Crop disease monitoring method and system based on Internet of Things

Abstract

The invention discloses a crop disease monitoring method and system based on the Internet of Things, and relates to the technical field of crop disease monitoring, and the method comprises the steps: collecting environment data and crop growth data in a farmland through a data collection module of the Internet of Things technology, and collecting and recording information data of related crops infected by diseases, a data processing calculation module is used for sequentially calculating and outputting a disease incidence rate BF, a disease monitoring index BK and a monitoring effect adjustment coefficient BT, a monitoring strategy implementation module is used for executing a monitoring strategy based on the monitoring effect adjustment coefficient BT, any time of monitoring of the system is matched with crop data of the same variety and the same disease type, and the crop data of the same variety and the same disease type is matched with the crop data of the same variety and the same disease type. According to the invention, the monitoring system can more accurately evaluate the disease occurrence condition, optimize and adaptively adjust the monitoring strategy, and improve the monitoring efficiency, thereby providing more comprehensive and accurate support for agricultural production.

Description

Technical Field

[0001] The present invention relates to the technical field of crop disease monitoring, and in particular to a crop disease monitoring method and system based on the Internet of Things. Background Art

[0002] With the rapid development of Internet of Things technology, its application in the agricultural field is becoming more and more extensive. In agricultural production, pests and diseases are important factors affecting crop yield and quality. Therefore, the crop disease monitoring method and system based on the Internet of Things, by integrating sensors, data processing and analysis technology, realizes real-time monitoring and early warning of crop growth environment and disease conditions. The system can collect environmental data and crop growth data in farmland, use advanced algorithms and models to calculate the incidence of diseases, and formulate and implement corresponding monitoring strategies based on the calculation results.

[0003] However, existing crop disease monitoring methods and systems often rely only on a single infection number and simple environmental parameters to assess the incidence of diseases, ignoring the impact of factors such as crop sensitivity to diseases, degree of loss, and speed of disease spread. Existing technologies usually lack a scientific monitoring strategy effectiveness evaluation system, making it difficult to accurately measure the actual effect of monitoring strategies on disease control. In addition, existing technologies often adopt fixed monitoring strategies, which make it difficult to make adaptive adjustments based on real-time changes in disease incidence. Summary of the invention

[0004] The purpose of the present invention is to provide a crop disease monitoring method and system based on the Internet of Things, which solves the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solution, and the specific implementation steps are as follows: Step 1: Use the data collection module of the Internet of Things technology to collect environmental data and crop growth data in the farmland, and at the same time, collect and record relevant information data of crops infected by diseases; Step 2, using the data processing calculation module, sequentially calculate and output the disease incidence rate BF, the disease monitoring index BK, and the monitoring effect adjustment coefficient BT; Step 3, adjusting the coefficient BT based on the monitoring effect, and using the monitoring strategy implementation module to execute the monitoring strategy; Among them, any monitoring and surveillance of the system will match the crop data of the same variety and disease type; The data processing and calculation module includes a unit for comprehensively reflecting the potential impact of diseases on crop growth and yield, a unit for evaluating the effect of disease monitoring strategies, and a unit for adaptively adjusting monitoring strategies; The equipment used in the data collection module includes Internet of Things sensors; The equipment used by the data processing and computing module includes data processing equipment; The equipment used in the monitoring strategy implementation module includes cameras, pesticide spraying devices, and irrigation systems.

[0006] Optionally, the calculation formula for the unit that fully reflects the potential impact of diseases on crop growth and yield is as follows: ; in: BF is the disease incidence rate; GS is the infection number, which reflects the number of crops infected by the disease; M is sensitivity, which reflects the sensitivity of crops to diseases; SS is the degree of loss, which reflects the degree of loss caused by the disease to crops; CB is the spreading rate, which reflects the spreading rate of the disease among crops; BF max is the maximum incidence of the disease, BF max Reflects the maximum disease occurrence probability of the same variety and disease type.

[0007] Optionally, the calculation formula of the sensitivity M is as follows: M=f(BF i , H, BL x ); H=(W max -W)+(S max -S)+(PH max -PH)-(G max -G); BF i is the average disease incidence rate of the i-th crop; H is the environmental index; W max is the maximum temperature, W is the temperature, S max is the maximum humidity, S is the humidity, PH max is the pH, PH is the maximum pH, G max is the maximum light intensity, G is the light intensity; BL x is the average degree of loss of the xth disease type; The calculation formula of the loss degree SS is as follows: SS=CJ / WBC max ; CJ is the reduction in yield, which reflects the reduction in yield caused by the disease; WBC max The maximum yield without disease, WBC maxReflects the maximum yield in the absence of disease; The propagation velocity CB is calculated as follows: CB = g(L, FQ, K); L is the disease spread distance, which reflects the distance from the starting point to the end point of the crop disease; FQ is wind speed; K is the proportion of spatial distribution of crops, and K reflects the proportion of crop planting area to the total area.

[0008] Optionally, the calculation formula for evaluating the disease monitoring strategy effect unit is as follows: ; in: BK is the disease monitoring index; JY is the monitoring strategy effectiveness index; JY max is the maximum effective index of the monitoring strategy, JY max It reflects the maximum effect value of the system monitoring the same variety and disease type of crops and taking corresponding strategies to reduce the disease.

[0009] Optionally, the calculation formula of the monitoring strategy effectiveness index JY is as follows: JY=(BF before -BF after ) / BF after ×JY max ; BF before is the disease incidence before the strategy; BF after is the disease incidence rate after the strategy.

[0010] Optionally, the calculation formula of the adaptive adjustment monitoring strategy unit is as follows: ; in: BT is the monitoring effect adjustment coefficient; Z is the monitoring accuracy; GS max is the maximum number of infections; GS max Reflects the maximum number of crops of the same variety and disease type infected.

[0011] Optionally, the crops of the same variety and disease type that are infected and detected by the system are recorded as 1, and the crops of the same variety and disease type that are infected and not detected by the system are recorded as -1. The calculation formula of the monitoring accuracy Z is as follows: Z=(ZQ 1 +ZQ 2+ZQ 3 +......+ZQ n ) / n; n is the total number of monitoring records, which reflects the total number of times crops of the same variety and disease type are monitored and calculated by the system, and is recorded as 1 and -1 accordingly; ZQ 1 is the first monitoring count, ZQ 2 For the second monitoring count, ZQ 3 For the third monitoring count, ZQ n Counts the nth monitoring.

[0012] Optionally, the analysis and adjustment strategy based on the monitoring effect adjustment coefficient BT and the monitoring effect adjustment coefficient BT of crops of the same variety and disease type monitored by the system last time is as follows: If the current monitoring effect adjustment coefficient BT is higher than the monitoring effect adjustment coefficient BT of the last system monitoring, it means that the current monitoring strategy is effective, the disease incidence rate BF is reduced, and the threshold of the sensitivity M should be lowered to reduce false alarms; If the current monitoring effect adjustment coefficient BT is lower than the monitoring effect adjustment coefficient BT of the previous system monitoring, it means that the current monitoring strategy is not effective enough, the disease propagation speed CB is fast, and the weight of the propagation speed CB should be increased to respond to the current disease spread.

[0013] Optionally, based on the result value of the disease incidence rate BF and the loss degree SS of the unit that comprehensively reflects the potential impact of the disease on the growth and yield of crops, the number of disease incidence rates BF and loss degrees SS of crops of the same variety and disease type that have occurred is accumulated, and the average disease incidence rate BF of the i-th crop is calculated. i The calculation formula is as follows: BF i =(BF 1 +BF 2 +BF 3 +......+BF m ) / m; m is the cumulative total, and m reflects the total number of disease incidence rates BF of crops of the same variety and disease type that have occurred; BF 1 is the first cumulative disease incidence, BF 2 is the second cumulative disease incidence, BF 3 is the third cumulative disease incidence, BF m is the mth cumulative disease incidence rate; The average loss degree of the x-th disease type BL x The calculation formula is as follows: BL x =(BL 1+BL 2 +BL 3 +......+BL m ) / m; m is the cumulative total, which reflects the total number of losses SS of crops of the same variety and disease type that have occurred; BL 1 is the first cumulative loss level, BL 2 is the second cumulative loss level, BL 3 The third cumulative loss level, BL m is the mth cumulative loss level.

[0014] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention comprehensively reflects the potential impact units of diseases on crop growth and yield, and comprehensively introduces the influence of infection quantity GS, sensitivity M, loss degree SS, and transmission speed CB on disease incidence rate BF, thereby realizing accurate calculation of disease incidence rate BF, which helps to understand the disease status in time, provides a scientific basis for formulating effective monitoring strategies, and reduces false alarms and missed alarms caused by inaccurate calculations.

[0015] 2. The disease monitoring strategy effectiveness evaluation unit of the present invention provides quantitative indicators for evaluating the effectiveness of the monitoring strategy by introducing the effectiveness of the monitoring strategy and the disease monitoring index BK, thereby being able to objectively evaluate the actual effect of the monitoring strategy, promptly discover and improve deficiencies, and improve the overall effectiveness of the monitoring system.

[0016] 3. The adaptive adjustment monitoring strategy unit of the present invention realizes flexible adjustment of the monitoring strategy by calculating the monitoring effect adjustment coefficient BT, and can dynamically adjust the threshold of the sensitivity M or the weight of the propagation speed CB according to the value of BT to adapt to the actual situation of the disease change. This adaptive adjustment mechanism improves the response speed and accuracy of the monitoring system, making the monitoring strategy more accurate and effective.

[0017] 4. The present invention forms a closed-loop system by closely combining a unit for comprehensively reflecting the potential impact of diseases on crop growth and yield, a unit for evaluating the effectiveness of disease monitoring strategies, and a unit for adaptively adjusting monitoring strategies. This system can adaptively adjust the monitoring strategy and dynamically optimize it according to the real-time changes in the disease incidence rate BF, thereby improving the accuracy and efficiency of disease monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A method flow chart of the crop disease monitoring method and system based on the Internet of Things; Figure 2 This is a schematic diagram of the overall structural module of the crop disease monitoring method and system based on the Internet of Things; Figure 3 It is a structural schematic diagram of the data processing and calculation module of the present invention; Figure 4 Schematic diagram of adaptive feedback adjustment under monitoring according to the present invention. DETAILED DESCRIPTION

[0019] 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.

[0020] Regarding this crop disease monitoring method and system based on the Internet of Things, it is different from the existing crop disease monitoring methods and systems. The existing crop disease monitoring methods and systems ignore the influence of factors such as the sensitivity of crops to diseases, the degree of loss, and the speed of disease transmission, lack a scientific monitoring strategy effectiveness evaluation system, and it is difficult to make adaptive adjustments based on real-time changes in disease incidence. This algorithm unit enables the monitoring system to more accurately evaluate the occurrence of diseases, optimize and adaptively adjust monitoring strategies, and improve monitoring efficiency, thereby providing more comprehensive and accurate support for agricultural production.

[0021] For example, see Figures 1 to 4 This implementation provides a crop disease monitoring method and system based on the Internet of Things. The specific implementation steps are as follows: Step 1: Use the data collection module of the Internet of Things technology to collect environmental data and crop growth data in the farmland, and at the same time, collect and record relevant information data of crops infected by diseases; Step 2, using the data processing calculation module, sequentially calculate and output the disease incidence rate BF, the disease monitoring index BK, and the monitoring effect adjustment coefficient BT; Step 3, adjusting the coefficient BT based on the monitoring effect, and using the monitoring strategy implementation module to execute the monitoring strategy; Among them, any monitoring and surveillance of the system will match the crop data of the same variety and disease type; The data processing and calculation module includes a unit that comprehensively reflects the potential impact of diseases on crop growth and yield, a unit that evaluates the effectiveness of disease monitoring strategies, and a unit that adaptively adjusts monitoring strategies; The devices used in the data collection module include IoT sensors; The equipment used in the data processing and computing module includes data processing equipment; The equipment used in the monitoring strategy implementation module includes cameras, pesticide spraying devices, and irrigation systems.

[0022] In this embodiment, the system, through the mutual cooperation of three algorithm units, together constitutes the core architecture of the crop disease monitoring method and system based on the Internet of Things. Combining the three operation results of BF, BK and BT, BF is the disease incidence rate. The high or low BF value directly reflects the severity of the disease, which provides an important scientific basis for subsequent monitoring and prevention work. By calculating the BF value, the occurrence of the disease can be understood in time, so as to take targeted prevention and control measures to reduce the loss of crops caused by the disease. BK is the disease monitoring index, which can quantitatively evaluate the actual effect of the monitoring measures. When the BK value is high, it means that the monitoring measures are effective and the disease is well controlled. When the BK value is low, it means that the monitoring measures are ineffective. The shortcomings and needs to be improved. By calculating the MBK value, the monitoring strategy can be discovered and optimized in time to improve the accuracy and efficiency of disease monitoring. BT is the monitoring effect adjustment coefficient, which can realize flexible adjustment of the monitoring strategy. By calculating the BTC value, the parameter setting of the monitoring strategy is continuously optimized to improve the adaptability and robustness of the disease monitoring system. The calculation results of BT can also affect the calculation of BF and BK, so that the three algorithms of this system together constitute a closed-loop system. Through mutual correlation and mutual influence, a comprehensive evaluation of the occurrence of diseases, a quantitative evaluation of the effectiveness of monitoring measures, and adaptive adjustment of monitoring strategy parameters are realized. This system provides strong technical support and scientific basis for crop disease monitoring.

[0023] See also Figures 1 to 4 , the calculation formula for the unit that fully reflects the potential impact of diseases on crop growth and yield is as follows: ; in: BF is the disease incidence rate; GS is the infection number, which reflects the number of crops infected by the disease; M is sensitivity, which reflects the sensitivity of crops to diseases; SS is the degree of loss, which reflects the degree of loss caused by the disease to crops; CB is the spreading rate, which reflects the spreading rate of the disease among crops; BF max is the maximum incidence of the disease, BF max Reflects the maximum probability of disease occurrence for the same variety and disease type; The calculation formula of sensitivity M is as follows: M=f(BF i , H, BL x ); H=(W max -W)+(S max -S)+(PH max -PH)-(Gmax -G); BF i is the average disease incidence rate of the i-th crop; H is the environmental index; W max is the maximum temperature, W is the temperature, S max is the maximum humidity, S is the humidity, PH max is the pH, PH is the maximum pH, G max is the maximum light intensity, G is the light intensity; BL x is the average degree of loss of the xth disease type; Based on the disease incidence rate BF and the loss degree SS, the number of disease incidence rates BF and loss degrees SS of crops of the same variety and disease type that have occurred is accumulated, and the average incidence rate BF of the i-th crop is i The calculation formula is as follows: BF i =(BF 1 +BF 2 +BF 3 +......+BF m ) / m; m is the cumulative total, and m reflects the total number of disease incidence rates BF of crops of the same variety and disease type that have occurred; BF 1 is the first cumulative disease incidence, BF 2 is the second cumulative disease incidence, BF 3 is the third cumulative disease incidence, BF m is the mth cumulative disease incidence rate; Average loss degree of x-th disease type BL x The calculation formula is as follows: BL x =(BL 1 +BL 2 +BL 3 +......+BL m ) / m; m is the cumulative total, which reflects the total number of losses SS of crops of the same variety and disease type that have occurred; BL 1 is the first cumulative loss level, BL 2 is the second cumulative loss level, BL 3 The third cumulative loss level, BL m is the mth cumulative loss level; The calculation formula of loss degree SS is as follows: SS=CJ / WBC max ; CJ is the reduction in yield, which reflects the reduction in yield caused by the disease; WBC max The maximum yield without disease, WBC max Reflects the maximum yield in the absence of disease; The propagation velocity CB is calculated as follows: CB = g(L, FQ, K); L is the disease spread distance, which reflects the distance from the starting point to the end point of the crop disease; FQ is wind speed; K is the proportion of spatial distribution of crops, and K reflects the proportion of crop planting area to the total area.

[0024] In this embodiment: First, the calculation part of "GS×M" in this algorithm unit calculates the comprehensive impact based on the infection number GS and the crop's sensitivity to the disease M. It reflects the direct contribution of the infection number GS to the disease incidence under a specific sensitivity M. As part of the BF calculation, it helps to combine the two factors of infection number GS and sensitivity M to jointly affect the final disease incidence BF, and a high infection number GS and sensitivity M will lead to a higher disease incidence BF. The "SS×CB" part calculates the comprehensive impact of the disease loss degree SS and the transmission speed CB, which reflects the speed at which the disease spreads among crops and the resulting loss degree. Also as part of the BF calculation, it takes into account the disease loss degree SS and the transmission speed CB. These two factors jointly determine the degree of impact of the disease on the overall health of the crop, and a fast transmission speed CB and a high loss degree SS will lead to a higher disease incidence BF. The algorithm comprehensively reflects the potential impact of diseases on crop growth and yield. The unit introduces the direct infection number GS and sensitivity M parameters of the disease, which reflects the susceptibility of crops to diseases. At the same time, the addition of loss degree SS and transmission speed CB enables the formula to more comprehensively evaluate the potential impact of diseases on crop growth and yield. This comprehensiveness helps managers to have a more comprehensive understanding of the disease status and thus formulate more comprehensive prevention and control strategies. Among them, this algorithm unit introduces sensitivity M and loss degree SS, so that the unit that comprehensively reflects the potential impact of diseases on crop growth and yield can more accurately assess the impact of diseases on crops. The level of sensitivity M directly determines the degree of harm of diseases to crops, while the loss degree SS reflects the actual impact of diseases on crop yields. The addition of these two parameters makes the calculation of disease incidence BF closer to reality, providing a more accurate scientific basis for subsequent monitoring and prevention. The parameters in the unit that comprehensively reflects the potential impact of diseases on crop growth and yield are adjusted and optimized according to actual conditions. For example, for different types of crops and different types of diseases, the sensitivity M and the propagation speed CB will be different. By adjusting the values ​​of these parameters, the unit that comprehensively reflects the potential impact of diseases on crop growth and yield can adapt to the monitoring needs of different crops and different diseases, making the monitoring system more flexible and practical.

[0025] See also Figures 1 to 4 , the calculation formula for evaluating the effectiveness unit of disease monitoring strategy is as follows: ; in: BK is the disease monitoring index; JY is the monitoring strategy effectiveness index; JY max is the maximum effective index of the monitoring strategy, JY max It reflects the maximum effect value of the system monitoring the same variety and disease type of crops and taking corresponding strategies to reduce the disease; The calculation formula of the monitoring strategy effectiveness index JY is as follows: JY=(BF before -BF after ) / BF after ×JY max ; BF before is the disease incidence before the strategy; BF after is the disease incidence rate after the strategy.

[0026] In this embodiment, first, "The calculation part calculates the residual effect of the disease incidence rate BF after considering the effectiveness of the monitoring strategy. It reflects the part of the disease incidence rate BF that still exists after the monitoring strategy is adopted. As the main part of the BK calculation, it takes into account the inhibitory effect of the monitoring strategy on the disease incidence rate. By subtracting the part reduced by the monitoring strategy from BF, the actual effect of the monitoring strategy can be evaluated." "The calculation part calculates the relative relationship between the loss level SS, sensitivity M and infection number GS. It reflects the relative contribution of the loss level SS and sensitivity M to the disease monitoring effect under a specific infection number GS. As another part of the BK calculation, it provides an adjustment item to consider the complex relationship between the loss level SS, sensitivity M and infection number GS. This adjustment item helps to more comprehensively evaluate the effect of disease monitoring; This algorithm unit provides a quantitative indicator for the disease monitoring effect through BK, and can objectively evaluate the actual effect of the monitoring strategy. By comparing the BK values ​​at different time points, the implementation effect of the monitoring strategy can be clearly seen, so that the monitoring strategy can be adjusted and optimized in time. And through the feedback of BK, the shortcomings of the monitoring strategy can be discovered and improved in time. Specifically, when the BK value is low, it means that the current monitoring strategy is not effective enough and there are some loopholes. At this time, according to the feedback results of BK, the monitoring strategy is adjusted and optimized to improve the overall effectiveness of the monitoring system; The early warning function of BK provides timely disease monitoring information. When the BK value is lower than a certain threshold, the system can automatically send out an early warning signal to remind timely response strategies. This early warning function helps to adopt effective prevention and control strategies in the early stages of the disease, thereby avoiding further spread and harm of the disease.

[0027] See also Figures 1 to 4 , the calculation formula for adaptively adjusting the monitoring strategy unit is as follows: ; in: BT is the monitoring effect adjustment coefficient; Z is the monitoring accuracy; GS max is the maximum number of infections; GS max Reflects the maximum number of crops of the same variety and disease type infected; Crops of the same variety and disease type that are infected and detected by the system are recorded as 1, and crops of the same variety and disease type that are infected but not detected by the system are recorded as -1. The calculation formula of the monitoring accuracy Z is as follows: Z=(ZQ 1 +ZQ 2 +ZQ 3 +......+ZQ n ) / n; n is the total number of monitoring records, which reflects the total number of times crops of the same variety and disease type are monitored and calculated by the system, and is recorded as 1 and -1 accordingly; ZQ 1 is the first monitoring count, ZQ 2 For the second monitoring count, ZQ 3 For the third monitoring count, ZQ n Counts the nth monitoring.

[0028] In this embodiment, the algorithm unit first " "The calculation part calculates the contribution of the disease monitoring index BK to the monitoring effect adjustment coefficient BT after considering the normalization of the infection number GS. It reflects the relative importance of the disease monitoring index BK to the monitoring effect adjustment under a specific infection number GS. As part of the BT calculation, it combines the normalized values ​​of the disease monitoring index BK and the infection number GS to jointly affect the final monitoring effect adjustment coefficient BT. This calculation part helps to adjust the effectiveness of the monitoring strategy according to the actual situation of disease monitoring." "The calculation part calculates the relative relationship between the disease incidence rate BF, the monitoring accuracy rate Z and the transmission speed CB. It reflects the relative contribution of the disease incidence rate BF and the monitoring accuracy rate Z to the adjustment of the monitoring effect under a specific transmission speed CB. As another part of the BT calculation, it provides an adjustment item to consider the complex relationship between the disease incidence rate BF, the monitoring accuracy rate Z and the transmission speed CB. This adjustment item helps to more accurately evaluate the effectiveness of the monitoring strategy and make adjustments based on actual conditions. This algorithm unit can adaptively adjust the monitoring strategy according to the changes of the disease monitoring index BK and the disease incidence BF parameters through BT. When the BK value and BF value change, BT can quickly respond and adjust the parameter settings of the monitoring strategy to ensure the accuracy and effectiveness of the monitoring system. This adaptive adjustment mechanism enables the monitoring system to continuously adapt to changes in the occurrence of diseases and improve the response speed and accuracy of the monitoring system. The introduction of BT in this algorithm unit enables the monitoring system to respond to disease spread more quickly and adopt effective monitoring strategies. By continuously optimizing and adjusting the parameter settings of the monitoring strategy, the monitoring system can more accurately locate the disease occurrence area and the degree of infection, thereby adopting more effective prevention and control strategies. This method of improving monitoring efficiency helps reduce the impact of diseases on crop growth and yield, and improve agricultural production efficiency.

[0029] For example 2, please refer to Figures 1 to 4 The analysis and adjustment strategy based on the monitoring effect adjustment coefficient BT and the monitoring effect adjustment coefficient BT of crops of the same variety and disease type monitored by the previous system is as follows: If the current monitoring effect adjustment coefficient BT is higher than the monitoring effect adjustment coefficient BT of the last system monitoring, it means that the current monitoring strategy is effective, the disease incidence rate BF is reduced, and the threshold of the sensitivity M should be lowered to reduce false alarms; If the current monitoring effect adjustment coefficient BT is lower than the monitoring effect adjustment coefficient BT of the previous system monitoring, it means that the current monitoring strategy is not effective enough, the disease propagation speed CB is fast, and the weight of the propagation speed CB should be increased to respond to the current disease spread.

[0030] In this embodiment, when the monitoring effect adjustment coefficient BT is high, it means that the current monitoring strategy is effective and the disease is well controlled. At this time, the threshold of the sensitivity M is appropriately lowered to reduce the system's oversensitivity to minor signs of disease, thereby reducing the false alarm rate. After lowering the threshold of the sensitivity M, the system can focus more on serious disease conditions while ensuring accuracy, issue warnings in a timely manner and take corresponding strategies, which helps to improve monitoring efficiency and ensure that crop diseases are controlled in a timely and effective manner. When the monitoring effect adjustment coefficient BT is low, it means that the current monitoring strategy is not effective enough and the disease propagation speed CB is fast. At this time, the weight of the propagation speed CB is increased, so that the system pays more attention to the disease propagation dynamics, issues warnings in a timely manner and takes corresponding strategies, thereby curbing the spread of the disease. By adjusting the weight of the propagation speed CB, the system can allocate monitoring resources more reasonably, ensure that monitoring resources are fully utilized, and improve the overall efficiency of the monitoring system. This embodiment adjusts the calculation and feedback mechanism of the monitoring strategy unit adaptively, and continuously adjusts the parameter settings in the unit that fully reflects the potential impact of diseases on crop growth and yield to optimize the calculation accuracy of disease incidence. This dynamic optimization mechanism enables the monitoring system to continuously adapt to changes in disease occurrence and optimize its performance. With the operation of the monitoring system and the accumulation of data, this dynamic optimization process will continue to iterate and improve, making the monitoring system more in line with the actual disease occurrence and improving its prediction and prevention capabilities. With the operation of the monitoring system and the accumulation of data, the adaptive monitoring strategy unit can continuously feedback the monitoring effect information and further improve the accuracy of the disease incidence BF calculation by adjusting the parameters in the unit that fully reflects the potential impact of diseases on crop growth and yield. This method of improving accuracy helps to reduce the occurrence of false alarms and missed alarms caused by calculation errors, thereby improving the reliability and practicality of the monitoring system. By adaptively adjusting the monitoring strategy unit to fully reflect the cyclic impact mechanism of the disease on the potential impact unit of crop growth and yield, the monitoring system can better cope with various complex situations such as sudden outbreaks of diseases and changes in the propagation speed CB. This way of enhancing robustness enables the monitoring system to maintain its stability and reliability when facing uncertainty and risks, thereby ensuring the safety and sustainable development of agricultural production. At the same time, this way of enhancing robustness also helps to improve the adaptability and scalability of the monitoring system, so that it can better adapt to new situations and new challenges that may arise in future agricultural production. In summary, the unit that comprehensively reflects the potential impact of diseases on crop growth and yield, the unit that evaluates the effectiveness of disease monitoring strategies, and the unit that adaptively adjusts monitoring strategies each have clear calculation purposes and important significance. They together constitute a closed-loop system. Through mutual correlation and mutual influence, a comprehensive evaluation of disease occurrence, a quantitative evaluation of the effectiveness of monitoring measures, and adaptive adjustment of monitoring strategy parameters are achieved. This system provides strong technical support and scientific basis for crop disease monitoring.

[0031] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method and system for monitoring crop diseases based on the Internet of Things, characterized in that: The specific implementation steps are as follows: Step 1: Use the data collection module of the Internet of Things technology to collect environmental data and crop growth data in the farmland, and at the same time, collect and record relevant information data of crops infected by diseases; Step 2, using the data processing calculation module, sequentially calculate and output the disease incidence rate BF, the disease monitoring index BK, and the monitoring effect adjustment coefficient BT; Step 3, adjusting the coefficient BT based on the monitoring effect, and using the monitoring strategy implementation module to execute the monitoring strategy; Among them, any monitoring and detection by the system will match the crop data of the same variety and disease type.

2. A method and system for monitoring crop diseases based on the Internet of Things according to claim 1, characterized in that: The data processing and calculation module includes a unit for comprehensively reflecting the potential impact of diseases on crop growth and yield, a unit for evaluating the effect of disease monitoring strategies, and a unit for adaptively adjusting monitoring strategies.

3. The method and system for monitoring crop diseases based on the Internet of Things according to claim 2, characterized in that: The equipment used in the data collection module includes Internet of Things sensors; The equipment used by the data processing and computing module includes data processing equipment; The equipment used in the monitoring strategy implementation module includes cameras, pesticide spraying devices, and irrigation systems.

4. The method and system for monitoring crop diseases based on the Internet of Things according to claim 3, characterized in that: The calculation formula for the unit that fully reflects the potential impact of diseases on crop growth and yield is as follows: ； in: BF is the disease incidence rate; GS is the infection number, which reflects the number of crops infected by the disease; M is sensitivity, which reflects the sensitivity of crops to diseases; SS is the degree of loss, which reflects the degree of loss caused by the disease to crops; CB is the spreading rate, which reflects the spreading rate of the disease among crops; BF max is the maximum incidence of the disease, BF max Reflects the maximum probability of disease occurrence for the same variety and disease type; The calculation formula of the sensitivity M is as follows: M=f(BF i ,H,BL x ); H=(W max -W)+(S max -S)+(PH max -PH)-(G max -G); BF i is the average disease incidence rate of the i-th crop; H is the environmental index; W max is the maximum temperature, W is the temperature, S max is the maximum humidity, S is the humidity, PH max is the pH, PH is the maximum pH, G max is the maximum light intensity, G is the light intensity; BL x is the average degree of loss of the xth disease type; The calculation formula of the loss degree SS is as follows: SS=CJ / WBC max ; CJ is the reduction in yield, which reflects the reduction in yield caused by the disease; WBC max The maximum yield without disease, WBC max Reflects the maximum yield in the absence of disease; The propagation velocity CB is calculated as follows: CB = g(L, FQ, K); L is the disease spread distance, which reflects the distance from the starting point to the end point of the crop disease; FQ is wind speed; K is the spatial distribution ratio of crops, and K reflects the ratio of crop planting area to total area; The calculation formula for evaluating the disease monitoring strategy effect unit is as follows: ； in: BK is the disease monitoring index; JY is the monitoring strategy effectiveness index; JY max is the maximum effective index of the monitoring strategy, JY max It reflects the maximum effect value of the system monitoring the same variety and disease type of crops and taking corresponding strategies to reduce the disease.

5. The method and system for monitoring crop diseases based on the Internet of Things according to claim 4, characterized in that: The calculation formula of the monitoring strategy effectiveness index JY is as follows: YOU=(BF before -BF after ) / BF after ×YOU max ; BF before is the disease incidence before the strategy; BF after is the disease incidence rate after the strategy.

6. The method and system for monitoring crop diseases based on the Internet of Things according to claim 5, characterized in that: The calculation formula of the adaptive adjustment monitoring strategy unit is as follows: ； in: BT is the monitoring effect adjustment coefficient; Z is the monitoring accuracy; GS max is the maximum number of infections; GS max Reflects the maximum number of crops of the same variety and disease type infected.

7. The method and system for monitoring crop diseases based on the Internet of Things according to claim 6, characterized in that: The crops of the same variety and disease type that are infected and detected by the system are recorded as 1, and the crops of the same variety and disease type that are infected and not detected by the system are recorded as -1. The calculation formula of the monitoring accuracy Z is as follows: Z=(ZQ1+ZQ2+ZQ3+……+ZQ n ) / n; n is the total number of monitoring records, which reflects the total number of times crops of the same variety and disease type are monitored and calculated by the system, and is recorded as 1 and -1 accordingly; ZQ1 is the first monitoring count, ZQ2 is the second monitoring count, ZQ3 is the third monitoring count, and ZQ n Counts the nth monitoring.

8. The method and system for monitoring crop diseases based on the Internet of Things according to claim 7, characterized in that: The analysis and adjustment strategy based on the monitoring effect adjustment coefficient BT and the monitoring effect adjustment coefficient BT of the same variety and disease type of crops monitored by the previous system is as follows: If the current monitoring effect adjustment coefficient BT is higher than the monitoring effect adjustment coefficient BT of the last system monitoring, it means that the current monitoring strategy is effective, the disease incidence BF is reduced, and the threshold of the sensitivity M should be lowered to reduce false alarms; If the current monitoring effect adjustment coefficient BT is lower than the monitoring effect adjustment coefficient BT of the previous system monitoring, it means that the current monitoring strategy is not effective enough, the disease propagation speed CB is fast, and the weight of the propagation speed CB should be increased to respond to the current disease spread.

9. The method and system for monitoring crop diseases based on the Internet of Things according to claim 4, characterized in that: Based on the result value of the unit that comprehensively reflects the potential impact of diseases on crop growth and yield, the disease incidence rate BF and the loss degree SS therein, the number of disease incidence rates BF and loss degrees SS of crops of the same variety and disease type that have occurred is accumulated, and the average disease incidence rate BF of the i-th crop is i The calculation formula is as follows: BF i =(BF1+BF2+BF3+......+BF m ) / m; m is the cumulative total, and m reflects the total number of disease incidence rates BF of crops of the same variety and disease type that have occurred; BF1 is the first cumulative disease incidence, BF2 is the second cumulative disease incidence, BF3 is the third cumulative disease incidence, BF m is the mth cumulative disease incidence rate; The average loss degree of the x-th disease type BL x The calculation formula is as follows: <h2 style=";text-align:left;direction:ltr">BL<h2 style=";text-align:left;direction:ltr"> x <h2 style=";text-align:left;direction:ltr"> =(BL1+BL2+BL3+......+BL<h2 style=";text-align:left;direction:ltr"> m <h2 style=";text-align:left;direction:ltr"> ) / m; m is the cumulative total, which reflects the total number of losses SS of crops of the same variety and disease type that have occurred; BL1 is the first cumulative loss level, BL2 is the second cumulative loss level, BL3 is the third cumulative loss level, and BL m is the mth cumulative loss level.

Images