Agricultural product producing area environment intelligent monitoring method and system based on data analysis

Abstract

The invention discloses an agricultural product producing area environment intelligent monitoring method and system based on data analysis, and belongs to the technical field of intelligent monitoring. Acquiring average soil humidity data, average oxygen concentration data and air pressure data in the agricultural product area; constructing a ground data set and a high-altitude data set based on the time sequence; calculating an average soil humidity change degree, an average oxygen concentration change degree and an air pressure data change degree; calculating an environmental health fluctuation value; obtaining all environmental health fluctuation values, and constructing an environmental health fluctuation coordinate system; superposing environmental health fluctuation coordinate systems of different agricultural product areas, and judging whether the different agricultural product areas are similar or not; and presetting an environment health fluctuation value threshold value, and analyzing and outputting an environment health abnormity early warning. According to the invention, by comprehensively considering a plurality of environmental factors and mutual influence, the accuracy and timeliness of monitoring are improved, scientific risk early warning is provided, agricultural producers are helped to optimize management strategies, and healthy growth of crops is guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology, and in particular to a method and system for intelligent monitoring of agricultural product production environments based on data analysis. Background Art

[0002] With the growing demand for modernization and precision in agricultural production, intelligent monitoring of the agricultural environment has gradually become a research hotspot. In recent years, the rapid development of data analysis technology has provided new solutions for agricultural environmental monitoring. Through satellite remote sensing images, drone aerial photography, sensor networks and other technologies, farmers can obtain real-time data on agricultural product growing areas and conduct intelligent management. By establishing an environmental health assessment model based on big data, agricultural producers can conduct a more comprehensive real-time assessment of the health status of the crop growing environment, thereby improving the accuracy and sustainability of agricultural production.

[0003] However, the existing environmental monitoring technology for agricultural product production areas still has many shortcomings. Traditional agricultural environmental monitoring mostly relies on single monitoring equipment and data analysis methods, and fails to fully utilize the complex information of various dynamic changes in the environment. For example, existing monitoring systems often ignore the interactions between environmental factors such as soil moisture, oxygen concentration, and air pressure, and only monitor a certain parameter separately, which cannot comprehensively evaluate the overall health of the production environment. In addition, when processing multi-source environmental data, traditional systems lack efficient dynamic change analysis methods, and often find it difficult to capture subtle changes in environmental fluctuations, resulting in delayed warning of abnormal fluctuations in the crop growth environment. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent monitoring method and system for the production environment of agricultural products based on data analysis to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] An intelligent monitoring method for the environment of agricultural product production areas based on data analysis, the method comprises the following steps: dividing the agricultural product production areas into several agricultural product areas, and arranging soil moisture sensors and micro oxygen concentration sensors in the agricultural product areas; obtaining average soil moisture data and average oxygen concentration data; obtaining air pressure data above the agricultural product areas; constructing ground data sets and high-altitude data sets for agricultural product areas based on time series; calculating the average soil moisture change degree, average oxygen concentration change degree and air pressure data change degree; calculating the environmental health fluctuation value of the agricultural product area; obtaining all environmental health fluctuation values ​​of the agricultural product area in the time series, and constructing an environmental health fluctuation coordinate system; superimposing the environmental health fluctuation coordinate systems of different agricultural product areas, and judging whether different agricultural product areas are similar; presetting the environmental health fluctuation value threshold, analyzing and outputting environmental health abnormality warning.

[0007] As a preferred solution of the method for intelligent monitoring of the environment of agricultural product production areas based on data analysis described in the present invention, high-precision remote sensing imaging equipment is used to survey the use range of agricultural product production areas, and the use range of the agricultural product production areas is divided into several agricultural product areas through gridding, wherein one agricultural product area corresponds to one type of agricultural product; a soil moisture sensor is buried in the agricultural product area, and the soil moisture sensor is used to detect the soil moisture in the agricultural product area; a micro oxygen concentration sensor is deployed on the surface of crops in the agricultural product area, and the micro oxygen concentration sensor is used to detect oxygen concentration data.

[0008] The i-th agricultural product area is denoted as AA i , get the agricultural product area AA i The average soil moisture data within is recorded as AMD i ; Get agricultural product area AA i The average oxygen concentration data within is recorded as AOD i .

[0009] As a preferred solution of the method for intelligently monitoring the environment of agricultural product production areas based on data analysis described in the present invention, the AA of the agricultural product area is obtained. i The air pressure data above is as follows:

[0010] Using geographic information system to obtain regional AA of agricultural products i The terrain features include low-lying terrain and high-land terrain; based on the agricultural product area AA i Based on the terrain features of the agricultural product area, different drone flight altitudes are preset for each agricultural product area, and the pressure sensor carried by the drone is used to collect the AA data of the agricultural product area. i Air pressure data above, recorded as APD i .

[0011] Constructing regional AA of agricultural products based on time series i The ground dataset and high-altitude dataset are denoted as D ground (t) = {AMD i (t), AOD i (t)|i∈[1,I],t∈[1,T]} and D air (t) = {APD i (t)|i∈[1,I],t∈[1,T]}, where AMD i (t) represents the average soil moisture data at time point t, AOD i (t) represents the average oxygen concentration data at time point t, APD i(t) represents the air pressure data at time point t, I represents the total number of agricultural product areas, and T represents the total number of time points.

[0012] As a preferred solution of the method for intelligent monitoring of agricultural product production environment based on data analysis described in the present invention, the average soil moisture data AMD i (t) and average oxygen concentration data AOD i (t) The average soil moisture change and average oxygen concentration change from time point t to time point t+1 are calculated as follows:

[0013]

[0014] Among them, ΔAMD i (t) represents the average soil moisture change, AMD i (t+1) represents the average soil moisture data at time point t+1, ΔAOD i (t) represents the average oxygen concentration change, AOD i (t+1) represents the average oxygen concentration data at time point t+1.

[0015] In the present invention, soil moisture is the core environmental factor for crop growth, which directly affects the ability of plant roots to absorb water and nutrients. The fluctuation of soil moisture is often closely related to natural and human factors such as precipitation, irrigation, and evaporation. Therefore, by analyzing the variation range of historical humidity data, it can be revealed whether there is abnormal fluctuation in the soil; if ΔAMD i (t) value is small, indicating that soil moisture changes steadily and the soil state is suitable for crop growth; if ΔAMD i A large (t) value may indicate that soil moisture fluctuates dramatically, such as over-irrigation or drought. The oxygen concentration in the soil will also affect the activity of soil microorganisms, thereby indirectly affecting soil fertility and crop growth. By analyzing the fluctuation of oxygen concentration, the dynamic change amplitude of the ambient oxygen content is quantified, which helps to find out whether there are abnormal phenomena that are not conducive to crop growth, such as poor ventilation or abnormal climate. If ΔAOD i (t) value is small, indicating that the ambient oxygen concentration is stable and suitable for plant respiration; if ΔAOD i Large (t) values ​​may indicate unstable ambient oxygen supply, for example, due to high temperature or high humidity resulting in poor air flow.

[0016] Calculate the agricultural product area AA i Air pressure data APD i (t) The change in air pressure data from time point t to time point t+1 is calculated as follows:

[0017] ΔAPD i(t) = ln[APD i (t+1)]-ln[APD i (t)];

[0018] Where, ΔAPD i (t) represents the change of air pressure data, APD i (t+1) represents the air pressure data at time point t+1.

[0019] In the present invention, air pressure is an important meteorological factor affecting the crop environment. Low air pressure may cause crop respiration to be blocked, while high air pressure may be related to dry weather. This formula quantifies the intensity of air pressure changes by analyzing the fluctuation pattern of air pressure over time. If ΔAPD i (t) A sudden increase may indicate a dramatic fluctuation in air pressure, and attention should be paid to the possibility of extreme weather such as typhoons and rainstorms. When the air pressure changes steadily, that is, ΔAPD i The (t) value is small, so agricultural production activities such as open-air work and picking can be arranged.

[0020] Based on the average soil moisture change ΔAMD i (t), average oxygen concentration change ΔAOD i (t) and air pressure data change ΔAPD i (t), calculate the agricultural product area AA from time point t to time point t+1 i The environmental health fluctuation value is calculated as follows:

[0021] R env (AA i , t) = [ΔAMD i (t)+∈] m ×[ΔAOD i (t)+∈] d ×[ΔAPD i (t)+∈] p ;

[0022] Among them, R env (AA i , t) represents the agricultural product area AA from time point t to time point t+1 i The environmental health fluctuation value, m, d and p represent the influencing factors of the preset average soil moisture data, average oxygen concentration data and air pressure data respectively, and ∈ represents the preset smoothing factor.

[0023] In the present invention, the environmental health fluctuation value formula integrates the three key environmental factors of soil moisture, oxygen concentration and air pressure into a comprehensive evaluation index according to the weights; the calculation result of the formula directly quantifies the fluctuation of the comprehensive health status of the production environment, providing a scientific basis for intelligent monitoring and intervention of the environment. Compared with single factor monitoring, the environmental health fluctuation value integrates multiple environmental data to provide a comprehensive quantitative assessment of the production environment; if R env (AA i , t) value is abnormally high, indicating that the environment fluctuates violently, which may threaten the growth of crops, and prevention and control measures need to be taken in time. env (AA i , t), can reveal deficiencies in long-term environmental management, such as improper irrigation or blind spots in meteorological monitoring.

[0024] As a preferred solution of the method for intelligent monitoring of agricultural product production environment based on data analysis described in the present invention, let t = t + 1, recalculate the average soil moisture change, average oxygen concentration change, air pressure data change and environmental health fluctuation value, and perform agricultural product area AA i Iterative analysis, when t = T-1, stop the iteration and obtain the agricultural product area AA i The environmental health fluctuation value calculated in each iteration is used to construct the environmental health fluctuation value set, which is denoted as R env，i = {R env (AA i , t)|t∈[1,T-1]}.

[0025] Based on the environmental health fluctuation value set, an agricultural product regional AA i The environmental health fluctuation coordinate system is a time point, the ordinate of the environmental health fluctuation coordinate system is the environmental health fluctuation value, and the curve in the environmental health fluctuation coordinate system is recorded as the agricultural product area AA i Environmental health fluctuation curve L i .

[0026] Let i = i + 1, recalculate the average soil moisture change, average oxygen concentration change, air pressure data change and environmental health fluctuation value, and reconstruct the agricultural product area AA i+1 Environmental health fluctuation coordinate system, agricultural product area AA i+1 Environmental health fluctuation coordinate system and agricultural product regional AA i The environmental health fluctuation coordinate system is superimposed to construct a dual environmental health fluctuation coordinate system, wherein the dual environmental health fluctuation coordinate system includes the environmental health fluctuation curve L i and environmental health fluctuation curve L i+1 .

[0027] Calculate the environmental health fluctuation curve L i and environmental health fluctuation curve L i+1 The difference in the vertical coordinates: d i，i+1 =|R env (AA i , t)-R env (AA i+1 , t)|, where R env (AA i+1 , t) represents the agricultural product area AA from time point t to time point t+1 i+1 Environmental health fluctuation value; get the maximum difference d max =max t∈[1，T-1] d i，i+1 .

[0028] Preset difference threshold τ, if d max <τ, then determine the environmental health fluctuation curve L i and environmental health fluctuation curve L i+1 Similar, then the agricultural product area AA i and agricultural product area AA i+1 Similar environmental health fluctuations, the construction of regional AA based on agricultural products i Similarity group S i , the agricultural product area AA i and agricultural product area AA i+1 Join Similar Groups i And, if the agricultural product area AA is determined i+1 and agricultural product area AA i+2 If the fluctuations in environmental health are similar, the agricultural product area AA i+2 Join Similar Groups i middle.

[0029] If d max >τ, then determine the environmental health fluctuation curve L i and environmental health fluctuation curve L i+1 If not similar, then the agricultural product area AA i and agricultural product area AA i+1 If the environmental health fluctuations are not similar, then construct the AA based on agricultural product regions. i and agricultural product area AA i+1 Similarity group S i and similar group S i+1 , the agricultural product area AA i Join Similar Groups i Middle, agricultural products area AA i+1 Join Similar Groups i+1 middle.

[0030] When i=I-1, stop the iteration, obtain all similar groups, and preset the environmental health fluctuation value threshold θ. If R env (AA i , t)>θ, then the agricultural product area AA is determined i If there is an abnormality in the environmental health of the agricultural product area, i Similarity group S i Abnormal environmental health warnings were issued for all agricultural product areas.

[0031] It should be noted that this step first iterates based on the time point, and then iterates based on the agricultural product area after the iteration is completed, so that the horizontal coordinate of the environmental health fluctuation coordinate system constructed for each agricultural product area is the same. On this basis, the environmental health fluctuation coordinate system is superimposed, and the horizontal coordinates of different curves in the coordinate system are consistent. It is only necessary to calculate the vertical coordinate to find the difference to obtain the distance between different curves. Furthermore, the present invention presets a difference threshold τ. If the maximum distance is less than the difference threshold τ, it can be determined that the curves are very close, that is, the agricultural product areas are similar.

[0032] The intelligent monitoring system of agricultural product production environment based on data analysis includes: sensor installation and data acquisition module, air pressure data acquisition and data set construction module, change degree and environmental health fluctuation value calculation module and coordinate system construction and early warning module.

[0033] The sensor installation and data acquisition module divides the agricultural product producing area into several agricultural product areas, arranges soil moisture sensors and micro oxygen concentration sensors in the agricultural product areas, and acquires average soil moisture data and average oxygen concentration data.

[0034] The air pressure data acquisition and data set construction module is used to acquire the air pressure data above the agricultural product area and to construct a ground data set and an air data set of the agricultural product area based on a time series.

[0035] The variation degree and environmental health fluctuation value calculation module calculates the average soil moisture variation degree, the average oxygen concentration variation degree and the air pressure data variation degree; and calculates the environmental health fluctuation value of the agricultural product area.

[0036] The coordinate system construction and early warning module: obtains all environmental health fluctuation values ​​of agricultural product areas within the time series and constructs an environmental health fluctuation coordinate system; superimposes the environmental health fluctuation coordinate systems of different agricultural product areas and determines whether different agricultural product areas are similar; presets environmental health fluctuation value thresholds, analyzes and outputs environmental health abnormality early warnings.

[0037] Furthermore, the sensor installation and data acquisition module includes a sensor installation unit and a data acquisition unit.

[0038] The sensor installation unit: uses high-precision remote sensing imaging equipment to survey the use range of agricultural product production areas, and divides the use range of the agricultural product production areas into several agricultural product areas through grid division, wherein one agricultural product area corresponds to one type of agricultural product; buries a soil moisture sensor in the agricultural product area, the soil moisture sensor is used to detect the soil moisture in the agricultural product area, and deploys a micro oxygen concentration sensor on the surface of crops in the agricultural product area, the micro oxygen concentration sensor is used to detect oxygen concentration data.

[0039] The data acquisition unit is used to acquire average soil moisture data and average oxygen concentration data in the agricultural product area.

[0040] Furthermore, the air pressure data acquisition and data set construction module includes an air pressure data acquisition unit and a data set construction unit.

[0041] The air pressure data acquisition unit uses a geographic information system to acquire terrain features of the agricultural product area, wherein the terrain features include low-lying terrain and high-land terrain; based on the terrain features of the agricultural product area, different drone flight altitudes are preset for each agricultural product area, and the air pressure data above the agricultural product area is collected using an air pressure sensor carried by the drone.

[0042] The dataset construction unit: constructing agricultural product regional AA based on time series i Ground and high-altitude datasets.

[0043] Furthermore, the degree of change and environmental health fluctuation value calculation module includes a degree of change calculation unit and an environmental health fluctuation value calculation unit.

[0044] The variation calculation unit calculates the variation of the average soil moisture data and the average oxygen concentration data at different time points respectively; and calculates the variation of the air pressure data over the agricultural product area at different time points.

[0045] The environmental health fluctuation value calculation unit calculates the environmental health fluctuation value of the agricultural product area at different time points based on the average soil moisture change, the average oxygen concentration change and the air pressure data change.

[0046] Furthermore, the coordinate system construction and early warning module includes a coordinate system construction unit and an early warning unit.

[0047] The coordinate system construction unit: based on the time series, performs iterative analysis of the agricultural product area, obtains the environmental health fluctuation value calculated in each iteration of the agricultural product area, and constructs an environmental health fluctuation value set; based on the environmental health fluctuation value set, constructs an environmental health fluctuation coordinate system based on the agricultural product area, the horizontal coordinate of the environmental health fluctuation coordinate system is the time point, the vertical coordinate of the environmental health fluctuation coordinate system is the environmental health fluctuation value, and the curve in the environmental health fluctuation coordinate system is recorded as the environmental health fluctuation curve of the agricultural product area; based on the agricultural product area, performs a second iteration, superimposes the environmental health fluctuation coordinate systems of different agricultural product areas, calculates the difference between the vertical coordinates of different environmental health fluctuation curves, obtains the maximum difference, presets a difference threshold, determines whether different agricultural product areas are similar, and adds similar agricultural product areas to a similar group.

[0048] The early warning unit obtains all similar groups, presets an environmental health fluctuation value threshold, and if there are agricultural product areas in the similar groups whose environmental health fluctuation values ​​are greater than the environmental health fluctuation value threshold, an environmental health abnormality early warning is issued for all agricultural product areas in the similar groups.

[0049] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in the intelligent monitoring method and system of the agricultural product production environment based on data analysis provided by the present invention, accurate survey and real-time monitoring of the agricultural product production environment are realized through the deployment of high-precision remote sensing imaging equipment and sensors; soil moisture sensors and micro oxygen concentration sensors can be used to accurately obtain soil moisture and oxygen concentration data of each agricultural product area, providing a reliable basis for subsequent environmental change analysis; then, by obtaining air pressure data and adjusting the flight altitude of the drone in combination with terrain features, the accuracy of air pressure data collection is further improved; on this basis, by calculating soil moisture, oxygen concentration and air pressure variation, the environmental fluctuation is quantified, and potential abnormal phenomena (such as over-irrigation, drought or unfavorable climate, etc.) are timely revealed, providing a scientific basis for precision agricultural management; finally, based on the calculation and iterative analysis of environmental health fluctuation values, the environmental health of different agricultural product areas can be comprehensively evaluated, and by constructing an environmental health fluctuation coordinate system and similarity groups, an environmental health abnormality warning can be issued in time, helping agricultural producers to take intervention measures at an appropriate time to ensure the healthy growth of crops, thereby improving the quality and yield of agricultural products. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0051] Figure 1 It is a schematic diagram of the steps of the intelligent monitoring method of the production environment of agricultural products based on data analysis of the present invention;

[0052] Figure 2 It is a structural schematic diagram of the intelligent monitoring system for the production environment of agricultural products based on data analysis of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] See also Figure 1 In the first embodiment, a method for intelligently monitoring the environment of agricultural product production areas based on data analysis is provided, and the method comprises the following steps:

[0055] Step S1: Divide the agricultural product producing area into several agricultural product areas, deploy soil moisture sensors and micro oxygen concentration sensors in the agricultural product areas; and obtain average soil moisture data and average oxygen concentration data.

[0056] Specifically, high-precision remote sensing imaging equipment is used to survey the use scope of agricultural product producing areas, and the use scope of the agricultural product producing areas is divided into several agricultural product areas through gridding, wherein one agricultural product area corresponds to one type of agricultural product; a soil moisture sensor is buried in the agricultural product area, and the soil moisture sensor is used to detect the soil moisture in the agricultural product area; a micro oxygen concentration sensor is deployed on the surface of crops in the agricultural product area, and the micro oxygen concentration sensor is used to detect oxygen concentration data.

[0057] Furthermore, the i-th agricultural product area is recorded as AA i , get the agricultural product area AA i The average soil moisture data within is recorded as AMD i ; Get agricultural product area AA i The average oxygen concentration data within is recorded as AOD i .

[0058] Step S2: Obtain the air pressure data above the agricultural product area; construct a ground data set and an air data set of the agricultural product area based on a time series.

[0059] Specifically, get the agricultural product area AA i The air pressure data above is as follows:

[0060] Using geographic information system to obtain regional AA of agricultural products iThe terrain features include low-lying terrain and high-land terrain; based on the agricultural product area AA i Based on the terrain features of the agricultural product area, different drone flight altitudes are preset for each agricultural product area, and the pressure sensor carried by the drone is used to collect the AA data of the agricultural product area. i Air pressure data above, recorded as APD i .

[0061] Furthermore, we construct an agricultural product regional AA based on time series. i The ground dataset and high-altitude dataset are denoted as D ground (t) = {AMD i (t), AOD i (t)|i∈[1,I],t∈[1,T]} and D air (t) = {APD i (t)|i∈[1,I],t∈[1,T]}, where AMD i (t) represents the average soil moisture data at time point t, AOD i (t) represents the average oxygen concentration data at time point t, APD i (t) represents the air pressure data at time point t, I represents the total number of agricultural product areas, and T represents the total number of time points.

[0062] Step S3: Calculate the average soil moisture variation, average oxygen concentration variation and air pressure data variation; calculate the environmental health fluctuation value of the agricultural product area.

[0063] Specifically, calculate the average soil moisture data AMD i (t) and average oxygen concentration data AOD i (t) The average soil moisture change and average oxygen concentration change from time point t to time point t+1 are calculated as follows:

[0064]

[0065] Among them, ΔAMD i (t) represents the average soil moisture change, AMD i (t+1) represents the average soil moisture data at time point t+1, ΔAOD i (t) represents the average oxygen concentration change, AOD i (t+1) represents the average oxygen concentration data at time point t+1.

[0066] For example, assuming that time point t is 1, the average soil moisture data AMD1(1) of agricultural product area AA1 is 4, AMD1(2) is 6, and the average oxygen concentration data AOD1(1) of agricultural product area AA1 is 6, AOD1(2) is 7. Substitute them into the formula to calculate the average soil moisture change Average oxygen concentration change

[0067] Further, calculate the agricultural product area AA i Air pressure data APD i (t) The change in air pressure data from time point t to time point t+1 is calculated as follows:

[0068] ΔAPD i (t) = ln[APD i (t+1)]-ln[APD i (t)];

[0069] Where, ΔAPD i (t) represents the change of air pressure data, APD i (t+1) represents the air pressure data at time point t+1.

[0070] For example, assuming that the air pressure data APD1(1) of the agricultural product area AA1 is 1005 and APD1(2) is 1050, the air pressure data change ΔAPD1(1) is calculated as follows: ln

[1050] -ln

[1005] =6.97-6.91=0.06.

[0071] Furthermore, based on the average soil moisture change ΔAMD i (t), average oxygen concentration change ΔAOD i (t) and air pressure data change ΔAPD i (t), calculate the agricultural product area AA from time point t to time point t+1 i The environmental health fluctuation value is calculated as follows:

[0072] R env (AA i , t) = [ΔAMD i (t)+∈] m ×[ΔAOD i (t)+∈] d ×[ΔAPD i (t)+∈] p ;

[0073] Among them, R env (AA i , t) represents the agricultural product area AA from time point t to time point t+1i The environmental health fluctuation value, m, d and p represent the influencing factors of the preset average soil moisture data, average oxygen concentration data and air pressure data respectively, and ∈ represents the preset smoothing factor.

[0074] For example, assuming that m is 2, d is 3, p is 1, and the smoothing factor ∈ is 0.1, the environmental health fluctuation value R is calculated by substituting it into the formula: env (AA1, 1) = (0.5 + 0.1) 2 +(0.17+0.1) 3 +(0.06+0.1) 1 =0.36+0.073+0.16=0.593.

[0075] Step S4: Obtain all environmental health fluctuation values ​​of agricultural product areas within the time series and construct an environmental health fluctuation coordinate system; superimpose the environmental health fluctuation coordinate systems of different agricultural product areas and determine whether different agricultural product areas are similar; preset environmental health fluctuation value thresholds, analyze and output environmental health abnormality warnings.

[0076] Specifically, let t = t + 1, return to step S3, and perform agricultural product area AA i Iterative analysis, when t = T-1, stop the iteration and obtain the agricultural product area AA i The environmental health fluctuation value calculated in each iteration is used to construct the environmental health fluctuation value set, which is denoted as R env，i = {R env (AA i , t)|t∈[1,T-1]}.

[0077] For example, suppose T is 4 and R env (AA1, 2) = 0.6, R env (AA1, 3) = 0.7, given R env (AA1, 1) = 0.593, then R env，1 ={0.593, 0.6, 0.7}.

[0078] Furthermore, based on the environmental health fluctuation value set, an agricultural product regional AA i The environmental health fluctuation coordinate system is a time point, the ordinate of the environmental health fluctuation coordinate system is the environmental health fluctuation value, and the curve in the environmental health fluctuation coordinate system is recorded as the agricultural product area AA i Environmental health fluctuation curve L i .

[0079] Furthermore, let i=i+1, return to step S3-step S4.2, and convert the agricultural product area AA i+1Environmental health fluctuation coordinate system and agricultural product regional AA i The environmental health fluctuation coordinate system is superimposed to construct a dual environmental health fluctuation coordinate system, wherein the dual environmental health fluctuation coordinate system includes the environmental health fluctuation curve L i and environmental health fluctuation curve L i+1 .

[0080] Calculate the environmental health fluctuation curve L i and environmental health fluctuation curve L i+1 The difference in the vertical coordinates: d i，i+1 =|R env (AA i , t)-R env (AA i+1 , t)|, where R env (AA i+1 , t) represents the agricultural product area AA from time point t to time point t+1 i+1 Environmental health fluctuation value; get the maximum difference d max =max t∈[1，T-1] d i，i+1 .

[0081] For example, suppose the environmental health fluctuation value set R of agricultural product area AA2 env，2 ={0.5, 0.57, 0.62}, substitute into the formula to calculate d 1，2 =(0.093, 0.03, 0.08}, then d max =0.093.

[0082] Furthermore, a difference threshold τ is preset, if d max <τ, then determine the environmental health fluctuation curve L i and environmental health fluctuation curve L i+1 Similar, then the agricultural product area AA i and agricultural product area AA i+1 Similar environmental health fluctuations, the construction of regional AA based on agricultural products i Similarity group S i , the agricultural product area AA i and agricultural product area AA i+1 Join Similar Groups i And, if the agricultural product area AA is determined i+1 and agricultural product area AA i+2 If the fluctuations in environmental health are similar, the agricultural product area AA i+2 Join Similar Groups i middle.

[0083] If d max >τ, then determine the environmental health fluctuation curve L iand environmental health fluctuation curve L i+1 If not similar, then the agricultural product area AA i and agricultural product area AA i+1 If the environmental health fluctuations are not similar, then construct the AA based on agricultural product regions. i and agricultural product area AA i+1 Similarity group S i and similar group S i+1 , the agricultural product area AA i Join Similar Groups i Middle, agricultural products area AA i+1 Join Similar Groups i+1 middle.

[0084] If in the previous iteration, the agricultural product area AA i and agricultural product area AA i+1 The environmental health fluctuations of the latter iteration are not similar, while in the latter iteration, the agricultural product area AA i+1 and agricultural product area AA i+2 If the fluctuations in environmental health are similar, the agricultural product area AA i+2 Join the agricultural product area AA i+1 The constructed similarity group S i+1 middle.

[0085] When i=I-1, stop the iteration, obtain all similar groups, and preset the environmental health fluctuation value threshold θ. If R env (AA i , t)>θ, then the agricultural product area AA is determined i If there is an abnormality in the environmental health of the agricultural product area, i Similarity group S i Abnormal environmental health warnings were issued for all agricultural product areas.

[0086] For example, Assumption 1: If the difference threshold τ is 0.1, then d max <τ, then it is determined that the environmental health fluctuation curve L1 is similar to the environmental health fluctuation curve L2, and the environmental health fluctuations of agricultural product area AA1 and agricultural product area AA2 are similar, then a similarity group S1 based on agricultural product area AA1 is constructed, and agricultural product area AA1 and agricultural product area AA2 are added to the similarity group S1, and, if it is determined that the environmental health fluctuations of agricultural product area AA2 and agricultural product area AA3 are similar, then agricultural product area AA3 is added to the similarity group S1.

[0087] Assuming that the environmental health fluctuation threshold θ is 0.5, then R env (AA1, 1)>θ, it is determined that the environmental health of the agricultural product area AA1 is abnormal, and an environmental health abnormality warning is issued to all agricultural product areas in the similar group S1 where the agricultural product area AA1 is located.

[0088] Assumption 2: If the difference threshold τ is 0.05, then d max >τ, then it is determined that the environmental health fluctuation curve L1 and the environmental health fluctuation curve L2 are not similar, and the environmental health fluctuations of the agricultural product area AA1 and the agricultural product area AA2 are not similar, then similarity group S1 and similarity group S2 based on agricultural product area AA1 and agricultural product area AA2 are respectively constructed, and the agricultural product area AA1 is added to the similarity group S1, and the agricultural product area AA2 is added to the similarity group S2.

[0089] See also Figure 2 In the second embodiment of the present invention, an intelligent monitoring system for the environment of agricultural product production areas based on data analysis is provided, the system comprising: a sensor installation and data acquisition module, an air pressure data acquisition and data set construction module, a change degree and environmental health fluctuation value calculation module and a coordinate system construction and early warning module.

[0090] The sensor installation and data acquisition module divides the agricultural product producing area into several agricultural product areas, arranges soil moisture sensors and micro oxygen concentration sensors in the agricultural product areas, and acquires average soil moisture data and average oxygen concentration data.

[0091] The air pressure data acquisition and data set construction module is used to acquire the air pressure data above the agricultural product area and to construct a ground data set and an air data set of the agricultural product area based on a time series.

[0092] The variation degree and environmental health fluctuation value calculation module calculates the average soil moisture variation degree, the average oxygen concentration variation degree and the air pressure data variation degree; and calculates the environmental health fluctuation value of the agricultural product area.

[0093] The coordinate system construction and early warning module: obtains all environmental health fluctuation values ​​of agricultural product areas within the time series and constructs an environmental health fluctuation coordinate system; superimposes the environmental health fluctuation coordinate systems of different agricultural product areas and determines whether different agricultural product areas are similar; presets environmental health fluctuation value thresholds, analyzes and outputs environmental health abnormality early warnings.

[0094] Furthermore, the sensor installation and data acquisition module includes a sensor installation unit and a data acquisition unit.

[0095] The sensor installation unit: uses high-precision remote sensing imaging equipment to survey the use range of agricultural product production areas, and divides the use range of the agricultural product production areas into several agricultural product areas through grid division, wherein one agricultural product area corresponds to one type of agricultural product; buries a soil moisture sensor in the agricultural product area, the soil moisture sensor is used to detect the soil moisture in the agricultural product area, and deploys a micro oxygen concentration sensor on the surface of crops in the agricultural product area, the micro oxygen concentration sensor is used to detect oxygen concentration data.

[0096] The data acquisition unit is used to acquire average soil moisture data and average oxygen concentration data in the agricultural product area.

[0097] Furthermore, the air pressure data acquisition and data set construction module includes an air pressure data acquisition unit and a data set construction unit.

[0098] The air pressure data acquisition unit uses a geographic information system to acquire terrain features of the agricultural product area, wherein the terrain features include low-lying terrain and high-land terrain; based on the terrain features of the agricultural product area, different drone flight altitudes are preset for each agricultural product area, and the air pressure data above the agricultural product area is collected using an air pressure sensor carried by the drone.

[0099] The dataset construction unit: constructing agricultural product regional AA based on time series i Ground and high-altitude datasets.

[0100] Furthermore, the degree of change and environmental health fluctuation value calculation module includes a degree of change calculation unit and an environmental health fluctuation value calculation unit.

[0101] The variation calculation unit calculates the variation of the average soil moisture data and the average oxygen concentration data at different time points respectively; and calculates the variation of the air pressure data over the agricultural product area at different time points.

[0102] The environmental health fluctuation value calculation unit calculates the environmental health fluctuation value of the agricultural product area at different time points based on the average soil moisture change, the average oxygen concentration change and the air pressure data change.

[0103] Furthermore, the coordinate system construction and early warning module includes a coordinate system construction unit and an early warning unit.

[0104] The coordinate system construction unit: based on the time series, performs iterative analysis of the agricultural product area, obtains the environmental health fluctuation value calculated in each iteration of the agricultural product area, and constructs an environmental health fluctuation value set; based on the environmental health fluctuation value set, constructs an environmental health fluctuation coordinate system based on the agricultural product area, the horizontal coordinate of the environmental health fluctuation coordinate system is the time point, the vertical coordinate of the environmental health fluctuation coordinate system is the environmental health fluctuation value, and the curve in the environmental health fluctuation coordinate system is recorded as the environmental health fluctuation curve of the agricultural product area; based on the agricultural product area, performs a second iteration, superimposes the environmental health fluctuation coordinate systems of different agricultural product areas, calculates the difference between the vertical coordinates of different environmental health fluctuation curves, obtains the maximum difference, presets a difference threshold, determines whether different agricultural product areas are similar, and adds similar agricultural product areas to a similar group.

[0105] The early warning unit obtains all similar groups, presets an environmental health fluctuation value threshold, and if there are agricultural product areas in the similar groups whose environmental health fluctuation values ​​are greater than the environmental health fluctuation value threshold, an environmental health abnormality early warning is issued for all agricultural product areas in the similar groups.

[0106] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0107] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent monitoring method for the production environment of agricultural products based on data analysis, characterized in that: The method comprises the following steps: Step S1: Divide the agricultural product producing area into several agricultural product areas, and deploy soil moisture sensors and micro oxygen concentration sensors in the agricultural product areas; obtain average soil moisture data and average oxygen concentration data; Step S2: Obtaining air pressure data above the agricultural product area; constructing a ground data set and an air data set of the agricultural product area based on a time series; Step S3: Calculate the average soil moisture variation, average oxygen concentration variation and air pressure data variation; calculate the environmental health fluctuation value of the agricultural product area; Step S4: Obtain all environmental health fluctuation values ​​of agricultural product areas within the time series and construct an environmental health fluctuation coordinate system; superimpose the environmental health fluctuation coordinate systems of different agricultural product areas and determine whether different agricultural product areas are similar; preset environmental health fluctuation value thresholds, analyze and output environmental health abnormality warnings.

2. The method for intelligent monitoring of agricultural product production environment based on data analysis according to claim 1 is characterized in that: The specific implementation process of step S1 includes: Step S1.1: Use high-precision remote sensing imaging equipment to survey the use range of agricultural product production areas, and divide the use range of the agricultural product production areas into several agricultural product areas through grid division, wherein one agricultural product area corresponds to one type of agricultural product; bury a soil moisture sensor in the agricultural product area, the soil moisture sensor is used to detect the soil moisture in the agricultural product area, and deploy a micro oxygen concentration sensor on the surface of the crops in the agricultural product area, the micro oxygen concentration sensor is used to detect oxygen concentration data; Step S1.2: Record the i-th agricultural product area as AA i , get the agricultural product area AA i The average soil moisture data within is recorded as AMD i ; Get agricultural product area AA i The average oxygen concentration data within is recorded as AOD i .

3. The method for intelligent monitoring of agricultural product production environment based on data analysis according to claim 2 is characterized in that: The specific implementation process of step S2 includes: Step S2.1: Get agricultural product area AA i The air pressure data above is as follows: Step S2.11: Using geographic information system, obtain agricultural product area AA i The terrain features include low-lying terrain and high-land terrain; based on the agricultural product area AA i Based on the terrain features of the agricultural product area, different drone flight altitudes are preset for each agricultural product area, and the pressure sensor carried by the drone is used to collect the AA data of the agricultural product area. i Air pressure data above, recorded as APD i ; Step S2.2: Construct agricultural product regional AA based on time series i The ground dataset and high-altitude dataset are denoted as D ground (t) = {AMD i (t),AOD i (t)|i∈[1,I],t∈[1,T]} and D air (T) = {APD i (T)|i∈[1,I],t∈[1,T]}, where AMD i (t) represents the average soil moisture data at time point t, AMD i (t) represents the average oxygen concentration data at time point t, APD i (t) represents the air pressure data at time point t, I represents the total number of agricultural product areas, and T represents the total number of time points.

4. The method for intelligent monitoring of agricultural product production environment based on data analysis according to claim 3 is characterized in that: The specific implementation process of step S3 includes: Step S3.1: Calculate the average soil moisture data AMD i (t) and average oxygen concentration data AOD i (t) The average soil moisture change and average oxygen concentration change from time point t to time point t+1 are calculated as follows: Among them, ΔAMD i (t) represents the average soil moisture change, AMD i (t+1) represents the average soil moisture data at time point t+1, ΔAOD i (t) represents the average oxygen concentration change, AOD i (t+1) represents the average oxygen concentration data at time point t+1; Step S3.2: Calculate the agricultural product area AA i Air pressure data APD i (t) The change in air pressure data from time point t to time point t+1 is calculated as follows: ΔAPD i (t)=ln[APD i (t+1)]-ln[APD i (t)]; Where ΔAPD i (t) represents the change of air pressure data, APD i (t+1) represents the air pressure data at time point t+1; Step S3.3: Based on the average soil moisture change ΔAMD i (t), average oxygen concentration change ΔAOD i (t) and air pressure data change ΔAPD i (t), calculate the agricultural product area AA from time point t to time point t+1 i The environmental health fluctuation value is calculated as follows: R env (AA i ,t)=[ΔAMD i (t)+∈] m ×[ΔAOD i (t)+∈] d ×[ΔAPD i (t)+∈] p ; Among them, R env (AA i ,t) represents the agricultural product area AA from time point t to time point t+1 i The environmental health fluctuation value, m, d and p represent the influencing factors of the preset average soil moisture data, average oxygen concentration data and air pressure data respectively, and ∈ represents the preset smoothing factor.

5. The method for intelligent monitoring of agricultural product production environment based on data analysis according to claim 4 is characterized in that: The specific implementation process of step S4 includes: Step S4.1: Set t = t + 1, return to step S3, and perform agricultural product area AA i Iterative analysis, when t = T-1, stop the iteration and obtain the agricultural product area AA i The environmental health fluctuation value calculated in each iteration is used to construct the environmental health fluctuation value set, which is denoted as R env,i = {R env (AA i ,t)|t∈[1,T-1]}; Step S4.2: Based on the environmental health fluctuation value set, construct an agricultural product area AA i The environmental health fluctuation coordinate system is a time point, the ordinate of the environmental health fluctuation coordinate system is the environmental health fluctuation value, and the curve in the environmental health fluctuation coordinate system is recorded as the agricultural product area AA i Environmental health fluctuation curve L i ; Step S4.3: Set i=i+1, return to step S3-step S4.2, and convert the agricultural product area AA i+1 Environmental health fluctuation coordinate system and agricultural product regional AA i The environmental health fluctuation coordinate system is superimposed to construct a dual environmental health fluctuation coordinate system, wherein the dual environmental health fluctuation coordinate system includes the environmental health fluctuation curve L i and environmental health fluctuation curve L i+1 ; Calculate the environmental health fluctuation curve L i and environmental health fluctuation curve L i+1 The difference in the vertical coordinates: d i,i+1 =|R env (AA i ,t)-R env (AA i+1 ,t)|, where R env (AA i+1 ,t) represents the agricultural product area AA from time point t to time point t+1 i+1 Environmental health fluctuation value; get the maximum difference d max =max t∈[1,T-1] d i,i+1 ; Preset difference threshold τ, if d max <τ, then determine the environmental health fluctuation curve L i and environmental health fluctuation curve L i+1 Similar, then the agricultural product area AA i and agricultural product area AA i+1 Similar environmental health fluctuations, the construction of regional AA based on agricultural products i Similarity group S i , the agricultural product area AA i and agricultural product area AA i+1 Join Similar Groups i And, if the agricultural product area AA is determined i+1 and agricultural product area AA i+2 If the fluctuations in environmental health are similar, the agricultural product area AA i+2 Join Similar Groups i middle; If d max >τ, then determine the environmental health fluctuation curve L i and environmental health fluctuation curve L i+1 If not similar, then the agricultural product area is AA i and agricultural product area AA i+1 If the environmental health fluctuations are not similar, then construct the AA based on agricultural product regions. i and agricultural product area AA i+1 Similarity group S i and similar group S i+1 , the agricultural product area AA i Join Similar Groups i Middle, agricultural products area AA i+1 Join Similar Groups i+1 middle; When i=I-1, stop the iteration, obtain all similar groups, and preset the environmental health fluctuation value threshold θ. If R env (AA i ,t)>θ, then determine the agricultural product area AA i If there is an abnormality in the environmental health of the agricultural product area, i Similarity group S i Abnormal environmental health warnings were issued for all agricultural product areas.

6. An intelligent monitoring system for the environment of agricultural product production areas based on data analysis, which implements an intelligent monitoring method for the environment of agricultural product production areas based on data analysis as described in any one of claims 1 to 5, characterized in that: The system includes: a sensor installation and data acquisition module, an air pressure data acquisition and data set construction module, a change degree and environmental health fluctuation value calculation module, and a coordinate system construction and early warning module; The sensor installation and data acquisition module: divides the agricultural product production area into several agricultural product areas, arranges soil moisture sensors and micro oxygen concentration sensors in the agricultural product areas; obtains average soil moisture data and average oxygen concentration data; The air pressure data acquisition and data set construction module: acquires the air pressure data above the agricultural product area; constructs a ground data set and an air data set of the agricultural product area based on a time series; The variation degree and environmental health fluctuation value calculation module: calculates the average soil moisture variation degree, the average oxygen concentration variation degree and the air pressure data variation degree; calculates the environmental health fluctuation value of the agricultural product area; The coordinate system construction and early warning module: obtains all environmental health fluctuation values ​​of agricultural product areas within the time series and constructs an environmental health fluctuation coordinate system; superimposes the environmental health fluctuation coordinate systems of different agricultural product areas and determines whether different agricultural product areas are similar; presets environmental health fluctuation value thresholds, analyzes and outputs environmental health abnormality early warnings.

7. The intelligent monitoring system for agricultural product production environment based on data analysis according to claim 6 is characterized in that: The sensor installation and data acquisition module includes a sensor installation unit and a data acquisition unit; The sensor installation unit: uses high-precision remote sensing imaging equipment to survey the use range of the agricultural product production area, and divides the use range of the agricultural product production area into several agricultural product areas through grid division, wherein one agricultural product area corresponds to one type of agricultural product; buries a soil moisture sensor in the agricultural product area, the soil moisture sensor is used to detect the soil moisture in the agricultural product area, and deploys a micro oxygen concentration sensor on the surface of the crops in the agricultural product area, the micro oxygen concentration sensor is used to detect oxygen concentration data; The data acquisition unit is used to acquire average soil moisture data and average oxygen concentration data in the agricultural product area.

8. The intelligent monitoring system for agricultural product production environment based on data analysis according to claim 7 is characterized in that: The air pressure data acquisition and data set construction module includes an air pressure data acquisition unit and a data set construction unit; The air pressure data acquisition unit: uses a geographic information system to acquire the terrain characteristics of the agricultural product area, wherein the terrain characteristics include low-lying terrain and high-land terrain; based on the terrain characteristics of the agricultural product area, a different drone flight altitude is preset for each agricultural product area, and the air pressure data above the agricultural product area is collected using the air pressure sensor carried by the drone; The dataset construction unit: constructing agricultural product regional AA based on time series i Ground and high-altitude datasets.

9. The intelligent monitoring system for agricultural product production environment based on data analysis according to claim 8 is characterized in that: The change degree and environmental health fluctuation value calculation module includes a change degree calculation unit and an environmental health fluctuation value calculation unit; The variation calculation unit is used to calculate the variation of the average soil moisture data and the average oxygen concentration data at different time points; and calculate the variation of the air pressure data above the agricultural product area at different time points. The environmental health fluctuation value calculation unit calculates the environmental health fluctuation value of the agricultural product area at different time points based on the average soil moisture change, the average oxygen concentration change and the air pressure data change.

10. The intelligent monitoring system for agricultural product production environment based on data analysis according to claim 9 is characterized in that: The coordinate system construction and early warning module includes a coordinate system construction unit and an early warning unit; The coordinate system construction unit: based on the time series, performs iterative analysis of the agricultural product area, obtains the environmental health fluctuation value calculated in each iteration of the agricultural product area, and constructs an environmental health fluctuation value set; Based on the environmental health fluctuation value set, an environmental health fluctuation coordinate system based on the agricultural product area is constructed, wherein the abscissa of the environmental health fluctuation coordinate system is the time point, and the ordinate of the environmental health fluctuation coordinate system is the environmental health fluctuation value, and the curve in the environmental health fluctuation coordinate system is recorded as the environmental health fluctuation curve of the agricultural product area; Based on the agricultural product area, a second iteration is performed to superimpose the environmental health fluctuation coordinate systems of different agricultural product areas, calculate the difference in the vertical coordinates of different environmental health fluctuation curves, obtain the maximum difference, preset the difference threshold, determine whether different agricultural product areas are similar, and add similar agricultural product areas to similar groups; The early warning unit obtains all similar groups, presets an environmental health fluctuation value threshold, and if there are agricultural product areas in the similar groups whose environmental health fluctuation values ​​are greater than the environmental health fluctuation value threshold, an environmental health abnormality early warning is issued for all agricultural product areas in the similar groups.

Images