Huanglongguo meteorological disaster monitoring method and system based on Internet of Things

Abstract

The invention relates to the technical field of data processing, and particularly discloses a Huanglongguo meteorological disaster monitoring method and system based on the Internet of Things, and the method comprises the steps: firstly, obtaining a target environment meteorological risk parameter, determining a risk level through model analysis, and synchronously monitoring the image attributes of Huanglongguo fruits, according to a preset threshold value, the planting areas are divided into a qualified type, a critical qualified type and an unqualified type; on the basis, fusing the meteorological risk and a region classification result, and implementing hierarchical adjustment; meanwhile, fruit burn characteristic parameters are continuously monitored, and whether secondary adjustment is needed or not is dynamically judged by means of real-time analysis of the Internet of Things; after adjustment, images are collected again for contrastive analysis, and once burn risks or quality decline trends are found, corresponding disaster early warning is triggered immediately; according to the scheme, the intelligent level of management of the growth environment of the Huanglongguo fruits can be effectively improved, early warning of meteorological disasters can be achieved, burn and disease losses are reduced, the fruit quality and yield are improved through accurate regulation and control, and scientific and efficient planting decision support is provided for farmers.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for monitoring Huanglong fruit meteorological disasters based on the Internet of Things. Background Art

[0002] The Internet of Things-based Huanglongguo meteorological disaster monitoring method and system relies on the Internet of Things technology to build an intelligent monitoring system, which has significant advantages such as multi-dimensional real-time monitoring, accurate early warning, data-driven decision-making and dynamic prevention and control. By deploying a sensor network, the system can conduct high-frequency real-time collection of key meteorological factors such as temperature and humidity, light, wind speed and direction, and rainfall that affect the growth of Huanglongguo, breaking through the time and space limitations of traditional manual monitoring and realizing early perception of disaster hazards; with the help of Internet of Things communication technology, the monitoring data can be transmitted to the cloud platform in real time, and abnormal meteorological parameters can be accurately identified through big data analysis models, and the probability and impact of disasters can be predicted in advance. The warning time is greatly improved compared with traditional methods; it can effectively improve the meteorological disaster response capabilities of Huanglongguo planting and provide scientific and technological support for the stable production and increase of Huanglongguo income.

[0003] For example, the invention patent with publication number CN119903207A discloses a method for constructing priority areas for vegetation engineering construction in dry and hot river valley basins based on micrometeorology; it includes drawing construction areas and regional boundaries, dividing the construction areas into sub-areas, screening out effective sub-areas from the sub-areas, obtaining comprehensive micrometeorological parameters of the effective sub-areas, calculating construction evaluation values, and constructing construction priority areas from the effective sub-areas. Sub-areas are drawn according to regional boundaries to achieve the effect of breaking up larger areas in dry and hot river valley basins into smaller areas. At the same time, by collecting comprehensive micrometeorological parameters of effective sub-areas, detailed collection and analysis of micrometeorological parameters of small areas in dry and hot river valley basins are realized, and construction priority areas that meet the needs of vegetation engineering construction are identified based on construction priority values.

[0004] For example, the invention patent with publication number CN115309832A discloses an agricultural meteorological data processing system and method thereof, which relate to the field of agricultural meteorological technology. The technical solutions adopted by the method include S1, data collection; S2, data classification and storage; S3, data call; the system includes a communication system, and also includes a database, server and terminal connected through the communication system network; the database includes at least three types: basic meteorological database, agricultural meteorological database, and agricultural information database; the server is used to execute the above method; the terminal is used to submit request information and send it to the server and receive products fed back from the server.

[0005] However, in the process of implementing the embodiments of the present application, the present application found that the above technology has at least the following technical problems: the skin of the yellow dragon fruit is relatively thin and the waxy layer on the epidermis is relatively fragile, and its ability to reflect and block strong light is weak, making it difficult to resist the strong ultraviolet radiation in the high temperature season in summer. Direct strong light can easily cause burns to the skin, and burned fruits are difficult to develop normally, resulting in a decrease in the commercial fruit filterability. Summary of the Invention

[0006] In response to the deficiencies in the prior art, the present invention provides a method and system for monitoring Huanglongguo meteorological disasters based on the Internet of Things, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: The first aspect of the present invention provides a Huanglong fruit meteorological disaster monitoring method based on the Internet of Things, including: step one, obtaining and analyzing the meteorological risk parameters of the target environment, thereby analyzing the meteorological risk level of the target environment; step two, monitoring the Huanglong fruit in each area, collecting and analyzing the Huanglong fruit fruit image attribute parameters in each area, obtaining analysis results, and classifying each area according to the analysis results, thereby obtaining regional classification results, and performing graded adjustment on each area based on the meteorological risk level of the target environment and the regional classification results; step three, monitoring and analyzing the Huanglong fruit burn characteristic parameters in each area, and judging whether to perform secondary adjustment on each area based on the Internet of Things, and at the same time obtaining the Huanglong fruit fruit image attribute parameters in each area after the secondary adjustment is completed, and judging whether to perform disaster warning for each area.

[0008] As a further method, the meteorological risk level of the target environment is analyzed. The specific analysis process is: compare the Huanglong fruit meteorological risk coefficient with the Huanglong fruit meteorological risk threshold; if the Huanglong fruit meteorological risk coefficient is greater than or equal to the Huanglong fruit meteorological risk threshold, the meteorological risk level of the target environment is marked as high meteorological risk; if the Huanglong fruit meteorological risk coefficient is less than the Huanglong fruit meteorological risk threshold, the meteorological risk level of the target environment is marked as low meteorological risk.

[0009] As a further method, each area is classified according to the analysis results. The specific classification process is: the yellow dragon fruit fruit abnormality coefficient of each area is compared with the first abnormality coefficient and the second abnormality coefficient; if the yellow dragon fruit fruit abnormality coefficient of a certain area is less than the first abnormality coefficient, the area is marked as a qualified area; if the yellow dragon fruit fruit abnormality coefficient of a certain area is greater than or equal to the first abnormality coefficient and less than or equal to the second abnormality coefficient, the area is marked as a critical qualified area; if the yellow dragon fruit fruit abnormality coefficient of a certain area is greater than the second abnormality index, the area is marked as an unqualified area, and an early warning is issued for the area.

[0010] As a further method, each area is regulated in a graded manner, and the specific regulation process is as follows: if an area is a qualified area and the meteorological risk level of the target environment is low meteorological risk, there is no need to regulate the area; if an area is a qualified area and the meteorological risk level of the target environment is high meteorological risk, the first-level regulation measures are matched to the area, thereby realizing graded regulation of the area; if an area is a critical qualified area and the meteorological risk level of the target environment is low meteorological risk, the second-level regulation measures are matched to the area, thereby realizing graded regulation of the area; if an area is a critical qualified area and the meteorological risk level of the target environment is high meteorological risk, the third-level regulation measures are matched to the area, thereby realizing graded regulation of the area; the first-level regulation measures refer to the The risk coefficient and the meteorological risk threshold of the yellow dragon fruit are used to obtain the meteorological risk deviation value of the yellow dragon fruit, and the shading rate improvement coefficient and the fogging frequency improvement coefficient are matched based on the meteorological risk deviation value of the yellow dragon fruit, so as to increase the shading rate of the lower sunshade net and the fogging frequency of the fogging equipment; the secondary adjustment measure refers to obtaining the first abnormal deviation value based on the yellow dragon fruit fruit abnormality coefficient and the first abnormal coefficient, and matching the fan speed improvement coefficient based on the first abnormal deviation value, so as to increase the fan speed; the tertiary adjustment measure refers to matching the shading rate secondary improvement coefficient and the fogging frequency secondary improvement coefficient based on the meteorological risk deviation value of the yellow dragon fruit, so as to further increase the shading rate of the lower sunshade net and the fogging frequency of the fogging equipment, and at the same time matching the fan speed secondary improvement coefficient based on the first abnormal deviation value, so as to further increase the fan speed.

[0011] As a further method, it is determined whether to make secondary adjustments to each area. The specific analysis process is: comparing the burn disaster warning index of each area with the burn disaster warning threshold; if the burn disaster warning index of a certain area is less than the burn disaster warning threshold, it is determined that no secondary adjustment is required for the area; if the burn disaster warning index of a certain area is greater than or equal to the burn disaster warning threshold, it is determined that secondary adjustment is required for the area. The specific adjustment content is: based on the burn disaster warning index and the burn disaster warning threshold of the area, the burn disaster warning deviation value of the area is obtained, and the burn disaster warning deviation value is compared with the burn disaster warning deviation threshold; if the burn disaster warning deviation value of the area is less than the burn disaster warning deviation threshold, the fogging time extension coefficient is matched based on the burn disaster warning deviation value of the area, thereby extending the fogging time; if the burn disaster warning deviation value of the area is greater than or equal to the burn disaster warning deviation threshold, the upper sunshade net is started, and the shading rate of the upper sunshade net is matched based on the burn disaster warning deviation value of the area.

[0012] As a further method, it is determined whether to issue a disaster warning for each region. The specific analysis process is: the yellow dragon fruit fruit abnormality coefficient of each region after the secondary adjustment is marked as the secondary yellow dragon fruit fruit abnormality coefficient, the secondary yellow dragon fruit fruit abnormality coefficient is compared with the first abnormality coefficient and the second abnormality coefficient, and the regions are reclassified; if a region is changed from a qualified region to a critical qualified region, it is determined that a monitoring and early warning is issued for the region; if a region is changed from a qualified region to an unqualified region, it is determined that an emergency early warning is issued for the region; if a region is changed from a critical region to an unqualified region, it is determined that an abnormal early warning is issued for the region; if a region is changed from an unqualified region to a critical qualified region, it is determined that no early warning is issued for the region; if a region is changed from an unqualified region to a qualified region, it is determined that no early warning is issued for the region; if a region is changed from a critical region to a qualified region, it is determined that no early warning is issued for the region.

[0013] The second aspect of the present invention provides a Huanglong fruit meteorological disaster monitoring system based on the Internet of Things, including: a target environment meteorological monitoring module, used to obtain and analyze the meteorological risk parameters of the target environment, thereby analyzing the meteorological risk level of the target environment; a Huanglong fruit fruit status monitoring module, used to monitor the Huanglong fruit in each area, collect and analyze the Huanglong fruit fruit image attribute parameters in each area, obtain analysis results, and classify each area according to the analysis results, thereby obtaining regional classification results, and based on the meteorological risk level of the target environment and the regional classification results, perform graded adjustment on each area; a Huanglong fruit burn monitoring and adjustment module, used to monitor and analyze the Huanglong fruit burn characteristic parameters in each area, and determine whether to perform secondary adjustment on each area based on the Internet of Things, and at the same time obtain the Huanglong fruit fruit image attribute parameters of each area after the secondary adjustment is completed, and determine whether to perform disaster warning for each area.

[0014] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0015] (1) The present invention provides a method and system for monitoring meteorological disasters of yellow dragon fruit based on the Internet of Things, thereby constructing a full-chain management system from environmental risk identification, fruit status assessment to precise regulation and early warning. Through multi-source data fusion analysis and intelligent decision-making, the impact of meteorological disasters on yellow dragon fruit can be significantly reduced, and the decline in fruit quality and yield loss caused by strong light burns, high temperatures, etc. can be reduced. At the same time, the hierarchical regulation and dynamic early warning mechanism can realize the precise allocation of resources, reduce manpower and material costs, and improve the efficiency of planting management. The scheme is both scientific and practical, providing strong technical support for the stable production and increase of income of yellow dragon fruit and the sustainable development of the industry.

[0016] (2) Obtain and analyze meteorological risk parameters and determine the meteorological risk level to lay the data foundation for subsequent management. This step can predict the probability of disasters and the extent of their impact in advance by real-time monitoring of key meteorological factors, thus transforming passive disaster relief into active defense. Farmers can prepare protective materials and adjust agricultural arrangements in advance based on the risk level to avoid major losses caused by sudden meteorological disasters and ensure the stability and controllability of the dragon fruit growth environment.

[0017] (3) Monitor the image attribute parameters of the fruit and classify the regions, implement graded adjustments based on the meteorological risk level, and achieve precise management. This step uses image recognition technology to quantitatively assess the fruit status and accurately locate the planting areas with abnormalities, avoiding the waste of resources caused by "one-size-fits-all" management. Differentiated control strategies are formulated for different risk levels and regional categories, which can not only effectively improve the fruit growth conditions, but also enhance resource utilization efficiency and improve the overall quality of Huanglong Fruit.

[0018] (4) Continuously monitor the characteristic parameters of burns and conduct secondary adjustments and disaster warnings to build a refined prevention and control closed loop; it can keenly capture subtle changes in the risk of fruit burns, adjust the control measures in time to prevent the risk from expanding, and collect the fruit image attribute parameters again after the secondary adjustment for comparative analysis to ensure that the control effect meets the standards. If any abnormality is found, the corresponding level of disaster warning will be triggered immediately to guide farmers to take remedial measures to minimize the disaster losses. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0020] Figure 1 Schematic diagram of the method steps of the present invention.

[0021] Figure 2 This is a schematic diagram of system module connections of the present invention.

[0022] Figure 3 The present invention is a schematic flow chart of the steps of the method for evaluating the meteorological risk factor of Huanglong fruit.

[0023] Figure 4 The figure is a schematic flow chart of the steps of the method for determining the abnormal coefficient of Huanglong fruit of the present invention.

[0024] Figure 5 The figure is a flow chart of the steps of the method for hierarchically regulating each area according to the present invention.

[0025] Figure 6 The figure is a flow chart of the burn warning index method steps of the present invention.

[0026] Figure 7 The figure is a schematic flow chart of the steps of the secondary fruit abnormality coefficient method of the present invention. DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0028] Reference Figure 1 As shown, the first aspect of the present invention provides a Huanglong fruit meteorological disaster monitoring method based on the Internet of Things, including: step one, obtaining and parsing the meteorological risk parameters of the target environment, thereby analyzing the meteorological risk level of the target environment; step two, monitoring the Huanglong fruit in each area, collecting and analyzing the Huanglong fruit fruit image attribute parameters in each area, obtaining analysis results, and classifying each area according to the analysis results, thereby obtaining regional classification results, and performing graded adjustment on each area based on the meteorological risk level of the target environment and the regional classification results; step three, monitoring and analyzing the Huanglong fruit burn characteristic parameters in each area, and judging whether to perform secondary adjustment on each area based on the Internet of Things, and at the same time obtaining the Huanglong fruit fruit image attribute parameters in each area after the secondary adjustment is completed, and judging whether to perform disaster warning for each area.

[0029] Specifically, the meteorological risk parameters of the target environment are obtained and analyzed. The specific analysis process is as follows: the meteorological risk parameters include the light intensity factor of the target environment, the fruit surface temperature factor of the target environment, and the air humidity factor of the target environment.

[0030] The light intensity factor of the above-mentioned target environment indicates the degree of deviation between the light intensity of the target environment and the reference light intensity; the fruit surface temperature factor of the above-mentioned target environment indicates the degree of deviation between the fruit surface temperature of the target environment and the reference fruit surface temperature; the air humidity factor of the above-mentioned target environment indicates the degree of deviation between the air humidity of the target environment and the reference air humidity.

[0031] By introducing influence coefficients, we can quantify the influence of light intensity, fruit surface temperature, and air humidity on the meteorological risk coefficient of yellow dragon fruit. By coupling various degrees, we can obtain the meteorological risk coefficient of yellow dragon fruit. The meteorological risk coefficient of yellow dragon fruit represents the abnormal influence of the target environment's meteorological conditions on yellow dragon fruit. The specific evaluation method is as follows:

[0032] USLF=HLO×ε1+GHF×ε2+TNM×ε3;

[0033]

[0034] Wherein, USLF is the meteorological risk factor of yellow dragon fruit, HLO is the light intensity factor of the target environment, SVC is the light intensity of the target environment, SVK is the reference light intensity preset in the monitoring database, GHF is the fruit surface temperature factor of the target environment, HGT is the fruit surface temperature of the target environment, HGK is the reference fruit surface temperature preset in the monitoring database, TNM is the air humidity factor of the target environment, PIM is the air humidity of the target environment, PIK is the reference air humidity preset in the monitoring database, ε1 is the influence coefficient corresponding to the light intensity factor preset in the monitoring database, ε2 is the influence coefficient corresponding to the fruit surface temperature factor preset in the monitoring database, and ε3 is the influence coefficient corresponding to the air humidity factor preset in the monitoring database.

[0035] The above-mentioned light intensity refers to the luminous flux of visible light received per unit area of ​​the target environment, which can be obtained through an intelligent monitoring device with an integrated light sensor; the above-mentioned fruit surface temperature indicates the real-time temperature of the fruit surface, which can be obtained through an intelligent sensor with an integrated infrared temperature measurement module; the above-mentioned air humidity indicates the water vapor content in the air in the target environment, which can be obtained through a humidity sensor.

[0036] The above-mentioned reference light intensity represents the reference value of light intensity; the above-mentioned reference fruit surface temperature represents the reference value of fruit surface temperature; the above-mentioned reference air humidity represents the reference value of air humidity.

[0037] The influence coefficient corresponding to the above-mentioned light intensity factor indicates the degree of influence of the unit value of the light intensity factor on the meteorological risk coefficient of yellow dragon fruit; the influence coefficient corresponding to the above-mentioned fruit surface temperature factor indicates the degree of influence of the unit value of the fruit surface temperature factor on the meteorological risk coefficient of yellow dragon fruit; the influence coefficient corresponding to the above-mentioned air humidity factor indicates the degree of influence of the unit value of the air humidity factor on the meteorological risk coefficient of yellow dragon fruit; the monitoring database stores the mapping relationship between the light intensity factor and its corresponding influence coefficient, the mapping relationship between the fruit surface temperature factor and its corresponding influence coefficient, and the mapping relationship between the air humidity factor and its corresponding influence coefficient; for example, the light intensity factor, the fruit surface temperature factor and the air humidity factor are input into the monitoring database, and the monitoring database can match the influence coefficient corresponding to the light intensity factor, the influence coefficient corresponding to the fruit surface temperature factor and the influence coefficient corresponding to the air humidity factor; the influence coefficient corresponding to the light intensity factor, the influence coefficient corresponding to the fruit surface temperature factor and the influence coefficient corresponding to the air humidity factor all have a value range between 0 and 1.

[0038] The stronger the light, the more heat the fruit absorbs, and the higher the temperature of the fruit surface. At the same time, strong light will accelerate the evaporation of water, making the air dry and reducing the humidity; when the temperature of the fruit surface rises, the fruit will accelerate transpiration, release water vapor, and make the surrounding air humid; conversely, if the air humidity is too high, the water on the surface of the fruit cannot evaporate, and the temperature of the fruit surface will also rise because it cannot effectively dissipate heat.

[0039] If the light intensity is significantly greater than the corresponding reference value, the fruit is easily sunburned, and the risk is high; if the light intensity is significantly lower than the corresponding reference value, the photosynthesis of the yellow dragon fruit is insufficient, and the disease resistance becomes worse, which also increases the risk. Therefore, the larger the light intensity factor, the higher the meteorological risk coefficient of the yellow dragon fruit; if the fruit surface temperature is significantly greater than the corresponding reference value, the fruit is easily "burned" by high temperature, and the risk rises sharply; if the fruit surface temperature is significantly lower than the corresponding reference value, the fruit grows slower, and it may be frostbitten due to continued low temperature, and the risk also increases. Therefore, the larger the fruit surface temperature factor, the higher the meteorological risk coefficient of the yellow dragon fruit; if the air humidity is significantly greater than the corresponding reference value, the surface of the fruit is moist, and it is easy to mold and get sick, and the risk increases greatly; if the air humidity is significantly lower than the corresponding reference value, the fruit loses water quickly, the skin becomes dry and cracked, and pathogens can easily take advantage of the opportunity to enter, and the risk also increases. Therefore, the larger the air humidity factor, the higher the meteorological risk coefficient of the yellow dragon fruit.

[0040] Furthermore, the meteorological risk level of the target environment is analyzed. The specific analysis process is: compare the Huanglong fruit meteorological risk coefficient with the Huanglong fruit meteorological risk threshold; if the Huanglong fruit meteorological risk coefficient is greater than or equal to the Huanglong fruit meteorological risk threshold, the meteorological risk level of the target environment is marked as high meteorological risk; if the Huanglong fruit meteorological risk coefficient is less than the Huanglong fruit meteorological risk threshold, the meteorological risk level of the target environment is marked as low meteorological risk.

[0041] The above-mentioned Huanglong Fruit meteorological risk threshold refers to the minimum value of the Huanglong Fruit meteorological risk coefficient allowed in the monitoring database.

[0042] In a specific embodiment, meteorological risk parameters are obtained and analyzed, and meteorological risk levels are determined, laying a data foundation for subsequent management. This step can predict the probability of disasters and the extent of their impact in advance through real-time monitoring of key meteorological elements, transforming passive disaster relief into active defense. Farmers can prepare protective materials and adjust farming arrangements in advance based on risk levels to avoid major losses caused by sudden meteorological disasters and ensure the stability and controllability of the dragon fruit growth environment.

[0043] Step 2: Monitor the yellow dragon fruit in each area, collect and analyze the image attribute parameters of the yellow dragon fruit in each area, obtain the analysis results, and classify each area according to the analysis results to obtain the regional classification results. Based on the meteorological risk level of the target environment and the regional classification results, each area is graded and adjusted.

[0044] Specifically, the image attribute parameters of the yellow dragon fruit in each area are collected and analyzed. The specific analysis process is: the image attribute parameters of the yellow dragon fruit in each area include the surface curvature factor of the yellow dragon fruit image in each area, the hue value factor of the yellow dragon fruit image in each area, and the fruit diameter volume factor of the yellow dragon fruit image in each area.

[0045] The above-mentioned surface curvature factor indicates the proportional relationship between the average surface curvature of a certain area and the defining surface curvature; the above-mentioned hue value factor indicates the degree of deviation between the average hue value of a certain area and the reference hue value; the above-mentioned fruit diameter volume factor indicates the proportional relationship between the average fruit diameter volume of a certain area and the defining fruit diameter volume.

[0046] By introducing influence coefficients, we can quantify the influence of the surface curvature factor, the hue value factor, the fruit diameter volume factor, and the meteorological risk factor on the abnormal coefficient of the yellow dragon fruit fruit. By coupling various degrees, we can obtain the abnormal coefficient of the yellow dragon fruit fruit. The abnormal coefficient of the yellow dragon fruit fruit indicates that the growth state of the yellow dragon fruit fruit deviates from the normal level. The specific evaluation method is as follows:

[0047]

[0048] Where USLF is the meteorological risk factor of Huanglongguo, GFFB q is the abnormal coefficient of the dragon fruit in the qth area, LFD q is the surface curvature factor of the qth region, KVX q is the hue value factor of the qth region, PSN q Fruit diameter volume factor of the qth region, FDS q is the average surface curvature of the qth region, FDK is the defined surface curvature preset in the monitoring database, and SDC q is the average hue value of the qth area, SDK is the reference hue value preset in the monitoring database, JYH q The average fruit diameter volume of the qth area, JYK is the defined fruit diameter volume preset in the monitoring database, To monitor the influence coefficient corresponding to the surface curvature factor preset in the database, It is the influence coefficient corresponding to the hue value factor preset in the monitoring database. It is the influence coefficient corresponding to the fruit diameter volume factor preset in the monitoring database. The first influence coefficient corresponding to the Huanglong fruit meteorological risk coefficient preset in the monitoring database, q is the number of each Huanglong fruit area, q=1, 2, 3, ..., s, s is the total number of Huanglong fruit areas.

[0049] It should be explained that the above-mentioned average surface curvature represents the average degree of curvature of the yellow dragon fruit in a certain area. The object can be photographed from different angles with a camera, and a three-dimensional model can be reconstructed through image processing algorithms (such as multi-view stereo vision) to calculate the curvature; the above-mentioned average hue value represents the average hue value of the yellow dragon fruit in a certain area. The color can be absorbed by the "eyedropper tool", and the hue value can be directly read by switching to the hue-saturation-lightness mode in the "color panel"; the above-mentioned average fruit diameter volume represents the average volume of the yellow dragon fruit in a certain area. The volume can be estimated by taking multi-angle images of the fruit and analyzing the pixels with professional software (such as ImageJ) (the scale needs to be calibrated).

[0050] The above-defined surface curvature indicates the maximum allowable value of the surface curvature; the above-defined reference hue value indicates the reference value of the hue value; the above-defined fruit diameter volume indicates the minimum allowable value of the fruit diameter volume; it should be explained that the above-defined surface curvature, reference hue value and defined fruit diameter volume need to be updated in real time by technical personnel according to the growth trend of the yellow dragon fruit.

[0051] The influence coefficient corresponding to the above-mentioned surface curvature factor indicates the degree of influence of the unit value of the surface curvature on the abnormal coefficient of the yellow dragon fruit fruit; the influence coefficient corresponding to the above-mentioned hue value factor indicates the degree of influence of the unit value of the hue value on the abnormal coefficient of the yellow dragon fruit fruit; the influence coefficient corresponding to the above-mentioned fruit diameter volume factor indicates the degree of influence of the unit value of the fruit diameter volume on the abnormal coefficient of the yellow dragon fruit fruit; the first influence coefficient corresponding to the above-mentioned yellow dragon fruit meteorological risk coefficient indicates the degree of influence of the unit value of the yellow dragon fruit meteorological risk coefficient on the abnormal coefficient of the yellow dragon fruit fruit; the monitoring database stores the mapping relationship between the surface curvature factor and its corresponding influence coefficient, the mapping relationship between the hue value factor and its corresponding influence coefficient, and the mapping relationship between the fruit diameter volume factor and The mapping relationship between its corresponding influence coefficient and the mapping relationship between the yellow dragon fruit meteorological risk coefficient and its corresponding first influence coefficient; for example, the surface curvature factor, hue value factor, fruit diameter volume factor and yellow dragon fruit meteorological risk coefficient are input into the monitoring database, and the monitoring database can match the influence coefficient corresponding to the surface curvature factor, the influence coefficient corresponding to the hue value factor, the influence coefficient corresponding to the fruit diameter volume factor and the first influence coefficient corresponding to the yellow dragon fruit meteorological risk coefficient; the influence coefficient corresponding to the surface curvature factor, the influence coefficient corresponding to the hue value factor, the influence coefficient corresponding to the fruit diameter volume factor and the first influence coefficient corresponding to the yellow dragon fruit meteorological risk coefficient all have value ranges between 0 and 1.

[0052] Under high temperature exposure, the greater the surface curvature, the more likely the raised part will be burned due to concentrated light, increasing the meteorological risk factor. The hue value reflects the maturity and health of the fruit. The greater the deviation from the reference hue value, the poor growth of the fruit. In bad weather, the fruit is more likely to be damaged, and the meteorological risk factor of the yellow dragon fruit is higher. Fruits with small diameter and small volume may be a sign of poor growth. They have weak resistance and are more likely to have problems in extreme weather. Therefore, the meteorological risk factor of the yellow dragon fruit will indirectly affect the diameter and volume of the fruit.

[0053] As the surface curvature factor increases, water and dust accumulate easily on the surface of the fruit, pathogens breed easily, and the probability of abnormalities such as rot and mold in the fruit increases, which leads to an increase in the abnormality coefficient of the yellow dragon fruit; the larger the hue value factor, the abnormal growth of the fruit, which leads to an increase in the abnormality coefficient of the yellow dragon fruit; the smaller the fruit diameter volume factor, the poor growth and underdevelopment of the fruit, which leads to an increase in the abnormality coefficient of the yellow dragon fruit; a high meteorological risk coefficient of the yellow dragon fruit means that the worse the weather the fruit faces, the more likely the fruit will be burned, which leads to an increase in the abnormality coefficient of the yellow dragon fruit.

[0054] Specifically, each area is classified according to the analysis results. The specific classification process is: the yellow dragon fruit fruit abnormality coefficient of each area is compared with the first abnormality coefficient and the second abnormality coefficient; if the yellow dragon fruit fruit abnormality coefficient of a certain area is less than the first abnormality coefficient, the area is marked as a qualified area; if the yellow dragon fruit fruit abnormality coefficient of a certain area is greater than or equal to the first abnormality coefficient and less than or equal to the second abnormality coefficient, the area is marked as a critical qualified area; if the yellow dragon fruit fruit abnormality coefficient of a certain area is greater than the second abnormality index, the area is marked as an unqualified area, and an early warning is issued for the area.

[0055] It should be explained that the above-mentioned first abnormality coefficient refers to the value in the monitoring database used to classify qualified areas and critical qualified areas; the above-mentioned second abnormality coefficient refers to the value in the monitoring database used to classify critical qualified areas and unqualified areas. It should be noted that the first abnormality coefficient is smaller than the second abnormality coefficient.

[0056] Furthermore, each area is adjusted in a graded manner, and the specific adjustment process is as follows: if an area is a qualified area and the meteorological risk level of the target environment is low meteorological risk, there is no need to adjust the area; if an area is a qualified area and the meteorological risk level of the target environment is high meteorological risk, the first-level adjustment measures are matched to the area, thereby realizing graded adjustment of the area; if an area is a critical qualified area and the meteorological risk level of the target environment is low meteorological risk, the second-level adjustment measures are matched to the area, thereby realizing graded adjustment of the area; if an area is a critical qualified area and the meteorological risk level of the target environment is high meteorological risk, the third-level adjustment measures are matched to the area, thereby realizing graded adjustment of the area.

[0057] The first-level adjustment measures refer to obtaining the Huanglong Fruit meteorological risk deviation value based on the Huanglong Fruit meteorological risk coefficient and the Huanglong Fruit meteorological risk threshold, and matching the shading rate improvement coefficient and the fogging frequency improvement coefficient based on the Huanglong Fruit meteorological risk deviation value, thereby increasing the shading rate of the lower shade net and the fogging frequency of the fogging equipment.

[0058] The above-mentioned acquisition of the Huanglong Fruit meteorological risk deviation value refers to performing difference processing on the Huanglong Fruit meteorological risk coefficient and the Huanglong Fruit meteorological risk threshold, and then performing ratio processing on the processing result and the Huanglong Fruit meteorological risk threshold, and finally obtaining the Huanglong Fruit meteorological risk deviation value; the above-mentioned matching of the shading rate improvement coefficient and the fog frequency improvement coefficient based on the Huanglong Fruit meteorological risk deviation value, the specific matching process is: the shading rate improvement coefficient (γ1) corresponding to each Huanglong Fruit meteorological risk deviation value interval is stored in the monitoring database, and the obtained Huanglong Fruit meteorological risk deviation value is input into the monitoring database. The monitoring database can match the corresponding Huanglong Fruit meteorological risk deviation value interval, and the shading rate improvement coefficient (γ1) corresponding to the interval is the required improvement coefficient. The obtained shading rate improvement coefficient (γ1) is multiplied by the original The shading rate, the result obtained is the shading rate that needs to be adjusted; the above-mentioned shading rate improvement coefficient (γ1) is greater than 1, which means that the shading rate of the lower shade net needs to be increased by a multiple; the monitoring database stores the fog frequency improvement coefficient (ρ1) corresponding to each Huanglong fruit meteorological risk deviation value interval, and the obtained Huanglong fruit meteorological risk deviation value is input into the monitoring database. The monitoring database can match the corresponding Huanglong fruit meteorological risk deviation value interval, and the fog frequency improvement coefficient (ρ1) corresponding to the interval is the required improvement coefficient. The obtained fog frequency improvement coefficient (ρ1) is multiplied by the original fog frequency, and the result obtained is the fog frequency that needs to be adjusted; the above-mentioned fog frequency improvement coefficient (ρ1) is greater than 1, which means that the fog frequency of the fogging equipment needs to be increased by a multiple.

[0059] The secondary adjustment measure refers to obtaining a first abnormal deviation value based on the abnormal coefficient of the yellow dragon fruit and the first abnormal coefficient, and matching the fan speed increase coefficient based on the first abnormal deviation value, thereby increasing the fan speed and accelerating air circulation.

[0060] The above-mentioned acquisition of the first abnormal deviation value refers to performing difference processing on the abnormal coefficient of the yellow dragon fruit fruit and the first abnormal coefficient, and then performing ratio processing on the processing result with the first abnormal coefficient, and the final result is the first abnormal deviation value; the above-mentioned matching of the fan speed increase coefficient based on the first abnormal deviation value, the specific matching process is: the fan speed increase coefficient (ω1) corresponding to each first abnormal deviation value interval is stored in the monitoring database, and the obtained first abnormal deviation value is input into the monitoring database. The monitoring database can match the corresponding first abnormal deviation value interval, and the fan speed increase coefficient (ω1) corresponding to the interval is the required increase coefficient. The obtained increase coefficient is multiplied by the original fan speed, and the result is the fan speed that needs to be adjusted, wherein the fan speed increase coefficient (ω1) is greater than 1, indicating that the fan speed needs to be increased by a multiple.

[0061] The third-level adjustment measures refer to matching the secondary increase coefficient of the shading rate and the secondary increase coefficient of the fogging frequency based on the meteorological risk deviation value of Huanglongguo, thereby further increasing the shading rate of the lower shade net and the fogging frequency of the fogging equipment, and at the same time matching the secondary increase coefficient of the fan speed based on the first abnormal deviation value, thereby further increasing the fan speed, which not only reduces the input of light energy, but also cools down through fogging evaporation.

[0062] It should be explained that the above-mentioned matching of the shading rate secondary improvement coefficient and the fog-making frequency secondary improvement coefficient based on the yellow dragon fruit meteorological risk deviation value is carried out in the following specific matching process: the shading rate secondary improvement coefficient (γ2) corresponding to each yellow dragon fruit meteorological risk deviation value interval is stored in the monitoring database, and the obtained yellow dragon fruit meteorological risk deviation value is input into the monitoring database. The monitoring database can match the corresponding yellow dragon fruit meteorological risk deviation value interval, and the shading rate secondary improvement coefficient (γ2) corresponding to the interval is the required improvement coefficient. The obtained shading rate secondary improvement coefficient (γ2) is multiplied by the original shading rate, and the result is the shading rate that needs to be adjusted; the above-mentioned shading rate secondary improvement coefficient (γ2) is greater than 1, indicating that the shading of the lower shading net is The rate needs to be increased by a multiple of the value; it should be noted that γ2 is greater than γ1; the monitoring database stores the secondary increase coefficient (ρ2) of the fogging frequency corresponding to each yellow dragon fruit meteorological risk deviation value interval, and the obtained yellow dragon fruit meteorological risk deviation value is input into the monitoring database. The monitoring database can match the corresponding yellow dragon fruit meteorological risk deviation value interval, and the secondary increase coefficient (ρ2) of the fogging frequency corresponding to the interval is the required increase coefficient. The obtained secondary increase coefficient (ρ2) of the fogging frequency is multiplied by the original fogging frequency, and the result is the fogging frequency that needs to be adjusted; the above-mentioned secondary increase coefficient (ρ2) of the fogging frequency is greater than 1, which means that the fogging frequency of the fogging equipment needs to be increased by a multiple of the value, and it should be noted that ρ2 is greater than ρ1.

[0063] It should be explained that the above-mentioned quadratic increase coefficient of the fan speed is matched based on the first abnormal deviation value. The specific matching process is: the quadratic increase coefficient of the fan speed (ω2) corresponding to each first abnormal deviation value interval is stored in the measurement database, and the obtained first abnormal deviation value is input into the monitoring database. The monitoring database can match the corresponding first abnormal deviation value interval, and the quadratic increase coefficient of the fan speed (ω2) corresponding to the interval is the required increase coefficient. The obtained increase coefficient is multiplied by the original fan speed, and the result is the fan speed that needs to be adjusted. The quadratic increase coefficient of the fan speed (ω2) is greater than 1, indicating that the fan speed needs to be increased by a multiple. It should be noted that ω1 is less than ω2.

[0064] In a specific embodiment, the image attribute parameters of the fruit are monitored and regional classification is performed, and graded adjustment is implemented in combination with the meteorological risk level to achieve precise management. This step uses image recognition technology to quantitatively evaluate the fruit status and accurately locate the abnormal planting areas to avoid the waste of resources caused by "one-size-fits-all" management. Differentiated control strategies are formulated for different risk levels and regional categories, which can not only effectively improve the fruit growth conditions, but also enhance resource utilization efficiency and improve the overall quality of Huanglong Fruit.

[0065] Step 3: Monitor and analyze the characteristic parameters of dragon fruit burns in each area, and determine whether to perform secondary adjustments in each area based on the Internet of Things. At the same time, obtain the image attribute parameters of the dragon fruit in each area after the secondary adjustment is completed, and determine whether to issue disaster warnings for each area.

[0066] The above-mentioned judgment on whether to make secondary adjustments to each area based on the Internet of Things refers to the wireless transmission of various data collected by sensors in real time to the cloud platform, and the Internet of Things automatically triggers the execution equipment based on the analysis results.

[0067] Specifically, the burn characteristic parameters of the yellow dragon fruit in each area are monitored and analyzed. The specific analysis process is: the burn characteristic parameters of the yellow dragon fruit in each area include the thermal boundary layer temperature gradient factor of each area and the near-infrared light reflectivity factor of the fruit surface in each area.

[0068] The above-mentioned thermal boundary layer temperature gradient factor represents the proportional relationship between the thermal boundary layer temperature gradient of a certain area and the defining thermal boundary layer temperature gradient; the above-mentioned fruit surface near-infrared light reflectance factor represents the proportional relationship between the near-infrared light reflectance of the fruit surface of a certain area and the defining fruit surface near-infrared light reflectance.

[0069] By introducing influence coefficients, we quantify the influence of the thermal boundary layer temperature gradient factor on the burn disaster warning index, the influence of the fruit surface near-infrared light reflectivity factor on the burn disaster warning index, the influence of the yellow dragon fruit fruit abnormality coefficient on the burn disaster warning index, and the influence of the yellow dragon fruit meteorological risk factor on the burn disaster warning index. By coupling various degrees, we can obtain the burn disaster warning index, among which the burn disaster warning index represents the risk level of yellow dragon fruit being burned. The specific evaluation method is as follows:

[0070]

[0071] Where, VBFN q is the burn disaster warning index of the qth region, USLF is the meteorological risk factor of Huanglong fruit, GFFB q is the abnormal coefficient of the dragon fruit in the qth region, RHP q is the thermal boundary layer temperature gradient factor of the qth region, BGH q is the thermal boundary layer temperature gradient of the qth region, NHG is the defined thermal boundary layer temperature gradient preset in the monitoring database, GFD q The near-infrared reflectance factor of the fruit surface in the qth region, FJU q is the near-infrared light reflectance of the fruit surface in the qth area, BPI is the near-infrared light reflectance of the defined fruit surface preset in the monitoring database, θ1 is the influence coefficient corresponding to the thermal boundary layer temperature gradient factor preset in the monitoring database, θ2 is the influence coefficient corresponding to the fruit surface near-infrared light reflectance factor preset in the monitoring database, θ3 is the second influence coefficient corresponding to the yellow dragon fruit meteorological risk factor preset in the monitoring database, and θ4 is the influence coefficient corresponding to the yellow dragon fruit fruit abnormality coefficient preset in the monitoring database.

[0072] The above-mentioned thermal boundary layer temperature gradient indicates the difference between the surface temperature of the fruit and the surrounding air temperature, which can be obtained by networking sensors. The above-mentioned near-infrared light reflectance of the fruit surface indicates the ability of the fruit surface to reflect near-infrared light. A multispectral camera can be used to capture light of different wavelengths (including near-infrared light), and the regional average reflectance can be calculated using image processing software (such as ImageJ).

[0073] The above definition of thermal boundary layer temperature gradient indicates the maximum value allowed by the thermal boundary layer temperature gradient; the above definition of fruit surface near-infrared light reflectance indicates the maximum value allowed by the fruit surface near-infrared light reflectance.

[0074] The influence coefficient corresponding to the above-mentioned thermal boundary layer temperature gradient factor indicates the degree of influence of the unit value of the thermal boundary layer temperature gradient on the burn disaster warning index; the influence coefficient corresponding to the above-mentioned fruit surface near-infrared light reflectance factor indicates the degree of influence of the unit value of the fruit surface near-infrared light reflectance on the burn disaster warning index; the second influence coefficient corresponding to the above-mentioned yellow dragon fruit meteorological risk coefficient indicates the degree of influence of the unit value of the yellow dragon fruit meteorological risk coefficient on the burn disaster warning index; the influence coefficient corresponding to the above-mentioned yellow dragon fruit fruit anomaly coefficient indicates the degree of influence of the unit value of the yellow dragon fruit fruit anomaly coefficient on the burn disaster warning index; the monitoring database stores the mapping relationship between the thermal boundary layer temperature gradient factor and its corresponding influence coefficient, the mapping relationship between the fruit surface near-infrared light reflectance factor and its corresponding influence coefficient, and the mapping relationship between the yellow dragon fruit meteorological risk coefficient and its The mapping relationship between the corresponding second influence coefficient and the mapping relationship between the yellow dragon fruit fruit anomaly coefficient and its corresponding influence coefficient; for example, the thermal boundary layer temperature gradient factor, the fruit surface near-infrared light reflectance factor, the yellow dragon fruit meteorological risk coefficient and the yellow dragon fruit fruit anomaly coefficient are input into the monitoring database, and the monitoring database can match the influence coefficient corresponding to the thermal boundary layer temperature gradient factor, the influence coefficient corresponding to the fruit surface near-infrared light reflectance factor, the second influence coefficient corresponding to the yellow dragon fruit meteorological risk coefficient and the influence coefficient corresponding to the yellow dragon fruit fruit anomaly coefficient; the influence coefficient corresponding to the thermal boundary layer temperature gradient factor, the influence coefficient corresponding to the fruit surface near-infrared light reflectance factor, the second influence coefficient corresponding to the yellow dragon fruit meteorological risk coefficient and the influence coefficient corresponding to the yellow dragon fruit fruit anomaly coefficient all have value ranges between 0 and 1.

[0075] The greater the meteorological risk coefficient of yellow dragon fruit, the worse the weather, the greater the temperature difference between the surface of the yellow dragon fruit and the surrounding air, and the larger the thermal boundary layer temperature gradient factor; it also means that the fruit is easily damaged and rotten by exposure to the sun, and the near-infrared light reflectivity of the fruit surface will decrease; a large thermal boundary layer temperature gradient factor means that the heat on the fruit surface cannot be dissipated, and the fruit is prone to sunburn and water loss, which will lead to a decrease in near-infrared light reflectivity; the larger the thermal boundary layer temperature gradient factor, the more difficult it is for the fruit to dissipate heat, the more likely it is to be burned by high temperature, and the higher the abnormality coefficient of the yellow dragon fruit.

[0076] The larger the thermal boundary layer temperature gradient factor, the greater the temperature difference between the fruit surface and the surrounding air, the more difficult it is for the fruit to dissipate heat, the more likely it is to be burned, and the higher the burn disaster warning index; a low near-infrared light reflectivity factor on the fruit surface means that the fruit is highly mature, has decreased water content, or has internal lesions. Such fruits are more likely to be burned, and the burn disaster warning index is also higher; the higher the abnormality coefficient of the yellow dragon fruit, the more abnormalities have occurred in the fruit, and the possibility of being burned is greater, which will lead to an increase in the burn disaster warning index; the higher the meteorological risk coefficient of the yellow dragon fruit, the greater the risk of the fruit being burned, and the higher the burn disaster warning index.

[0077] Specifically, it is determined whether to make a secondary adjustment to each area. The specific analysis process is: compare the burn disaster warning index of each area with the burn disaster warning threshold; if the burn disaster warning index of a certain area is less than the burn disaster warning threshold, it is determined that no secondary adjustment is required for the area; if the burn disaster warning index of a certain area is greater than or equal to the burn disaster warning threshold, it is determined that a secondary adjustment is required for the area. The specific adjustment content is: based on the burn disaster warning index and the burn disaster warning threshold of the area, obtain the burn disaster warning deviation value of the area, and compare the burn disaster warning deviation value with the burn disaster warning deviation threshold.

[0078] The above-mentioned burn disaster warning threshold value represents the maximum value of the burn disaster warning index allowed in the monitoring database; the above-mentioned acquisition of the burn disaster warning deviation value of the area refers to performing difference processing on the burn disaster warning index of the area and the burn disaster warning threshold value, and then performing ratio processing on the processing result with the burn disaster warning threshold value. The final result is the burn disaster warning deviation value of the area; the above-mentioned burn disaster warning deviation threshold value represents the maximum value of the burn disaster warning deviation allowed in the monitoring database.

[0079] If the burn disaster warning deviation value of the area is less than the burn disaster warning deviation threshold, the fogging time extension coefficient is matched based on the burn disaster warning deviation value of the area, thereby extending the fogging time.

[0080] The above-mentioned burn disaster warning deviation value based on the area matches the fog-making duration extension coefficient. The specific matching process is: the monitoring database stores the fog-making duration extension coefficient corresponding to each burn disaster warning deviation value interval, and the burn disaster warning deviation value of the area is input into the monitoring database. The monitoring database can match the corresponding burn disaster warning deviation value interval, and the fog-making duration extension coefficient corresponding to the interval is the required extension coefficient. The obtained fog-making duration extension coefficient is multiplied by the original fog-making duration, and the result is the fog-making duration that needs to be adjusted; the above-mentioned fog-making duration extension coefficient is greater than 1, indicating that the fog-making duration needs to be extended by a multiple.

[0081] If the burn disaster warning deviation value of the area is greater than or equal to the burn disaster warning deviation threshold, the upper sunshade net is activated, and the shading rate of the upper sunshade net is matched based on the burn disaster warning deviation value of the area.

[0082] The above-mentioned burn disaster warning deviation value based on the area is used to match the shading rate of the upper sunshade net. The specific matching process is: the shading rate of the upper sunshade net corresponding to each burn disaster warning deviation value is stored in the monitoring database, and the burn disaster warning deviation value of the area is input into the monitoring database. The monitoring database can match the corresponding shading rate of the upper sunshade net.

[0083] In a specific embodiment, the burn characteristic parameters are continuously monitored and secondary adjustments and disaster warnings are carried out to build a refined prevention and control closed loop; the subtle changes in the risk of fruit burns can be keenly captured, and the control measures can be adjusted in time to prevent the risk from expanding. After the secondary adjustment, the fruit image attribute parameters are collected again for comparative analysis to ensure that the control effect meets the standards. If an abnormality is found, a disaster warning of the corresponding level is immediately triggered to guide farmers to take remedial measures to minimize disaster losses.

[0084] Furthermore, it is determined whether to issue a disaster warning for each region. The specific analysis process is: the yellow dragon fruit fruit abnormality coefficient of each region after the secondary adjustment is marked as the secondary yellow dragon fruit fruit abnormality coefficient, the secondary yellow dragon fruit fruit abnormality coefficient is compared with the first abnormality coefficient and the second abnormality coefficient, and each region is reclassified; if a region is changed from a qualified region to a critical qualified region, it is determined to issue a monitoring and early warning for the region; if a region is changed from a qualified region to an unqualified region, it is determined to issue an emergency warning for the region; if a region is changed from a critical region to an unqualified region, it is determined to issue an abnormal warning for the region; if a region is changed from an unqualified region to a critical qualified region, it is determined not to issue an early warning for the region; if a region is changed from an unqualified region to a qualified region, it is determined not to issue an early warning for the region; if a region is changed from a critical region to a qualified region, it is determined not to issue an early warning for the region. It should be noted that the emergency warning level is greater than the abnormal warning level, and the abnormal warning level is greater than the monitoring warning level.

[0085] In a specific embodiment, the present invention provides a Huanglong fruit meteorological disaster monitoring method based on the Internet of Things, and constructs a full-chain management system from environmental risk identification, fruit status assessment to precise regulation and early warning; through multi-source data fusion analysis and intelligent decision-making, it can significantly reduce the impact of meteorological disasters on Huanglong fruit, and reduce the decline in fruit quality and yield losses caused by strong light burns, high temperature, etc.; at the same time, the hierarchical adjustment and dynamic early warning mechanism realizes the precise allocation of resources, reduces manpower and material costs, and improves planting management efficiency; the solution is both scientific and practical, and provides strong technical support for the stable production and income increase of Huanglong fruit and the sustainable development of the industry.

[0086] Reference Figure 2 As shown, the second aspect of the present invention provides a Huanglong fruit meteorological disaster monitoring system based on the Internet of Things, including: a target environment meteorological monitoring module, a Huanglong fruit fruit status monitoring module, a Huanglong fruit burn monitoring and adjustment module, and a monitoring database.

[0087] The target environment meteorological monitoring module is connected to the yellow dragon fruit fruit status monitoring module, and the yellow dragon fruit fruit status monitoring module is connected to the yellow dragon fruit burn monitoring and adjustment module. The three are connected to the monitoring database; the monitoring database is used to store various parameters involved in the yellow dragon fruit meteorological disaster monitoring system based on the Internet of Things.

[0088] The target environment meteorological monitoring module is used to obtain and analyze the meteorological risk parameters of the target environment, so as to analyze the meteorological risk level of the target environment; the yellow dragon fruit fruit status monitoring module is used to monitor the yellow dragon fruit in each area, collect and analyze the image attribute parameters of the yellow dragon fruit in each area, obtain the analysis results, and classify each area according to the analysis results, so as to obtain the regional classification results, and perform graded adjustments on each area based on the meteorological risk level of the target environment and the regional classification results; the yellow dragon fruit burn monitoring and adjustment module is used to monitor and analyze the characteristic parameters of the yellow dragon fruit burn in each area, and determine whether to perform secondary adjustments on each area based on the Internet of Things, and at the same time obtain the image attribute parameters of the yellow dragon fruit in each area after the secondary adjustment is completed, and determine whether to issue disaster warnings for each area.

[0089] Figure 3 As shown in the flowchart of the steps of the Huanglong Fruit Meteorological Risk Coefficient Assessment Method of the present invention, the process begins with obtaining the Huanglong Fruit Meteorological Risk Coefficient, comparing the Huanglong Fruit Meteorological Risk Coefficient with the Huanglong Fruit Meteorological Risk Threshold. If the Huanglong Fruit Meteorological Risk is greater than or equal to the Huanglong Fruit Meteorological Risk Threshold, it is determined to be a high meteorological risk; if the Huanglong Fruit Meteorological Risk is less than the Huanglong Fruit Meteorological Risk Threshold, it is a low meteorological risk. This step prioritizes the assessment of external environmental risks to provide a basic basis for subsequent decision-making.

[0090] Figure 4 As shown in the flowchart of the step of the method for judging the abnormality coefficient of yellow dragon fruit fruit of the present invention, the system obtains the abnormality coefficient of yellow dragon fruit fruit in each area and compares it with the first abnormality coefficient and the second abnormality coefficient; if the abnormality coefficient of yellow dragon fruit fruit is less than the first abnormality coefficient, the area is a qualified area and no warning is required; if the abnormality coefficient of yellow dragon fruit fruit is between the first abnormality coefficient and the second abnormality coefficient, it is a critical qualified area; if the abnormality coefficient of yellow dragon fruit fruit is greater than the second abnormality coefficient, it is an unqualified area and a direct warning is issued.

[0091] Figure 5As shown in the flowchart of the steps of the method for graded adjustment of each area of ​​the present invention, if an area is a qualified area and the meteorological risk level of the target environment is low meteorological risk, there is no need to adjust the area; if an area is a qualified area and the meteorological risk level of the target environment is high meteorological risk, the first-level adjustment measures are matched to the area; if an area is a critical qualified area and the meteorological risk level of the target environment is low meteorological risk, the second-level adjustment measures are matched to the area; if an area is a critical qualified area and the meteorological risk level of the target environment is high meteorological risk, the third-level adjustment measures are matched to the area, thereby realizing graded adjustment of the area.

[0092] Figure 6 As shown in the flowchart of the burn warning index method steps of the present invention, the system obtains the burn disaster warning index of each area and compares it with the burn disaster warning threshold. If the burn disaster warning index is greater than or equal to the burn disaster warning threshold, the burn disaster warning deviation value is further calculated: when the burn disaster warning deviation value is less than the burn disaster warning deviation threshold, the fogging time is increased; when the burn disaster warning deviation value is greater than or equal to the burn disaster warning deviation threshold, the upper sunshade net is started and the corresponding shading rate is matched.

[0093] Figure 7 As shown in the flowchart of the secondary fruit abnormality coefficient method of the present invention, the system finally re-acquires the abnormality coefficient of the yellow dragon fruit fruit and compares it with the initial classification; if the regional status deteriorates (such as qualified → critical / unqualified), the corresponding warning is triggered; if the status improves (such as unqualified → critical / qualified), the warning is canceled; through dynamic monitoring and feedback adjustment, a complete prevention and control closed loop is formed to ensure the continuous optimization of the yellow dragon fruit growth environment.

[0094] The above content is merely an example and explanation of the structure of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the scope of protection of the present invention.

Claims

1. A method for monitoring meteorological disasters of Huanglong fruit based on the Internet of Things, characterized in that: include: Step 1: Obtain and analyze the meteorological risk parameters of the target environment to analyze the meteorological risk level of the target environment; Step 2: Monitor the yellow dragon fruit in each area, collect and analyze the image attribute parameters of the yellow dragon fruit in each area, obtain analysis results, and classify each area according to the analysis results to obtain regional classification results. Based on the meteorological risk level of the target environment and the regional classification results, each area is graded and adjusted; Step 3: Monitor and analyze the characteristic parameters of dragon fruit burns in each area, and determine whether to perform secondary adjustments in each area based on the Internet of Things. At the same time, obtain the image attribute parameters of the dragon fruit in each area after the secondary adjustment is completed, and determine whether to issue disaster warnings for each area.

2. The method for monitoring meteorological disasters of Huanglong Fruit based on Internet of Things according to claim 1, wherein: The specific analysis process of obtaining and analyzing the meteorological risk parameters of the target environment is as follows: The meteorological risk parameters include the light intensity factor of the target environment, the fruit surface temperature factor of the target environment, and the air humidity factor of the target environment; By introducing influence coefficients, we can quantify the degree of influence of light intensity factor, fruit surface temperature factor and air humidity factor on the meteorological risk coefficient of yellow dragon fruit, and couple various degrees to obtain the meteorological risk coefficient of yellow dragon fruit. The meteorological risk coefficient of yellow dragon fruit represents the degree of abnormal influence of the target environment's meteorology on yellow dragon fruit.

3. The method for monitoring meteorological disasters of Huanglong Fruit based on Internet of Things according to claim 2, wherein: The meteorological risk level of the target environment is analyzed, and the specific analysis process is as follows: Compare the meteorological risk coefficient of Huanglongguo with the meteorological risk threshold of Huanglongguo; If the Huanglongguo meteorological risk coefficient is greater than or equal to the Huanglongguo meteorological risk threshold, the meteorological risk level of the target environment is marked as high meteorological risk; If the Huanglongguo meteorological risk coefficient is less than the Huanglongguo meteorological risk threshold, the meteorological risk level of the target environment will be marked as low meteorological risk.

4. The method for monitoring meteorological disasters of Huanglong Fruit based on Internet of Things according to claim 1, wherein: The image attribute parameters of the yellow dragon fruit in each area are collected and analyzed, and the specific analysis process is as follows: The attribute parameters of the yellow dragon fruit image in each region include a surface curvature factor of the yellow dragon fruit image in each region, a hue value factor of the yellow dragon fruit image in each region, and a fruit diameter volume factor of the yellow dragon fruit image in each region; By introducing influence coefficients, the influence of surface curvature factor, hue value factor, fruit diameter volume factor and meteorological risk factor on the abnormal coefficient of yellow dragon fruit are quantified respectively. Then, various degrees are coupled to obtain the abnormal coefficient of yellow dragon fruit. The abnormal coefficient of yellow dragon fruit is an indicator that the growth status of yellow dragon fruit deviates from the normal level.

5. The method for monitoring meteorological disasters of Huanglong fruit based on the Internet of Things according to claim 1, wherein: The regions are classified according to the analysis results. The specific classification process is as follows: Compare the abnormal coefficient of the yellow dragon fruit in each region with the first abnormal coefficient and the second abnormal coefficient; If the abnormal coefficient of the dragon fruit in a certain area is less than the first abnormal coefficient, the area is marked as a qualified area; If the abnormal coefficient of the dragon fruit in a certain area is greater than or equal to the first abnormal coefficient and less than or equal to the second abnormal coefficient, the area is marked as a critical qualified area; If the abnormal coefficient of the dragon fruit in a certain area is greater than the second abnormal index, the area will be marked as an unqualified area and an early warning will be issued for the area.

6. The method for monitoring meteorological disasters of Huanglong fruit based on the Internet of Things according to claim 1, wherein: The specific adjustment process for each region is as follows: If an area is a qualified area and the meteorological risk level of the target environment is low meteorological risk, there is no need to adjust the area; If a region is a qualified region and the target environment's meteorological risk level is high, the region will be matched with the first-level regulation measures, thereby achieving hierarchical regulation of the region; If an area is a critical qualified area and the meteorological risk level of the target environment is low meteorological risk, the secondary adjustment measures will be matched to the area, thereby achieving hierarchical adjustment of the area; If an area is a critical qualified area and the meteorological risk level of the target environment is high meteorological risk, the area will be matched with three-level adjustment measures to achieve hierarchical adjustment of the area; The first-level adjustment measure refers to obtaining the Huanglong Fruit meteorological risk deviation value based on the Huanglong Fruit meteorological risk coefficient and the Huanglong Fruit meteorological risk threshold, and matching the shading rate improvement coefficient and the fogging frequency improvement coefficient based on the Huanglong Fruit meteorological risk deviation value, thereby increasing the shading rate of the lower shading net and the fogging frequency of the fogging equipment; The secondary adjustment measure refers to obtaining a first abnormal deviation value based on the abnormal coefficient of the yellow dragon fruit and the first abnormal coefficient, and matching the fan speed increase coefficient based on the first abnormal deviation value, thereby increasing the fan speed; The three-level adjustment measures refer to matching the secondary increase coefficient of the shading rate and the secondary increase coefficient of the fogging frequency based on the meteorological risk deviation value of the dragon fruit, thereby further improving the shading rate of the lower shade net and the fogging frequency of the fogging equipment, and at the same time matching the secondary increase coefficient of the fan speed based on the first abnormal deviation value, thereby further increasing the fan speed.

7. The method for monitoring meteorological disasters of Huanglong Fruit based on the Internet of Things according to claim 1, wherein: The monitoring and analysis of the characteristic parameters of the dragon fruit burns in each area are as follows: The burn characteristic parameters of the dragon fruit in each region include the thermal boundary layer temperature gradient factor of each region and the fruit surface near-infrared light reflectivity factor of each region; By introducing influence coefficients, we quantify the influence of the thermal boundary layer temperature gradient factor on the burn disaster warning index, the influence of the fruit surface near-infrared light reflectivity factor on the burn disaster warning index, the influence of the yellow dragon fruit fruit abnormality coefficient on the burn disaster warning index, and the influence of the yellow dragon fruit meteorological risk coefficient on the burn disaster warning index. By coupling various degrees, we can obtain the burn disaster warning index, among which the burn disaster warning index represents the risk degree of yellow dragon fruit being burned.

8. The method for monitoring meteorological disasters of Huanglong fruit based on the Internet of Things according to claim 1, wherein: The specific analysis process for determining whether to perform secondary adjustment on each region is as follows: Compare the burn disaster warning index of each region with the burn disaster warning threshold; If the burn disaster warning index of a certain area is less than the burn disaster warning threshold, it is determined that no secondary adjustment is required for the area; If the burn hazard warning index of a certain area is greater than or equal to the burn hazard warning threshold, it is determined that a secondary adjustment is required for the area. The specific adjustment content is: based on the burn hazard warning index and the burn hazard warning threshold of the area, the burn hazard warning deviation value of the area is obtained, and the burn hazard warning deviation value is compared with the burn hazard warning deviation threshold; If the burn disaster warning deviation value of the area is less than the burn disaster warning deviation threshold, the fogging duration extension coefficient is matched based on the burn disaster warning deviation value of the area, thereby extending the fogging duration; If the burn disaster warning deviation value of the area is greater than or equal to the burn disaster warning deviation threshold, the upper sunshade net is activated, and the shading rate of the upper sunshade net is matched based on the burn disaster warning deviation value of the area.

9. The method for monitoring meteorological disasters of Huanglong Fruit based on Internet of Things according to claim 1, wherein: The specific analysis process for determining whether to issue a disaster warning for each region is as follows: Marking the abnormal coefficient of the yellow dragon fruit in each area after the secondary adjustment as the secondary yellow dragon fruit abnormal coefficient, comparing the secondary yellow dragon fruit abnormal coefficient with the first abnormal coefficient and the second abnormal coefficient, and reclassifying each area; If an area changes from a qualified area to a critical qualified area, it is determined that the area should be monitored and warned; If an area changes from a qualified area to an unqualified area, an emergency warning will be issued for the area; If an area changes from a critical area to an unqualified area, an abnormal warning will be issued for the area; If an area changes from an unqualified area to a critical qualified area, it is determined that no warning will be issued for this area; If an area changes from an unqualified area to a qualified area, it will be determined that no warning will be issued for this area; If an area changes from a critical area to a qualified area, it is determined that no warning will be issued for this area.

10. A system using the method for monitoring Huanglong fruit meteorological disasters based on the Internet of Things according to any one of claims 1 to 9, characterized in that: include: The target environment meteorological monitoring module is used to obtain and analyze the meteorological risk parameters of the target environment, thereby analyzing the meteorological risk level of the target environment; The Huanglong Fruit Status Monitoring Module is used to monitor Huanglong Fruit in each area, collect and analyze the Huanglong Fruit image attribute parameters in each area, obtain analysis results, and classify each area based on the analysis results to obtain regional classification results. Based on the meteorological risk level of the target environment and the regional classification results, each area is graded and adjusted; The yellow dragon fruit burn monitoring and adjustment module is used to monitor and analyze the characteristic parameters of yellow dragon fruit burns in each area, and determine whether to perform secondary adjustments in each area based on the Internet of Things. At the same time, it obtains the image attribute parameters of the yellow dragon fruit in each area after the secondary adjustment is completed, and determines whether to issue disaster warnings for each area.

Images