Intelligent agricultural monitoring method and system

Abstract

The application is suitable for the technical field of agricultural monitoring, and particularly relates to a smart agricultural monitoring method and system.The method comprises the following steps: delimiting a target area requiring disease and pest monitoring, and dividing the target area into a plurality of sections, selecting monitoring points, irradiating the sections by using light source devices previously arranged at the monitoring points, and clustering the light source devices into a fixed group and an adjustable group; starting the light source devices of the fixed group, collecting spectral reflectance data at each monitoring point, wherein each wave band corresponds to a reflectance, drawing a plurality of spectral curves, and identifying the change trend of each spectral curve.The application can adjust the irradiation angle, optimize the light coverage, reduce the monitoring dead angle, meet the monitoring requirements of different leaf orientations and plant structures, greatly improve the monitoring accuracy, and improve the disease and pest control efficiency and intelligent level of crops.

Description

Technical Field

[0001] This invention relates to the field of pest and disease monitoring technology, and in particular to a smart agriculture monitoring method and system. Background Technology

[0002] Smart agriculture refers to a new agricultural model that utilizes technologies such as the Internet of Things, big data, artificial intelligence, and blockchain to manage agricultural production in a refined and intelligent manner.

[0003] In the current technology, the application of smart agriculture in the field of pest and disease control has not been effectively carried out. Most monitoring methods still rely on manual inspection or experience-based judgment. This approach is not only inefficient but also easily affected by subjective factors, resulting in lag and uncertainty in pest and disease identification. Since manual inspection usually requires sampling and observation of each field, it is time-consuming and labor-intensive, and it is difficult to achieve large-scale, continuous, real-time monitoring. Often, pests and diseases are only discovered after they have spread over a large area, missing the best time for prevention and control. Furthermore, with the gradual reduction of labor force and the continuous expansion of agricultural and forestry scale, relying solely on manual inspection can no longer meet the needs of smart agriculture for refined and intelligent pest and disease management.

[0004] When plants are healthy, their leaves have a high chlorophyll content and a strong ability to absorb red and blue light, while also exhibiting strong reflectivity in the near-infrared band. When crops are attacked by pests and diseases, the chlorophyll content decreases, photosynthesis weakens, resulting in a decrease in the absorption rate of red and blue light, and the reflectivity curve in the near-infrared band also shifts significantly.

[0005] Therefore, "how to use the light reflection characteristics of leaves for pest and disease monitoring" is the technical problem that this invention needs to solve. Summary of the Invention

[0006] The purpose of this invention is to provide a smart agriculture monitoring method and system to solve the problem of "how to use the light reflection characteristics of leaves for pest and disease monitoring" mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] A smart agriculture monitoring method, the method comprising:

[0009] The target area for pest and disease monitoring is delineated and divided into several zones. Monitoring points are selected, and the zones are illuminated using light source equipment pre-deployed at the monitoring points. The light source equipment is then clustered into two groups: fixed and adjustable.

[0010] Start the fixed group of light source equipment, collect spectral reflectance data at each monitoring point, where each band corresponds to a reflectance, plot several spectral curves, identify the changing trend of each spectral curve, compare it with the pre-built evaluation rule set, and determine whether there are risk characteristics.

[0011] If so, identify the irradiation area corresponding to the risk characteristics and define it as a potential hazard area. Activate the light source device in the adjustable group whose irradiation area includes the potential hazard area, configure several irradiation angles, plot the spectral curve for each irradiation angle, and adjust the potential hazard area, including increasing and decreasing it.

[0012] If not, update the risk characteristics at a preset frequency;

[0013] Draw a plan of each area, construct a coordinate system, determine the location coordinates of the potential hazard areas, write the area and location coordinates of the potential hazard areas into a preset template, generate a monitoring report, and push it to a preset terminal.

[0014] Furthermore, the step of selecting monitoring points and illuminating the area using light source equipment pre-deployed at the monitoring points includes:

[0015] Configure the visible light band of each light source device and integrate them to obtain the spectral sequence;

[0016] Establish the correspondence between regions and spectral band sequences, determine the environmental factors of the target region, wherein the environmental factors include at least: time and geographical location, and update the spectral band sequence.

[0017] Furthermore, the method also includes:

[0018] Based on the aforementioned environmental factors, a risk level is set for each area, wherein the risk level includes at least: high, medium, and low.

[0019] The number of light source devices in each area was counted, and a mapping between risk level and quantity was established.

[0020] Furthermore, the method also includes:

[0021] Historical data of spectral reflectance are obtained and labeled using the evaluation rule set to obtain a labeled dataset;

[0022] A risk feature recognition model is constructed and trained using the labeled dataset. Real-time spectral reflectance data is collected and input into the risk feature recognition model to output risk assessment results and correct the risk features.

[0023] Furthermore, the step of plotting several spectral curves and identifying the changing trend of each spectral curve includes:

[0024] Based on the aforementioned trend, the spectral curve is divided into several segments, relevant intervals of risk characteristics are identified, and reference data is generated.

[0025] Generate relevant links to the reference data and embed them into the monitoring report.

[0026] Furthermore, the step of writing the area and location coordinates of the potential hazard zone into a preset template includes:

[0027] The location coordinates are mapped onto a planar distribution map to generate a risk heat map, and access to view the map is granted.

[0028] Edit the handling rules that correspond one-to-one with the risk characteristics and write them into the risk heat map.

[0029] Furthermore, the system includes:

[0030] The irradiation module is used to delineate the target area for pest and disease monitoring, divide it into several areas, select monitoring points, and use light source equipment pre-deployed at the monitoring points to irradiate the areas. The light source equipment is then clustered into fixed groups and adjustable groups.

[0031] The identification module is used to activate the fixed group of light source devices, collect spectral reflectance data at each monitoring point, where each band corresponds to a reflectance, plot several spectral curves, identify the changing trend of each spectral curve, compare it with a pre-built evaluation rule set, determine whether there are risk characteristics, if so, find the irradiation area corresponding to the risk characteristics and define it as a hidden danger area, activate the light source devices in the adjustable group whose irradiation area includes the hidden danger area, configure several irradiation angles, plot the spectral curve in each irradiation angle, and adjust the hidden danger area, the adjustment including: increasing and decreasing; if not, update the risk characteristics according to a preset frequency.

[0032] The push module is used to draw a planar distribution map of each area, construct a coordinate system, determine the location coordinates of the potential hazard area, write the area and location coordinates of the potential hazard area into a preset template, generate a monitoring report, and push it to a preset terminal.

[0033] Furthermore, the irradiation module includes:

[0034] An integration unit is used to configure the visible light band of each light source device and integrate them to obtain a spectral sequence.

[0035] The update unit is used to establish the correspondence between the region and the spectral band sequence, determine the environmental factors of the target region, wherein the environmental factors include at least: time and geographical location, and update the spectral band sequence.

[0036] Furthermore, the identification module includes:

[0037] The generation unit is used to divide the spectral curve into several segments based on the changing trend, find the relevant intervals of the risk characteristics, and generate reference data.

[0038] An embedding unit is used to generate associated links to reference data and embed them into the monitoring report.

[0039] Furthermore, the push module includes:

[0040] An open unit is used to map the location coordinates onto a planar distribution map, generate a risk heat map, and grant access to view it;

[0041] The writing unit is used to edit the handling rules that correspond one-to-one with the risk characteristics and write them into the risk heat map.

[0042] Compared with the prior art, the beneficial effects of the present invention are:

[0043] By deploying light source equipment, stable light can be obtained to illuminate the leaves, resulting in a reflectance spectrum with a higher signal-to-noise ratio, thus improving the accuracy of pest and disease detection. By dividing the light source equipment into fixed and adjustable groups, the wavelength and intensity of the light source can be controlled, improving detection sensitivity, avoiding monitoring blind spots, and optimizing coverage and spatial resolution. By plotting spectral curves, the reflectance changes of leaves in different wavelength bands can be displayed intuitively, determining the health status of leaves and potential pest and disease characteristics, and effectively achieving early warning of pests and diseases. By enabling the adjustable group, the illumination angle can be adjusted, optimizing the light coverage, reducing monitoring blind spots, and meeting the monitoring needs of different leaf orientations and plant structures, greatly improving the accuracy of monitoring and enhancing the efficiency and intelligence level of crop pest and disease control. Attached Figure Description

[0044] Figure 1 A flowchart illustrating the smart agriculture monitoring method provided in an embodiment of the present invention;

[0045] Figure 2 This is a flowchart of the first sub-process of the smart agriculture monitoring method provided in the embodiments of the present invention;

[0046] Figure 3 This is a second sub-flowchart of the smart agriculture monitoring method provided in an embodiment of the present invention;

[0047] Figure 4This is a third sub-flow diagram of the smart agriculture monitoring method provided in an embodiment of the present invention;

[0048] Figure 5 This is a block diagram of the intelligent agriculture monitoring system provided in an embodiment of the present invention;

[0049] Figure 6 This is a block diagram of the illumination module in the smart agriculture monitoring system provided in an embodiment of the present invention;

[0050] Figure 7 This is a block diagram of the identification module in the smart agriculture monitoring system provided in an embodiment of the present invention;

[0051] Figure 8 This is a block diagram of the push module in the smart agriculture monitoring system provided in an embodiment of the present invention. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0053] In Example 1, Figure 1 The implementation flow of the smart agriculture monitoring method provided in this embodiment of the invention is illustrated below, and will be described in detail below:

[0054] S100: Delineate the target area for pest and disease monitoring, divide it into several zones, select monitoring points, and use the light source equipment pre-deployed at the monitoring points to illuminate the zones, and cluster the light source equipment into: fixed group and adjustable group.

[0055] Identify the target area for pest and disease monitoring, such as a field or several plots within it. According to agricultural common sense, pest and disease monitoring is generally conducted during the peak growing season or the period when pests and diseases are prone to occur. The specific timing varies depending on the crop; for example, monitoring is mainly conducted during the heading stage of rice, and usually during the jointing stage of wheat. The target area is determined based on the crop type and growth status of different fields. Divide the target area into several zones based on crop type, growth status, or physical spacing; one acre of land can be considered a zone. Select several monitoring points within each zone. The selection of monitoring points needs to comprehensively consider factors such as crop leaf orientation and areas prone to pests and diseases. Deploy light source equipment at each monitoring point. The light source equipment is divided into fixed and adjustable groups. Specifically, the light source equipment is an LED light panel. The fixed group refers to LED light panels with fixed illumination angle, brightness, and wavelength, while the adjustable group refers to LED light panels with controllable wavelength, adjustable brightness, and adjustable angle.

[0056] In this application, the fixed group is generally deployed in key locations in the field (such as the center). Since the angle, brightness and wavelength of the fixed group are fixed and do not change with the monitoring needs, it can reduce the impact of light fluctuations on spectral data, facilitate the analysis of long-term trends of spectral data, and identify early characteristics of diseases and pests. On the other hand, the brightness, irradiation angle and light band of the adjustable group can be adjusted, and localized key irradiation of leaves can be carried out. For example, key irradiation of wavelengths or areas that are sensitive to certain diseases and pests can be carried out to highlight the spectral characteristics of the diseased areas.

[0057] Using a fixed group, the area is irradiated, and the adjustable group is activated according to a preset frequency. The advantage of this method is that, in addition to enhancing the characteristics of the lesion area and long-term dynamic monitoring, the adjustable group adopts an on-demand activation mode rather than continuous operation, which greatly reduces the amount of subsequent data processing and computational load.

[0058] S200: Start the fixed group of light source equipment, collect spectral reflectance data at each monitoring point, where each band corresponds to a reflectance, plot several spectral curves, identify the changing trend of each spectral curve, compare it with the pre-constructed evaluation rule set, determine whether there is a risk feature, if so, find the irradiation area corresponding to the risk feature and define it as a hidden danger area, start the light source equipment in the adjustable group whose irradiation area includes the hidden danger area, configure several irradiation angles, plot the spectral curve in each irradiation angle, and adjust the hidden danger area, the adjustment including: increasing and decreasing; if not, update the risk feature according to a preset frequency.

[0059] When night falls, the fixed light source equipment is activated. The selected irradiation band of the fixed light source equipment is configured according to the spectral response characteristics of the target crop. Using a handheld spectrometer or other spectral acquisition equipment, spectral reflectance data at the monitoring points are collected to determine the reflectance value of each spectral segment and generate a spectral curve.

[0060] For example, a spectral reflectance data of leaves is collected at monitoring point A using a spectral analyzer. Assuming the spectral band range is 400–1000 nm, each band corresponds to a reflectance value, such as 0.32 for the 450 nm band (blue light region of the visible spectrum), 0.28 for the 550 nm band (green light region of the visible spectrum), and 0.15 for the 680 nm red light region. A spectral curve is plotted with wavelength as the x-axis and reflectance as the y-axis.

[0061] According to the preset step size, several time points are selected, the spectral curves of two adjacent time points are compared, abnormal change trends are found, and they are compared with the pre-constructed evaluation rule set to determine the monitoring results of leaves in the area and judge whether there are risk characteristics. Risk characteristics are leaves with pests and diseases. The evaluation rule set is a collection of several evaluation rules, which are the basis for judgment.

[0062] Continuing with the above details, analysis of the spectral curves revealed a significant decrease in reflectance at the 680nm band (chlorophyll absorption peak). The corresponding evaluation rule is as follows: 680nm is one of the positions of strong chlorophyll absorption peaks. Since chlorophyll absorbs most of the red light, healthy leaves will exhibit low reflectance in this band. If the leaves are affected by pests, diseases, or nutrient deficiencies, the chlorophyll content will decrease, the absorption capacity will weaken, and the reflectance will increase. The reason for this phenomenon may be that the leaves may be chlorotic or affected by diseases.

[0063] If risk features (disease-infested leaves) exist in a monitoring area, the irradiated area where the risk features are located is defined as a potential hazard area. During monitoring, fixed groups can be activated at different times to locate the irradiated range of the risk features. The adjustable light source equipment corresponding to that range is then activated, and the irradiation angle is adjusted to irradiate the potential hazard area at different incident angles (direct, oblique, or a combination of multiple directions). The specific irradiation angle is determined by professionals based on crop type, growth status, etc. At each irradiation angle, a spectrometer collects reflectance data of the leaves in multiple wavelengths and plots it as a spectral curve. This method can reveal the spectral characteristics of leaves under different angular illumination conditions. By cross-referencing the spectral curves from multiple angles, the location of leaf lesions can be accurately located, identifying which areas show abnormal spectral characteristics under different illumination conditions, thus pinpointing the location of lesions. This also prevents monitoring blind spots caused by leaf shading, revealing the true optical characteristics of potential hazard areas at a higher angular resolution, providing reliable data support for early diagnosis and precise control of diseases and pests.

[0064] According to basic optical principles, when the illumination angle of the adjustable group changes, the corresponding illumination area will inevitably change as well. The illumination area with the most obvious trend of change in the spectral curve is determined, and the identified potential hazard area is adjusted. The adjustment refers to increasing the area of ​​the potential hazard area or reducing the boundary of the potential hazard area.

[0065] In this application, by setting up a fixed group, the location of the diseased and pest-infested leaves (i.e., the potential danger area) is initially determined, and by using an adjustable group, the potential danger area is verified and its boundaries are adjusted, thereby accurately locating the position of the diseased and pest-infested leaves.

[0066] S300: Draw a plan of each area, construct a coordinate system, determine the location coordinates of the hazard area, write the area and location coordinates of the hazard area into a preset template, generate a monitoring report, and push it to a preset terminal.

[0067] A planar distribution map of each area is drawn, and a coordinate system is established on each planar distribution map to determine the location coordinates of the potential hazard areas. The location coordinates are only one way to represent potential hazard areas, mainly used to quickly determine the location of potential hazard areas. Potential hazard areas can also be marked by directly tying a marker rope (such as a red rope) to the crops in the potential hazard area. The area number or identifier of each area is determined, and the area number and location coordinates of the potential hazard area are written into a preset template. The generated monitoring report is then pushed to preset terminal devices, such as farmers' mobile applications, agricultural management platforms, or the display screen of the monitoring center.

[0068] In Example 2, Figure 2 The implementation flow of the smart agriculture monitoring method provided by an embodiment of the present invention is illustrated below. The steps of selecting monitoring points and illuminating the area using light source devices pre-deployed at the monitoring points are described in detail below:

[0069] S101: Configure the visible light band of each light source device and integrate them to obtain the spectral sequence.

[0070] When irradiating the area, a visible light band (such as blue light, green light, and red light) can be set for each light source device, and the luminous intensity and irradiation range of each light source in each band can be recorded. For example, if there are three fixed groups of light source devices A, B, and C, A is irradiated with blue light, B with green light, and C with red light, the spectral sequence can be obtained by integrating them, where the spectral sequence is "blue-green-red".

[0071] S102: Establish the correspondence between the region and the spectral band sequence, determine the environmental factors of the target region, wherein the environmental factors include at least: time and geographical location, and update the spectral band sequence.

[0072] Each region corresponds to a spectral band sequence to determine the impact of environmental factors on spectral acquisition. These environmental factors include acquisition time (specific time period at night) and geographical location (such as the latitude and longitude or relative coordinates of the region in farmland). This allows for adjustments to the light source power or band sequence under different lighting conditions and geographical locations, thereby improving the stability and comparability of spectral data.

[0073] In Embodiment 3, unlike Embodiment 1, the method further includes:

[0074] Based on the aforementioned environmental factors, a risk level is set for each area, wherein the risk level includes at least: high, medium, and low.

[0075] The number of light source devices in each area was counted, and a mapping between risk level and quantity was established.

[0076] The risk level of each area is determined, which includes high, medium and low. For example, if an area is in the peak period of pests and diseases and the crops grown in the area have high economic value, then the risk level of the area can be defined as high. Different numbers of light source devices are set up for areas with different risk levels to highlight key areas and achieve accurate monitoring of potential danger areas.

[0077] In Example 4, unlike Example 1, the method further includes:

[0078] Historical data of spectral reflectance are obtained and labeled using the evaluation rule set to obtain a labeled dataset;

[0079] A risk feature recognition model is constructed and trained using the labeled dataset. Real-time spectral reflectance data is collected and input into the risk feature recognition model to output risk assessment results and correct the risk features.

[0080] Historical data on spectral reflectance is obtained, including multi-band reflectance curves collected from different areas, at different times, and under different light source conditions. Professionals label the historical data according to the evaluation rule set (e.g., healthy, suspected disease, disease), and integrate them to obtain a labeled dataset.

[0081] By utilizing machine learning or deep learning methods, a risk feature recognition model is created. This model learns from historical spectral reflectance data and its corresponding annotations, enabling it to identify the mapping relationship between different spectral features and risk categories. Real-time spectral reflectance data is input into the risk feature recognition model, which extracts and compares features from the data and outputs risk assessment results. These risk assessment results refer to potential risk features, and the risk features are then corrected using these results. The advantage of this approach is that it can significantly improve the accuracy of risk features.

[0082] In Example 5, Figure 3 The implementation flow of the smart agriculture monitoring method provided by the embodiment of the present invention is shown below. The steps of drawing several spectral curves and identifying the changing trend of each spectral curve are described in detail below:

[0083] S201: Based on the aforementioned trend, the spectral curve is divided into several segments, relevant intervals of risk characteristics are identified, and reference data is generated.

[0084] The spectral curve is divided into several segments, such as the rising segment and the falling segment. Continuing with the example in S200, when the red light region at 680nm shows a decreasing trend between two adjacent time points, the reflectance of the green light region can be found. It can then be determined whether the reflectance increases between two adjacent time points. If it increases, it indicates that there are indeed diseased or pest-infested leaves, thus verifying the analysis results of the red light region. The two adjacent time points are the relevant intervals, and the reflectance of the green light region is the reference data.

[0085] S202: Generate a link to the reference data and embed it into the monitoring report.

[0086] Generate links for accessing reference data, i.e., association links, and write them to the monitoring report, thereby greatly improving the traceability of the monitoring report.

[0087] In Example 6, Figure 4 The implementation flow of the smart agriculture monitoring method provided by the embodiment of the present invention is shown below. The step of writing the area and location coordinates of the potential hazard area into the preset template is described in detail below:

[0088] S301: Map the location coordinates onto the planar distribution map to generate a risk heat map and grant access to view it.

[0089] The location coordinates are mapped onto a planar distribution map, and a risk heat map is generated. The risk level is reflected by the color depth and hue changes. For example, red areas represent high risk, yellow represents medium risk, and green represents low risk. Access to the map is granted to all farmers in the target area.

[0090] S302: Edit the handling rules that correspond one-to-one with the risk characteristics and write them into the risk heat map.

[0091] Based on different risk characteristics, corresponding disposal rules are formulated. These rules include specific prevention and control measures, light source control strategies, monitoring frequency, and personnel patrol arrangements. The disposal rules are then written into the corresponding areas of the risk heat map.

[0092] Figure 5 This diagram illustrates the structural block diagram of a smart agriculture monitoring system provided in an embodiment of the present invention. The smart agriculture monitoring system 1 includes:

[0093] The irradiation module 11 is used to delineate the target area that needs to be monitored for pests and diseases, divide it into several areas, select monitoring points, and use the light source equipment pre-deployed in the monitoring points to irradiate the areas, and cluster the light source equipment into: fixed group and adjustable group.

[0094] The identification module 12 is used to determine the deployment location of the spectral imaging device, activate the light source device of the fixed group, collect spectral reflectance data at each monitoring point, where each band corresponds to a reflectance, draw several spectral curves, identify the changing trend of each spectral curve, compare it with the pre-constructed evaluation rule set, determine whether there is a risk feature, if so, find the irradiation area corresponding to the risk feature and define it as a hidden danger area, activate the light source device in the adjustable group whose irradiation area includes the hidden danger area, configure several irradiation angles, draw the spectral curve in each irradiation angle, and adjust the hidden danger area, the adjustment including: increasing and decreasing; if not, update the risk feature according to a preset frequency.

[0095] The push module 13 is used to draw a planar distribution map of each area, construct a coordinate system, determine the location coordinates of the hidden danger area, write the area and location coordinates of the hidden danger area into a preset template, generate a monitoring report, and push it to a preset terminal.

[0096] Figure 6 This diagram illustrates the structural block diagram of the smart agriculture monitoring system provided in an embodiment of the present invention. The illumination module 11 includes:

[0097] Integration unit 111 is used to configure the visible light band of each light source device and integrate them to obtain a spectral sequence.

[0098] The update unit 112 is used to establish the correspondence between the region and the spectral band sequence, determine the environmental factors of the target region, wherein the environmental factors include at least: time and geographical location, and update the spectral band sequence.

[0099] Figure 7 This diagram illustrates the structural composition of a smart agriculture monitoring system provided in an embodiment of the present invention. The identification module 12 includes:

[0100] The generation unit 121 is used to divide the spectral curve into several segments based on the changing trend, find the relevant intervals of the risk characteristics, and generate reference data.

[0101] The embedding unit 122 is used to generate associated links to the reference data and embed them into the monitoring report.

[0102] Figure 8 This diagram illustrates the structural composition of a smart agriculture monitoring system provided in an embodiment of the present invention. The push module 13 includes:

[0103] The open unit 131 is used to map the location coordinates onto a planar distribution map, generate a risk heat map, and grant access to view it;

[0104] The writing unit 132 is used to edit the handling rules that correspond one-to-one with the risk characteristics and write them into the risk heat map.

[0105] The irradiation module 11 is mainly used to complete step S100, the identification module 12 is mainly used to complete step S200, and the push module 13 is mainly used to complete step S300.

[0106] Integration unit 111 is mainly used to complete step S101, and updating unit 112 is mainly used to complete step S102;

[0107] The generating unit 121 is mainly used to complete step S201, and the embedding unit 122 is mainly used to complete step S202.

[0108] The open unit 131 is mainly used to complete step S301, and the write unit 132 is mainly used to complete step S302.

[0109] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0110] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0111] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A smart agriculture monitoring method, characterized in that, The method includes: The target area for pest and disease monitoring is delineated and divided into several zones. Monitoring points are selected, and the zones are illuminated using light source equipment pre-deployed at the monitoring points. The light source equipment is then clustered into two groups: fixed and adjustable. Start the fixed group of light source equipment, collect spectral reflectance data at each monitoring point, where each band corresponds to a reflectance, plot several spectral curves, identify the changing trend of each spectral curve, compare it with the pre-built evaluation rule set, and determine whether there are risk characteristics. If so, find the irradiation area corresponding to the risk characteristics and define it as the hidden danger area. Start the light source equipment in the adjustable group whose irradiation area includes the hidden danger area, configure several irradiation angles, and draw the spectral curve in each irradiation angle. By cross-comparing the spectral curves of multiple angles, determine the irradiation area with the most obvious trend of spectral curve change, and adjust the identified hidden danger area. The adjustment refers to increasing the area of ​​the hidden danger area or reducing the boundary of the hidden danger area. If not, update the risk characteristics at a preset frequency; Draw a plan of each area, construct a coordinate system, determine the location coordinates of the potential hazard areas, write the area and location coordinates of the potential hazard areas into a preset template, generate a monitoring report, and push it to a preset terminal.

2. The smart agriculture monitoring method according to claim 1, characterized in that, The step of selecting monitoring points and illuminating the area using light source equipment pre-deployed at the monitoring points includes: Configure the visible light band of each light source device and integrate them to obtain the spectral sequence; Establish the correspondence between regions and spectral band sequences, determine the environmental factors of the target region, wherein the environmental factors include at least: time and geographical location, and update the spectral band sequence.

3. The smart agriculture monitoring method according to claim 2, characterized in that, The method further includes: Based on the aforementioned environmental factors, a risk level is set for each area, wherein the risk level includes at least: high, medium, and low. The number of light source devices in each area was counted, and a mapping between risk level and quantity was established.

4. The smart agriculture monitoring method according to claim 1, characterized in that, The method further includes: Historical data of spectral reflectance are obtained and labeled using the evaluation rule set to obtain a labeled dataset; A risk feature recognition model is constructed and trained using the labeled dataset. Real-time spectral reflectance data is collected and input into the risk feature recognition model to output risk assessment results and correct the risk features.

5. The smart agriculture monitoring method according to claim 1, characterized in that, The step of plotting several spectral curves and identifying the changing trend of each spectral curve includes: Based on the aforementioned trend, the spectral curve is divided into several segments, relevant intervals of risk characteristics are identified, and reference data is generated. Generate relevant links to the reference data and embed them into the monitoring report.

6. The smart agriculture monitoring method according to claim 1, characterized in that, The step of writing the area and location coordinates of the potential hazard zone into the preset template includes: The location coordinates are mapped onto a planar distribution map to generate a risk heat map, and access to view the map is granted. Edit the handling rules that correspond one-to-one with the risk characteristics and write them into the risk heat map.

7. The smart agriculture monitoring method according to claim 1, characterized in that, The method further includes: Collect multimodal sensing data for each area, wherein the multimodal sensing data includes at least: soil moisture, pH value and nutrient index; Create fluctuation ranges that correspond one-to-one with multimodal sensing data, and edit a set of emergency rules consisting of several emergency rules, where each fluctuation range corresponds to one emergency rule; When the multimodal sensing data exceeds the fluctuation range, the corresponding emergency rule is activated.

8. A smart agriculture monitoring system, characterized in that, The system includes: The irradiation module is used to delineate the target area for pest and disease monitoring, divide it into several areas, select monitoring points, and use light source equipment pre-deployed at the monitoring points to irradiate the areas. The light source equipment is then clustered into fixed groups and adjustable groups. The identification module is used to activate the fixed group of light source devices, collect spectral reflectance data at each monitoring point, where each band corresponds to a reflectance, plot several spectral curves, identify the changing trend of each spectral curve, compare it with the pre-constructed evaluation rule set, determine whether there are risk characteristics, if so, find the irradiation area corresponding to the risk characteristics and define it as a hidden danger area, activate the light source devices in the adjustable group whose irradiation area includes the hidden danger area, configure several irradiation angles, plot the spectral curve at each irradiation angle, determine the irradiation area with the most obvious changing trend of the spectral curve through cross-comparison of multi-angle spectral curves, and adjust the identified hidden danger area, where adjustment refers to increasing the area of ​​the hidden danger area or reducing the boundary of the hidden danger area; if not, update the risk characteristics according to a preset frequency. The push module is used to draw a planar distribution map of each area, construct a coordinate system, determine the location coordinates of the potential hazard area, write the area and location coordinates of the potential hazard area into a preset template, generate a monitoring report, and push it to a preset terminal.

9. The intelligent agricultural monitoring system according to claim 8, characterized in that, The irradiation module includes: An integration unit is used to configure the visible light band of each light source device and integrate them to obtain a spectral sequence. The update unit is used to establish the correspondence between the region and the spectral band sequence, determine the environmental factors of the target region, wherein the environmental factors include at least: time and geographical location, and update the spectral band sequence.

10. The intelligent agricultural monitoring system according to claim 8, characterized in that, The identification module includes: The generation unit is used to divide the spectral curve into several segments based on the changing trend, find the relevant intervals of the risk characteristics, and generate reference data. An embedding unit is used to generate associated links to reference data and embed them into the monitoring report.

Images