Intelligent agriculture cloud platform monitoring system based on big data
By monitoring plant growth areas in real time on the smart agriculture cloud platform, calculating growth conditions and impact values, identifying growth abnormal areas, and determining the amount of pesticide spraying based on the risk value, the problem of difficult to monitor and deal with plant growth abnormalities in the prior art is solved. Effective management and environmental protection of crop growth have been achieved.
Patent Information
- Application Number
- CN202410962832.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing smart agriculture remote monitoring system is difficult to monitor plant growth abnormalities in real time, fails to provide timely warnings, and cannot identify unstable plants, resulting in excessive pesticide use and environmental pollution.
A smart agricultural cloud platform monitoring system based on big data was designed, including anomaly monitoring module, impact analysis module, risk assessment module and optimization processing module. By monitoring the plant growth area in real time, calculating the growth status value and impact value, and generating abnormal signals , mark the growth abnormal areas and determine the targeted pesticide spray amount based on the risk value.
It realizes timely detection and treatment of abnormal plant growth, reduces the use of pesticides, avoids environmental pollution, and ensures the uniformity and health of crop growth.
Smart Images

Figure CN118917664A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of agricultural big data information technology, and in particular to a smart agricultural cloud platform monitoring system based on big data. Background Art
[0002] Smart agriculture is the application of Internet of Things technology in the field of modern agriculture. It mainly includes monitoring function systems, surveillance function systems, and real-time image and video surveillance functions. At present, different types of crops are planted in agricultural plantations. During the growth process of crops, they need to be monitored regularly (for example, monitoring whether pests and diseases occur). Generally, the status monitoring is carried out by the managers of agricultural plantations. Due to the large scale of agricultural plantations and high labor costs, the managers’ agricultural planting experience may not be comprehensive, which may lead to inadequate status monitoring.
[0003] A Chinese invention patent with publication number CN116300608A discloses a smart agricultural remote monitoring system based on big data, including a remote monitoring unit, an information processing unit, an information storage unit, a crop classification and filing unit, a crop evaluation unit, an information display unit and an alarm unit. The remote monitoring unit is used to comprehensively monitor and collect agricultural environment images in the area through multiple monitoring cameras.
[0004] However, there is no real-time monitoring to detect abnormal plant growth in time, provide real-time warnings for managers, and use the growth impact values obtained by analysis to provide data support for the subsequent treatment of abnormally growing plants. There is no identification of plants with unstable growth, thereby avoiding the impact on the growth of other surrounding plants, and quantitative pesticide spraying on abnormally growing plants in the pest control area, so that targeted pesticide spraying is carried out on abnormally growing plants in each pest control area, avoiding excessive use of pesticides and causing environmental pollution. Summary of the invention
[0005] The purpose of the present invention is to provide a smart agriculture cloud platform monitoring system based on big data to solve the technical problems in the above background.
[0006] The purpose of the present invention can be achieved through the following technical solutions:
[0007] In a first aspect, the present invention provides a smart agriculture cloud platform monitoring system based on big data, the system comprising the following modules:
[0008] Abnormal monitoring module: Real-time monitoring of plant growth areas, dividing the plant planting area into multiple monitoring areas in equal areas, and then obtaining the growth status value of each monitoring area, comparing the growth status value with the growth status threshold, and generating a growth abnormality signal;
[0009] If the growth condition value is greater than or equal to the growth condition threshold, the plant corresponding to the abnormal growth signal is marked as an abnormal growth area;
[0010] Impact analysis module: Based on the regional plant abnormality signal, the total value of the proportion of pests and diseases leaves is calculated with the total abnormality value to obtain the growth impact value of each plant. All growth impact values in the growth abnormality area are summed up to obtain the growth impact value of the growth abnormality area, which is compared with the growth impact threshold to generate an impact degree signal;
[0011] If the growth impact value is greater than or equal to the growth deviation threshold, a high impact signal is generated, and the abnormal growth area is marked as a harm-removal area;
[0012] Risk assessment module: Based on the large signal of the impact degree, the annular abnormal growth coefficient and the height abnormal growth coefficient are obtained in the plant growth area, and the annular abnormal growth coefficient and the height abnormal growth coefficient are added together to obtain the growth risk value;
[0013] Optimization processing module: Based on the growth risk value of each pest control area, the pesticide spraying coefficient of the pest control area is obtained, and the pesticide spraying coefficient of the pest control area is multiplied by the current total amount of pesticide spraying to obtain the pesticide spraying amount of each pest control area, and complete the pesticide spraying work on pest-prone plants.
[0014] As a further solution of the present invention: the growth status value is obtained in the following manner:
[0015] In each monitoring area, the growth height deviation coefficient in the monitoring area is obtained, and the growth height deviation coefficients in the monitoring area are added and averaged to obtain the growth status value.
[0016] As a further solution of the present invention: the process of obtaining the growth height deviation coefficient is as follows:
[0017] During the monitoring period, the growth height of each plant in the monitoring area is obtained, and the growth height of each plant is subtracted from the preset growth height to obtain the growth height deviation value. The growth height deviation value is ratio-calculated with the preset growth height to obtain the growth height deviation coefficient of each plant.
[0018] As a further solution of the present invention: the method for obtaining the total abnormal value of each plant is:
[0019] In the abnormal growth area, each plant is identified for pests and diseases, abnormal plants and normal plants are obtained, and the pest and disease leaves of the abnormal plants are obtained;
[0020] The abnormal plants were analyzed to obtain the stem line abnormality value and the branch line abnormality value. The annular abnormality value and the height abnormality value were summed to obtain the total abnormality value of each plant.
[0021] As a further solution of the present invention: the analysis process of the annular outlier is:
[0022] The abnormal plants were divided into several analysis angle areas at equal angles along the main trunk as the center. The maximum value of the proportion of diseased and insect pest leaves in each analysis angle area was extracted. The standard deviation of the maximum value of the proportion of diseased and insect pest leaves in all analysis angle areas was calculated to obtain the annular outlier value.
[0023] As a further solution of the present invention: the analysis process of the highly abnormal value is:
[0024] Based on the percentage of leaves with pests and diseases, the abnormal plants were divided at equidistant heights to obtain several analysis high areas. The maximum percentage of leaves with pests and diseases in each analysis high area was extracted, and then the standard deviation of the maximum percentage of leaves with pests and diseases in all analysis high areas was calculated to obtain the height abnormality value.
[0025] As a further solution of the present invention: the process of obtaining the total value of the percentage of leaves with pests and diseases is as follows:
[0026] Get the number of leaves on each branch of the abnormal plants, marked as the total number of abnormal branches and leaves, and the number of diseased and insect-infested leaves on each branch, marked as the number of branch and trunk diseased and insect-infested leaves, calculate the ratio of the number of branch and trunk diseased and insect-infested leaves to the total number of abnormal branches and trunk leaves, and calculate the sum of the diseased and insect-infested leaf ratios of all branches in the abnormal plants to obtain the total diseased and insect-infested leaf ratio.
[0027] As a further solution of the present invention: the process of obtaining the annular abnormal growth coefficient is:
[0028] During the monitoring period, the ring anomaly value at the beginning of the monitoring period and the ring anomaly value at the end of the monitoring period are obtained, which are marked as the starting ring anomaly value and the ending ring anomaly value respectively. The difference between the ending ring anomaly value and the starting ring anomaly value is calculated to obtain the ring anomaly growth coefficient.
[0029] As a further solution of the present invention, the process of obtaining the height abnormal growth coefficient is:
[0030] During the monitoring period, the height anomaly value at the beginning and the end of the monitoring period are obtained, marked as the starting height anomaly value and the ending height anomaly value respectively, and the difference between the ending height anomaly value and the starting height anomaly value is calculated to obtain the height anomaly growth coefficient.
[0031] As a further solution of the present invention, the process of obtaining the pesticide spraying coefficient in the abnormal growth area is as follows:
[0032] The growth risk value of each pest control area is marked as ZF i, where i represents the number of pest control areas, and the formula The pesticide spraying coefficient XPi of each pest control area is calculated.
[0033] Beneficial effects of the present invention:
[0034] (1) The present invention monitors the plant growth area in real time, divides the plant planting area into multiple monitoring areas in an equal area manner, and then obtains the growth status value of each monitoring area, compares the growth status value with the growth status threshold, generates a growth abnormality signal, and calculates the ratio of the total value of the leaf proportion of pests and diseases to the total abnormal value based on the regional plant abnormality signal to obtain the growth impact value of each plant, sums all the growth impact values in the growth abnormality area to obtain the growth impact value of the growth abnormality area, compares it with the growth impact threshold, and generates an impact degree signal. By calculating the growth height deviation coefficient of the plants in the monitoring area, the uniformity of plant growth can be reflected. According to the impact degree signal, a targeted management area can be formulated to timely discover and solve problems existing in the plant growth process;
[0035] (2) The present invention obtains the abnormal plant growth value and the abnormal plant state value based on the large signal of the degree of influence, adds the abnormal plant growth value and the abnormal plant state value to obtain the growth risk value, compares the growth risk threshold value, generates the abnormal area risk size signal, obtains the pesticide spraying coefficient of the pest control area based on the growth risk value of each pest control area, determines the pesticide spraying amount of each pest control area, and completes the pesticide spraying work on the abnormal plants. By obtaining the pesticide spraying coefficient of the pest control area and determining the pesticide spraying amount of each pest control area accordingly, the abnormal growth plants in each abnormal growth area are sprayed with targeted pesticides to avoid environmental pollution caused by excessive use of pesticides. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The present invention will be further described below in conjunction with the accompanying drawings.
[0037] Figure 1 It is a flow chart of the system of the present invention;
[0038] Figure 2 is a flow chart of the method of embodiment 1 of the present invention;
[0039] Figure 3 It is a flow chart of the method of embodiment 2 of the present invention. DETAILED DESCRIPTION
[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0041] Embodiment 1:
[0042] See also Figure 1-2 As shown, the smart agriculture cloud platform monitoring system based on big data described in the embodiment of the present invention specifically includes the following modules:
[0043] Abnormal monitoring module: monitors the plant growth area in real time, obtains the growth status value, compares it with the growth status threshold, and generates a signal whether the growth is abnormal;
[0044] Wherein, whether the growth is abnormal signal includes an abnormal growth signal and a normal growth signal;
[0045] In some embodiments, the plant planting area is divided into a plurality of monitoring areas in an equal area manner, and then the growth status value of each monitoring area is obtained, and the growth status value is compared with the growth status threshold value. The comparison process is as follows:
[0046] If the growth status value is greater than or equal to the growth status threshold, it means that the plant growth height deviation is large, and a regional plant abnormality signal is generated, and the plant corresponding to the generated growth abnormality signal is marked as a growth abnormality area;
[0047] If the growth status value is less than the growth status threshold, it means that the plant growth height deviation is small, and a normal plant signal is generated in the area, and the plant corresponding to the normal growth signal is marked as a normal growth area;
[0048] Exemplarily, the growth status value is obtained in the following manner:
[0049] In each monitoring area, the growth height deviation coefficient in the monitoring area is obtained, and the growth height deviation coefficients in the monitoring area are added and averaged to obtain the growth status value;
[0050] Specifically, the process of obtaining the growth height deviation coefficient is as follows:
[0051] During the monitoring period, the growth height of each plant in the monitoring area is obtained, the growth height of each plant is subtracted from the preset growth height to obtain a growth height deviation value, and the growth height deviation value is calculated by ratio with the preset growth height to obtain a growth height deviation coefficient of each plant;
[0052] Impact analysis module: Based on the abnormal signals of regional plants, the growth impact value is obtained, compared with the growth impact threshold, and the impact degree signal is generated;
[0053] The impact degree signal includes a large impact degree signal and a small impact degree signal;
[0054] In some embodiments, when a regional plant abnormality signal is generated, a growth impact value of the growth abnormality region is obtained, and the growth impact value is compared with a growth impact threshold. The comparison process is as follows:
[0055] If the growth impact value is greater than or equal to the growth deviation threshold, it means that there are plants with diseased leaves in a large range in the current abnormal growth area, and a large impact signal is generated, marking the abnormal growth area as a pest control area;
[0056] If the growth impact value is less than the growth deviation threshold, it means that there are plants with diseased leaves in a smaller range in the current growth abnormality area, generating a small impact signal;
[0057] The growth impact value is obtained as follows:
[0058] In the abnormal growth area, each plant is identified for pests and diseases, abnormal plants and normal plants are obtained, and the pest and disease leaves of the abnormal plants are obtained;
[0059] Analyze the abnormal plants to obtain the stem line abnormality value and the branch line abnormality value, calculate the sum of the ring abnormality value and the height abnormality value to obtain the total abnormality value of each plant, calculate the ratio of the total value of the leaf proportion of pests and diseases to the total abnormality value to obtain the growth impact value of each plant, sum up all the growth impact values in the growth abnormal area to obtain the growth impact value of the growth abnormal area;
[0060] Among them, it is necessary to further explain that the identification of pests and diseases for each plant is carried out by analyzing the state of each leaf on the plant through existing technology. If there are changes in color state such as spots, yellowing, chlorosis, etc. on the leaves, or morphological changes such as curling, deformity and perforation on the leaves, or there are leaf attachments such as mold layer, mucus, insect bodies, etc. on the leaf surface, it is identified as a leaf with pests and diseases;
[0061] First, specifically, the process of obtaining the total value of the proportion of leaves with pests and diseases is as follows:
[0062] Obtain the number of leaves on each branch of the abnormal plant, marked as the total number of leaves on the abnormal branches, and the number of pest-infected leaves on each branch, marked as the number of pest-infected leaves on the branches, calculate the ratio of the number of pest-infected leaves on the branches to the total number of leaves on the abnormal branches, and obtain the percentage of pest-infected leaves. Calculate the sum of the percentage of pest-infected leaves on all branches of the abnormal plant to obtain the total percentage of pest-infected leaves.
[0063] Second, specifically, the analysis process of the annular outlier is:
[0064] The abnormal plants are divided into several analysis angle regions along the main trunk with equal angles as the center (the number of analysis angle regions is: 360° divided by the divided angles), the maximum value of the proportion of pests and diseases leaves in each analysis angle region is extracted, and then the standard deviation of the maximum value of the proportion of pests and diseases leaves in all analysis angle regions is calculated to obtain the annular outlier value;
[0065] The meaning of the branch line abnormal value: the area of abnormal plants scattered along the ring, judging the severity of pests and diseases. The larger the branch line abnormal value, the more uneven the pests and diseases are in the plant ring direction, and the smaller the branch line abnormal value, the more even the pests and diseases are in the plant ring direction.
[0066] Third, specifically, the analysis process of highly outliers is:
[0067] Based on the percentage of pests and diseases leaves, the abnormal plants are divided into several analysis high areas at equal distances, and the maximum percentage of pests and diseases leaves in each analysis high area is extracted. Then, the standard deviation of the maximum percentage of pests and diseases leaves in all analysis high areas is calculated to obtain the height abnormal value;
[0068] Among them, it is necessary to further explain that the meaning of the stem line abnormal value is: taking the growth height of the main trunk of the abnormal plant as an example, the main trunk of the abnormal plant is divided at equal heights to obtain several equal-height main trunk areas, and the distribution of the leaves of pests and diseases along the height of the main trunk of the entire abnormal plant is analyzed. The larger the stem line abnormal value, the more uneven the damage of pests and diseases in the height direction of the plant, and the smaller the stem line abnormal value, the more even the damage of pests and diseases in the height direction of the plant.
[0069] The specific scheme of the embodiment of the present invention is: real-time monitoring of the plant growth area, dividing the plant planting area into multiple monitoring areas in an equal area manner, and then obtaining the growth status value of each monitoring area, comparing the growth status value with the growth status threshold, generating a growth abnormality signal, based on the regional plant abnormality signal, calculating the ratio of the total value of the proportion of leaves with pests and diseases to the total abnormality value, obtaining the growth impact value of each plant, summing up all the growth impact values in the growth abnormality area, obtaining the growth impact value of the growth abnormality area, comparing it with the growth impact threshold, generating an impact degree signal, and by calculating the growth height deviation coefficient of the plants in the monitoring area, the uniformity of plant growth can be reflected, and according to the impact degree signal, targeted management areas can be formulated to promptly discover and solve problems existing in the plant growth process.
[0070] Embodiment 2:
[0071] Based on Example 1, please refer to Figure 3 As shown, the smart agriculture cloud platform monitoring system based on big data described in the embodiment of the present invention also includes the following specific methods:
[0072] Risk assessment module: based on the large signal of impact degree, obtain the growth risk value of the pest control area;
[0073] In some embodiments, when a large impact degree signal is generated, a growth risk value of each pest control area in the plant growth area is obtained;
[0074] The growth risk value is obtained as follows:
[0075] Obtaining a ring abnormal growth coefficient and a height abnormal growth coefficient, adding the ring abnormal growth coefficient and the height abnormal growth coefficient together to obtain a growth risk value;
[0076] First, specifically, the process of obtaining the annular anomaly growth coefficient is:
[0077] During the monitoring period, the annular anomaly value at the beginning of the monitoring period and the annular anomaly value at the end of the monitoring period are obtained, which are marked as the beginning annular anomaly value and the ending annular anomaly value respectively, and the difference between the ending annular anomaly value and the beginning annular anomaly value is calculated to obtain the annular anomaly growth coefficient;
[0078] Second, specifically, the process of obtaining the highly abnormal growth coefficient is:
[0079] During the monitoring period, the height anomaly value at the beginning of the monitoring period and the height anomaly value at the end of the monitoring period are obtained, which are marked as the starting height anomaly value and the ending height anomaly value respectively. The difference between the ending height anomaly value and the starting height anomaly value is calculated to obtain the height anomaly growth coefficient;
[0080] Optimization processing module: Based on the growth risk value of each pest control area, the pesticide spraying coefficient of the pest control area is obtained, the pesticide spraying amount of each pest control area is determined, and the pesticide spraying work on abnormal plants is completed;
[0081] In some embodiments, according to the growth risk value of each pest control area, the pesticide spraying coefficient of the pest control area is obtained, and the pesticide spraying coefficient of the pest control area is multiplied by the current total amount of pesticide spraying to obtain the pesticide spraying amount of each pest control area, so as to complete the pesticide spraying work on the pest plants;
[0082] Among them, the process of obtaining the pesticide spraying coefficient in the abnormal growth area is as follows:
[0083] The growth risk value of each pest control area is marked as ZF i, where i represents the number of pest control areas, and the formula Calculate the pesticide spraying coefficient XPi for each pest control area;
[0084] It should be noted that the current total amount of pesticide spraying is determined by technicians based on experience;
[0085] The specific implementation plan of the embodiment of the present invention is: based on the large signal of the degree of influence, the abnormal plant growth value and the abnormal plant state value are obtained, the abnormal plant growth value and the abnormal plant state value are added and summed to obtain the growth risk value, the growth risk threshold is compared, and the abnormal area risk size signal is generated, based on the growth risk value of each pest control area, the pesticide spraying coefficient of the pest control area is obtained, the pesticide spraying amount of each pest control area is determined, and the pesticide spraying work on the abnormal plants is completed. By obtaining the pesticide spraying coefficient of the pest control area and determining the pesticide spraying amount of each pest control area accordingly, the abnormal growth plants in each abnormal growth area are sprayed with targeted pesticides to avoid environmental pollution caused by excessive use of pesticides.
[0086] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.
Claims
1. A smart agriculture cloud platform monitoring system based on big data, characterized in that: The system includes the following modules: Abnormal monitoring module: Real-time monitoring of plant growth areas, dividing the plant planting area into multiple monitoring areas in equal areas, and then obtaining the growth status value of each monitoring area, comparing the growth status value with the growth status threshold, and generating a growth abnormality signal; If the growth condition value is greater than or equal to the growth condition threshold, the plant corresponding to the abnormal growth signal is marked as an abnormal growth area; Impact analysis module: Based on the regional plant abnormality signal, the total value of the proportion of pests and diseases leaves is calculated with the total abnormality value to obtain the growth impact value of each plant. All growth impact values in the growth abnormality area are summed up to obtain the growth impact value of the growth abnormality area, which is compared with the growth impact threshold to generate an impact degree signal; If the growth impact value is greater than or equal to the growth deviation threshold, a high impact signal is generated, and the abnormal growth area is marked as a harm-removal area; Risk assessment module: Based on the large signal of the impact degree, the annular abnormal growth coefficient and the height abnormal growth coefficient are obtained in the plant growth area, and the annular abnormal growth coefficient and the height abnormal growth coefficient are added together to obtain the growth risk value; Optimization processing module: Based on the growth risk value of each pest control area, the pesticide spraying coefficient of the pest control area is obtained, and the pesticide spraying coefficient of the pest control area is multiplied by the current total amount of pesticide spraying to obtain the pesticide spraying amount of each pest control area, and complete the pesticide spraying work on pest-prone plants.
2. According to the big data-based smart agriculture cloud platform monitoring system of claim 1, it is characterized in that: The growth status value is obtained in the following manner: In each monitoring area, the growth height deviation coefficient in the monitoring area is obtained, and the growth height deviation coefficients in the monitoring area are added and averaged to obtain the growth status value.
3. According to the big data-based smart agriculture cloud platform monitoring system of claim 1, it is characterized in that: The process of obtaining the growth height deviation coefficient is as follows: During the monitoring period, the growth height of each plant in the monitoring area is obtained, and the growth height of each plant is subtracted from the preset growth height to obtain the growth height deviation value. The growth height deviation value is ratio-calculated with the preset growth height to obtain the growth height deviation coefficient of each plant.
4. According to the big data-based smart agriculture cloud platform monitoring system of claim 3, it is characterized in that: The total abnormal value of each plant is obtained as follows: In the abnormal growth area, each plant is identified for pests and diseases, abnormal plants and normal plants are obtained, and the pest and disease leaves of the abnormal plants are obtained; The abnormal plants were analyzed to obtain the stem line abnormality value and the branch line abnormality value. The annular abnormality value and the height abnormality value were summed to obtain the total abnormality value of each plant.
5. According to the big data-based smart agriculture cloud platform monitoring system of claim 3, it is characterized in that: The analysis process of the annular outlier is as follows: The abnormal plants were divided into several analysis angle areas at equal angles along the main trunk as the center. The maximum value of the proportion of diseased and insect pest leaves in each analysis angle area was extracted. The standard deviation of the maximum value of the proportion of diseased and insect pest leaves in all analysis angle areas was calculated to obtain the annular outlier value.
6. According to the big data-based smart agriculture cloud platform monitoring system of claim 1, it is characterized in that: The analysis process of the highly outlier value is as follows: Based on the percentage of leaves with pests and diseases, the abnormal plants were divided at equidistant heights to obtain several analysis high areas. The maximum percentage of leaves with pests and diseases in each analysis high area was extracted, and then the standard deviation of the maximum percentage of leaves with pests and diseases in all analysis high areas was calculated to obtain the height abnormality value.
7. The big data-based smart agriculture cloud platform monitoring system according to claim 1 is characterized in that: The process of obtaining the total value of the percentage of leaves with pests and diseases is as follows: Get the number of leaves on each branch of the abnormal plants, marked as the total number of abnormal branches and leaves, and the number of diseased and insect-infested leaves on each branch, marked as the number of branch and trunk diseased and insect-infested leaves, calculate the ratio of the number of branch and trunk diseased and insect-infested leaves to the total number of abnormal branches and trunk leaves, and calculate the sum of the diseased and insect-infested leaf ratios of all branches in the abnormal plants to obtain the total diseased and insect-infested leaf ratio.
8. The big data-based smart agriculture cloud platform monitoring system according to claim 1 is characterized in that: The process of obtaining the annular anomaly growth coefficient is as follows: During the monitoring period, the ring anomaly value at the beginning of the monitoring period and the ring anomaly value at the end of the monitoring period are obtained, which are marked as the starting ring anomaly value and the ending ring anomaly value respectively. The difference between the ending ring anomaly value and the starting ring anomaly value is calculated to obtain the ring anomaly growth coefficient.
9. The big data-based smart agriculture cloud platform monitoring system according to claim 1, characterized in that: The process of obtaining the height abnormal growth coefficient is as follows: During the monitoring period, the height anomaly value at the beginning and the end of the monitoring period are obtained, marked as the starting height anomaly value and the ending height anomaly value respectively, and the difference between the ending height anomaly value and the starting height anomaly value is calculated to obtain the height anomaly growth coefficient.
10. The big data-based smart agriculture cloud platform monitoring system according to claim 1, characterized in that: The process of obtaining the pesticide spraying coefficient in the abnormal growth area is as follows: The growth risk value of each pest control area is marked as ZF i, where i represents the number of pest control areas, and the formula The pesticide spraying coefficient XPi of each pest control area is calculated.
Citation Information
Patent Citations
Agricultural monitoring and early warning method and system based on mobile terminal
CN115938083A
Agricultural disaster monitoring system based on Internet of Things and remote sensing technology
CN117172952A
Crop growth data management decision system based on artificial intelligence
CN117350525A
Intelligent cultivation system and method for irrigation and fertilization of crops
CN118235589A
Band cutting and collection apparatus
KR102400841B1
