions. Analysis of crop evaporation, the average number of crop leaves, and growth rate factors can more accurately determine the growth of crops, thereby reasonably controlling the irrigation water volume, avoiding waste of water resources, improving water resource utilization efficiency, and reducing irrigation costs.

[0034] The amount of rainfall since the last irrigation indicates the amount of rainfall received by the farmland after the last irrigation, which can reflect the replenishment of soil moisture by natural precipitation; the current soil moisture indicates the current water content in the soil. Soil moisture is an important indicator that can directly reflect the water situation in the soil, which in turn affects the growth and physiological activities of plants; the evaporation of crops and the average number of leaves of crops respectively indicate the amount of water evaporated from the surface of plants and the growth status of plants and the impact of evaporation; the growth rate of crops indicates the growth rate of crops. Crops with fast growth have a greater demand for water, so the growth rate is also an important consideration; the amount of rainfall since the last irrigation, the current Soil moisture, crop evaporation, average number of crop leaves, and crop growth rate can be obtained through various sensors, weather stations, and soil moisture detectors: use rain gauges to measure rainfall, use soil moisture sensors to monitor soil moisture, use evaporometers to measure evaporation, use photogrammetry methods to obtain the average number of crop leaves, and use growth monitoring systems to measure crop growth rates; the setting of weight factors corresponding to current crop and environmental humidity related information and crop growth information needs to be determined based on the importance of the two to actual crop irrigation. The importance of each factor is determined by field experiments or expert experience, and is set according to its impact on crop growth.

[0035] Specifically, the pest and disease detection and early warning module includes: a monitoring unit, a risk assessment unit, and a pest and disease detection and early warning unit, wherein: the monitoring unit is used to monitor crops in real time, and obtain pest and disease related monitoring information based on real-time monitoring; the risk assessment unit is used to obtain a pest and disease risk detection deviation value by analyzing the pest and disease related monitoring information and the crop pest and disease record data stored in the database, and the pest and disease risk detection deviation value is used to numerically represent the difference between the current crop state and the crop state where pests and diseases occur; the pest and disease detection and early warning unit is used to detect whether there is a pest and disease risk in crops through pest and disease risk detection deviation value analysis, and then to give early warning and disposal of the pest and disease risk.

[0036] In this implementation scheme, by real-time monitoring of the environment and growth conditions of crops, possible pest and disease problems can be discovered in a timely manner, and timely monitoring and early warning of the health status of crops can be achieved, which helps to take measures in advance to deal with them, thereby reducing the damage to crops caused by pests and diseases; the risk assessment unit can obtain the pest and disease risk detection deviation value by analyzing the monitoring information and historical data in the database, thereby quantifying the gap between the current crop status and the pest and disease occurrence status, helping farmers or managers to more accurately assess the degree of pest and disease risk; the pest and disease detection and early warning unit uses the risk detection deviation value for analysis, which can more accurately detect whether crops have pest and disease risks, and then provide timely early warnings and disposal, which helps to avoid false alarms, and can also effectively reduce unnecessary treatment of crops and improve the accuracy and efficiency of early warnings.

[0037] Specifically, pest and disease related monitoring information includes: crop survival related information, crop status information; crop survival related information includes: crop growth density, leaf moisture; crop status information includes: average number of leaf patches, average root corruption value, average number of fruit gaps; crop pest and disease record data includes: historical pest and disease occurrence environment information, historical pest and disease occurrence crop status information; historical pest and disease occurrence environment information includes: crop growth density where pests and diseases occurred, leaf moisture where pests and diseases occurred; historical pest and disease occurrence crop status information includes: average number of leaf patches where pests and diseases occurred, average root corruption value where pests and diseases occurred, average number of fruit gaps where pests and diseases occurred.

[0038] In this implementation plan, the crop growth density reflects the growth status and density of vegetation. It is obtained through remote sensing technology. The value of crop growth density can help evaluate the vegetation coverage, growth status and health of vegetation; leaf humidity indicates the wetness of the leaf surface. Leaf humidity has a certain influence on the occurrence of certain diseases. Too high or too low leaf humidity may lead to the breeding of diseases; the average number of leaf patches refers to the average number of diseased spots and lesions on the leaf surface. An increase in the number of leaf patches indicates that the plant is affected by diseases and insect pests. The number of patches on the leaves is calculated by visual inspection or image analysis of the plant leaves; the average root decay degree value refers to the average value of the degree of decay of the plant roots. By digging the plant roots and A visual inspection is carried out to obtain the value of the root corruption degree; the average number of fruit notches refers to the average number of notches on the fruit surface. Fruit notches are caused by insect gnawing and diseases, and can be used as a standard for disease and insect pest detection. The number of notches on the fruit surface is calculated by visual inspection or image analysis of the fruit; the crop growth density, leaf moisture, average number of leaf patches, average root corruption degree and average number of fruit notches indicate the corresponding crop growth density, leaf moisture, leaf patch condition, root corruption condition and number of fruit notches when diseases and insect pests occur. Through these indicators, we can more accurately understand the impact of diseases and insect pests on plant health, which is helpful to take control and prevention measures in time.

[0039] Specifically, the specific steps for detecting whether crops have pest and disease risks are as follows: based on the analysis of crop pest and disease record data, obtain the pest and disease risk detection deviation threshold; compare and analyze the pest and disease risk detection deviation value with the pest and disease risk detection deviation threshold; when the pest and disease risk detection deviation value is greater than the pest and disease risk detection deviation threshold, there is no pest and disease risk for the current crops, and the monitoring unit continues to monitor the living environment and growth conditions of the crops; when the pest and disease risk detection deviation value is less than or equal to the pest and disease risk detection deviation threshold, there is a pest and disease risk for the current crops, and the alarm mechanism is used to send warning text messages to remind agricultural managers to carry out pest and disease prevention and control, and automatically provide agricultural managers with recommendations on the use of pesticides based on the crop pesticide use data stored in the database.

[0040] In this implementation scheme, by analyzing historical data and setting thresholds, the possible risks of plant diseases and pests in crops can be discovered in a timely manner, and control measures can be taken in advance to reduce the damage to crops caused by plant diseases and pests; once the risk of plant diseases and pests is detected, the system will automatically send a warning text message to agricultural managers to remind them to take appropriate prevention and control measures, reducing the need for manual intervention and improving work efficiency; based on the crop pesticide usage data stored in the database, the system can provide agricultural managers with targeted pesticide usage recommendations to help them make more scientific and reasonable decisions and improve prevention and control effects; accurate early warnings and pesticide usage recommendations can reduce unnecessary pesticide use and human resource investment, reduce costs in the crop production process, and improve economic benefits.

[0041] Specifically, the specific steps for obtaining the deviation value of the risk detection of pests and diseases are as follows: by analyzing the growth density of crops and the humidity of leaves, the environmental monitoring characteristic value is obtained. The environmental monitoring characteristic value is used to numerically represent the characteristic conditions of the current living environment of crops. In addition to obtaining the environmental monitoring characteristic value through detection of the living environment of crops by professional institutions, it can also be obtained through calculation. The specific calculation formula of the environmental monitoring characteristic value is:

[0042] ; In the formula Indicates the sampling point number for crop environmental monitoring. , represents the total number of sampling points for crop environmental monitoring, Indicates The environmental monitoring characteristic values ​​of the crop environmental monitoring sampling points, Indicates The crop growth density at each crop environment monitoring sampling point, Indicates Leaf moisture at each crop environmental monitoring sampling point, Indicates the reference value of crop growth density, Indicates the leaf humidity reference value, represents the weight factor of crop growth density, A weighting factor representing leaf wetness.

[0043] By analyzing the average number of leaf patches, the average degree of root corruption, and the average number of fruit gaps, the crop status monitoring characteristic value is obtained. The crop status monitoring characteristic value is used to numerically represent the comprehensive characteristic status of the current crops. In addition to obtaining the crop status through professional institutions, the crop status monitoring characteristic value can also be obtained through calculation. The specific calculation formula for the crop status monitoring characteristic value is: ; In the formula Indicates The characteristic value of crop status monitoring at each crop environment monitoring sampling point, Indicates The average number of leaf patches at each crop environmental monitoring sampling point, Indicates The average root corruption degree value of the crop environmental monitoring sampling points, Indicates The average number of fruit gaps at each crop environmental monitoring sampling point, represents the reference value of the number of leaf patches, A reference value indicating the degree of root corruption. Indicates the reference value of the number of fruit gaps, The weight factor representing the average number of patches on leaves, The weight factor representing the average root corruption value, Represents the weight factor for the average number of notches in the fruit.

[0044] By analyzing the growth density of crops with pests and diseases, the leaf humidity and average number of patches on the leaves with pests and diseases, the average degree of root corruption with pests and diseases, and the average number of gaps in fruits with pests and diseases, the pest and disease record characteristic values ​​are obtained. The pest and disease record characteristic values ​​are used to numerically describe the comprehensive characteristic conditions of crops when pests and diseases occur. In addition to simulating the pest and disease situation of crops through computer simulation software and analyzing their environment and growth conditions, the pest and disease record characteristic values ​​can also be obtained through calculation. The specific formula for calculating the pest and disease record characteristic values ​​is as follows: ; In the formula Indicates the number of all records of crop diseases and insect pests. , Indicates the total number of records of crop pests and diseases, Indicates The characteristic value of the pest and disease record of the crop pest and disease record, Indicates Environmental record characteristic values ​​of crop pest and disease records, Indicates The characteristic value of the crop status record of the crop pest record, represents the weight factor of the characteristic value of the environmental record, Represents the weight factor of the characteristic value of the crop status record, where: ; Indicates The growth density of crops with pests and diseases recorded in the crop pest and disease records, Indicates The leaf moisture of the pests and diseases recorded in the crop pests and diseases, Indicates the reference value of crop growth density, Indicates the leaf humidity reference value;

[0045] ; Indicates The average number of leaf patches with pests and diseases recorded for each crop pest and disease, Indicates The average root corruption degree of pests and diseases recorded in the crop pests and diseases record, Indicates The average number of fruit gaps caused by pests and diseases recorded in the crop pest and disease records, represents the reference value of the number of leaf patches, A reference value indicating the degree of root corruption. Indicates the reference value of the number of fruit gaps.

[0046] The environmental monitoring characteristic values, crop status monitoring characteristic values ​​and pest and disease record characteristic values ​​are analyzed to obtain the pest and disease risk detection deviation value, and the calculation formula of the pest and disease risk detection deviation value is:

[0047] ; In the formula Indicates the pest risk detection deviation value, Indicates the sampling point number for crop environmental monitoring. , represents the total number of sampling points for crop environmental monitoring, Indicates The environmental monitoring characteristic values ​​of the crop environmental monitoring sampling points, Indicates The crop status monitoring characteristic value of each crop environment monitoring sampling point, Indicates the number of all records of crop diseases and insect pests. , Indicates the total number of records of crop pests and diseases, Indicates The characteristic value of the pest and disease record of the crop pest and disease record, represents the weight factor of the environmental monitoring characteristic value, Represents the weight factor of the crop status monitoring feature value.

[0048] In this implementation scheme, by calculating the environmental monitoring characteristic values, multiple environmental parameters such as crop growth density and leaf humidity can be comprehensively considered, so as to more accurately evaluate the current living environment characteristics of crops, which is helpful for agricultural managers to adjust management strategies in time. The environmental monitoring characteristic values ​​are numerically represented, and quantitative analysis and comparison can be performed, so that agricultural managers can more intuitively understand the living environment characteristics of crops in different periods and locations, and provide a scientific basis for agricultural production decisions; the crop growth density is obtained through remote sensing technology, and remote sensing images of vegetation are obtained using platforms such as satellites or drones, and then the growth density of specific crops is calculated to reflect the growth status and coverage of vegetation; leaf humidity is monitored by sensors, Use a surface humidity sensor or a leaf humidity sensor to directly measure the leaf humidity on the surface of the plant leaves; the setting of the weight factors of crop growth density and leaf humidity needs to be adjusted and optimized according to the specific situation and characteristics of the crops, and the weight factors are determined by comprehensive analysis of the sensitivity of different crops to crop growth density and leaf humidity through expert experience, historical data analysis, and machine learning; the reference values ​​of crop growth density and leaf humidity can use historical environmental monitoring data, and the comprehensive analysis of crop growth density and leaf humidity as reference values, or draw on expert experience and relevant research literature to understand the ideal range and reference values ​​of crop growth density and leaf humidity for different crops at different growth stages.

[0049] By comprehensively considering the leaf patch status, root corruption status and average number of fruit gaps, the health status and growth status of crops can be comprehensively evaluated, helping agricultural managers to discover and solve problems in a timely manner. The numerical representation of crop status monitoring characteristic values ​​will help agricultural managers to more intuitively understand the overall status of current crops so as to formulate corresponding management strategies and measures; the average number of leaf patches is obtained by visually inspecting or image analyzing the plant leaves to calculate the number of patches on the leaves; the average root corruption degree value is obtained by digging the plant roots and visually inspecting them or using some type of root detection tool to evaluate; the average number of fruit gaps is obtained by visually inspecting or image analyzing the fruits to calculate the number of gaps on the fruit surface; the setting of the weight factors corresponding to the average number of leaf patches, the average root corruption degree value, and the average number of fruit gaps needs to be adjusted and optimized according to the specific situation and crop characteristics. The weight factors are determined through expert experience, historical data analysis, and machine learning, so that the contribution of each scoring indicator in the crop status monitoring characteristic value is more in line with the actual situation and crop needs.

[0050] By comprehensively considering the scoring factors of crop growth density where pests and diseases occur, leaf moisture and average number of patches on leaves where pests and diseases occur, average degree of root corruption where pests and diseases occur, and average number of gaps in fruits where pests and diseases occur, we can comprehensively evaluate the conditions of crop diseases and pests when they occur, quantify and score various indicators of disease and pest occurrence, and calculate the characteristic values ​​of disease and pest record based on weight factors, which can provide agricultural managers with intuitive and comparable numerical descriptions and help scientific decision-making and management; the setting of weight factors needs to be adjusted and optimized according to specific circumstances and crop characteristics, and adjusted through expert experience, historical data analysis, field surveys and machine learning analysis of the contribution of each scoring indicator in calculating the characteristic values ​​of disease and pest record.

[0051] Specifically, the user interface and visualization module include: a report survival unit, a message notification unit, and a user authority management unit, wherein: the report survival unit is used to automatically generate a smart agriculture management report based on the results of pest and disease detection and early warning and irrigation intelligent control. The smart agriculture management report includes the current irrigation water required for crops and the current monitored pest and disease occurrence; the message notification unit is used to send irrigation reminder text messages and pest and disease reminder text messages; the user authority management unit is used to provide user identity authentication and authority management mechanism to ensure that only authorized personnel can access the user interface, and at the same time provide authorized users with remote alarm marking function.

[0052] In this implementation scheme, the report survival unit can monitor the results of pest and disease detection and early warning and the intelligent irrigation control in real time, and timely understand the amount of irrigation water required for crops and the occurrence of pests and diseases through the smart agricultural management report, which is conducive to taking timely measures to ensure the healthy growth of crops; the irrigation intelligent control automatically generates smart agricultural management reports, improves the efficiency and accuracy of agricultural management, reduces the need for manual intervention, and reduces management costs; the message notification unit can send irrigation reminder text messages and pest and disease reminder text messages in time to help farmers and managers take corresponding measures at critical moments to prevent disasters and accidents, and improve the stability and reliability of agricultural production; the user authority management unit provides a user identity authentication and authority management mechanism to ensure that only authorized personnel can access the user interface, ensuring the security and privacy of system data, and at the same time authorizing users to remotely mark alarm functions, improving management flexibility and response speed; integrating the report survival unit, the message notification unit and the user authority management unit enables agricultural managers to complete various management tasks on the same interface, improving management efficiency and convenience, and helping to respond to various risks and challenges in a timely manner, ensuring the stability and sustainable development of agricultural production.

[0053] In summary, this application has at least the following effects:

[0054] By using big data analysis and Internet of Things technology, intelligent control and early warning of crop irrigation and pest and disease detection can be achieved, which improves the level of intelligence in agricultural production and reduces human intervention; real-time monitoring of crop irrigation needs and environmental conditions can accurately regulate irrigation water volume, avoid excessive waste of water resources, and also reduce the use of fertilizers and pesticides, reducing the cost of agricultural production; by reasonably controlling crop irrigation and timely warning of pests and diseases, the system can ensure that crops get enough water and reduce the invasion of pests and diseases, thereby improving crop yield and quality; based on analysis of historical data and real-time monitoring data, a smart agriculture management report is generated to provide farmers with decision support and optimization suggestions to help better manage farmland and increase yields.

[0055] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as systems. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0056] The present invention is described with reference to the block diagram of the system according to the embodiment of the present invention. It should be understood that the combination of each structure in the block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate a device for implementing the functions specified in each structure in the block diagram.

[0057] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in each structure of the structural diagram.

[0058] These computer program instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in each structure in the structural diagram.

[0059] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0060] 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 claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A smart agricultural management system based on the IoT cloud big model, characterized in that: It includes irrigation intelligent control module, pest detection and early warning module, user interface and visualization module, among which: The irrigation intelligent control module is used to obtain an irrigation monitoring and evaluation index based on real-time monitoring of crop irrigation related information. The irrigation monitoring and evaluation index is used to detect the current irrigation demand of crops, and the irrigation monitoring and evaluation index is matched with the irrigation records stored in the database to perform intelligent irrigation control on the crops. The irrigation intelligent control module specifically includes: a crop irrigation related information collection unit, a crop irrigation related information analysis unit, and an irrigation matching execution unit, wherein: The crop irrigation related information acquisition unit is used to obtain crop irrigation related information based on the knowledge of crop types and varieties and on-site observation of crop planting sites, and preprocess the crop irrigation related information, the preprocessing including filling missing values, deleting outliers, data normalization, and data integration. The crop irrigation related information specifically includes current crop and environmental humidity related information and crop growth information; The crop irrigation related information analysis unit is used to obtain an irrigation monitoring and evaluation index by analyzing the current crop and environmental humidity related information and crop growth information; The irrigation matching execution unit is used to match and analyze the irrigation monitoring and evaluation index with the previous irrigation data of crops stored in the database, automatically identify the irrigation water required for the current crops, and start the irrigation execution controller to perform automatic irrigation; The specific process of obtaining the irrigation monitoring and evaluation index is as follows: The information related to the current crops and environmental humidity specifically includes: the amount of rainfall since the last irrigation period, the current soil moisture, and the amount of crop evaporation; The crop growth information specifically includes: average number of crop leaves and crop growth rate; The irrigation monitoring and evaluation index is obtained by analyzing the amount of rainfall since the last irrigation, current soil moisture, crop evaporation, average number of crop leaves, and crop growth rate; The pest detection and early warning module is used to perform real-time monitoring of the environment and growth conditions of crops that implement intelligent irrigation control, and to perform pest detection and early warning on crops based on pest-related monitoring information obtained through real-time monitoring and pest record information stored in a database; The user interface and visualization module are used to automatically generate smart agriculture management reports based on pest and disease detection and early warning results and irrigation intelligent control; The calculation formula of the irrigation monitoring and evaluation index is: ； In the formula represents the irrigation monitoring and evaluation index, Indicates the amount of rainfall since the last irrigation period. Indicates the current soil moisture. represents the evaporation of crops, represents the average number of leaves of crops, Indicates the growth rate of crops. Indicates the reference value of the amount of rainfall during the irrigation period, represents the reference value of soil moisture, Indicates the reference value of crop evaporation, Indicates the reference value of the number of leaves of crops, A reference value indicating the growth rate of crops. Represents the weight factor of the current crop and environmental humidity related information, Represents the weight factor of crop growth information.

2. According to claim 1, a smart agricultural management system based on the IoT cloud big model is characterized in that , also includes a database, which is used to store crop growth data, crop disease and pest record data, crop growth data at each stage, crop irrigation data, and crop drug usage data.

3. According to claim 1, a smart agricultural management system based on the IoT cloud big model is characterized in that The pest detection and early warning module specifically includes: a monitoring unit, a risk assessment unit, and a pest detection and early warning unit, wherein: The monitoring unit is used to monitor crops in real time and obtain pest and disease related monitoring information based on the real-time monitoring; The risk assessment unit is used to obtain a pest risk detection deviation value by analyzing pest-related monitoring information and crop pest record data stored in a database, wherein the pest risk detection deviation value is used to numerically represent the difference between the current crop state and the crop state where the pest occurs; The pest and disease detection and early warning unit is used to detect whether there is a pest and disease risk in crops through pest and disease risk detection deviation value analysis, and then to provide early warning for the pest and disease risk.

4. According to claim 3, a smart agricultural management system based on the IoT cloud big model is characterized in that ,The pest and disease related monitoring information specifically includes: crop survival related information and crop status information; The crop survival related information specifically includes: crop growth density and leaf humidity; The crop status information specifically includes: the average number of leaf patches, the average root corruption level, and the average number of fruit gaps; The crop pest and disease record data specifically includes: historical pest and disease occurrence environment information, historical pest and disease occurrence crop status information; The historical pest and disease occurrence environment information specifically includes: the growth density of crops where pests and diseases occur, and the leaf humidity where pests and diseases occur; The historical crop status information due to pests and diseases specifically includes: the average number of patches on leaves due to pests and diseases, the average degree of root corruption due to pests and diseases, and the average number of gaps in fruits due to pests and diseases.

5. According to claim 3, a smart agricultural management system based on the IoT cloud big model is characterized in that ,The specific steps for detecting whether crops have pest and disease risks are: Based on the analysis of crop pest and disease record data, the deviation threshold of pest and disease risk detection is obtained; Compare and analyze the pest risk detection deviation value with the pest risk detection deviation threshold. When the pest risk detection deviation value is greater than the pest risk detection deviation threshold, it is judged that there is no pest risk for the current crops, and the monitoring unit continues to monitor the living environment and growth status of the crops. When the pest and disease risk detection deviation value is less than or equal to the pest and disease risk detection deviation threshold, it is judged that the current crops are at risk of pests and diseases, and an alarm mechanism is used to send a warning SMS to remind agricultural managers to carry out pest and disease prevention and control, and automatically provide agricultural managers with recommendations on the use of pesticides based on the crop pesticide usage data stored in the database.

6. According to claim 3, a smart agricultural management system based on the IoT cloud big model is characterized in that ,The specific steps for obtaining the pest risk detection deviation value are: By analyzing the growth density and leaf humidity of crops, the characteristic values ​​of environmental monitoring are obtained; By analyzing the average number of leaf patches, the average degree of root corruption, and the average number of fruit gaps, the characteristic values ​​for monitoring crop status were obtained. The characteristic values ​​of pest and disease records were obtained by analyzing the growth density of crops affected by pests and diseases, the leaf humidity and average number of patches on leaves affected by pests and diseases, the average degree of root corruption caused by pests and diseases, and the average number of gaps in fruits caused by pests and diseases. The environmental monitoring characteristic values, crop status monitoring characteristic values ​​and pest and disease record characteristic values ​​are analyzed to obtain the pest and disease risk detection deviation value, and the calculation formula of the pest and disease risk detection deviation value is: ； In the formula Indicates the pest risk detection deviation value, Indicates the sampling point number for crop environmental monitoring. , represents the total number of sampling points for crop environmental monitoring, Indicates The environmental monitoring characteristic values ​​of the crop environmental monitoring sampling points, Indicates The crop status monitoring characteristic value of each crop environment monitoring sampling point, Indicates the number of all records of crop diseases and insect pests. , Indicates the total number of records of crop pests and diseases, Indicates The characteristic value of the pest and disease record of the crop pest and disease record, represents the weight factor of the environmental monitoring characteristic value, Represents the weight factor of the crop status monitoring feature value.

7. According to claim 1, a smart agricultural management system based on the IoT cloud big model is characterized in that ,The user interface and visualization module specifically includes: a report survival unit, a message notification unit, and a user authority management unit, where: The report survival unit is used to automatically generate a smart agriculture management report based on the pest and disease detection and early warning results and the irrigation intelligent control. The smart agriculture management report includes the current amount of irrigation water required for crops and the current monitored pest and disease occurrence situation; The message notification unit is used to send irrigation reminder text messages and pest and disease reminder text messages; The user rights management unit is used to provide a user identity authentication and rights management mechanism to ensure that only authorized personnel can access the user interface, while providing a remote alarm marking function for authorized users.

Images