Early warning system for forest plant diseases and insect pests

By obtaining and analyzing seasonal and regional natural information, calculating the probability interval of pests and diseases, and performing hierarchical early warnings, the problem of lack of climatic conditions early warnings in the existing technology is solved, the scientificity and credibility of early warnings are improved, and the pest and diseases zones are reduced economic and ecological losses.

CN118968323AInactive Publication Date: 2024-11-15HUIMEI (ANSHAN) AGRI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411463757.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-10-21
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The lack of early warnings for forest pests and diseases based on climatic conditions in the prior art leads to lack of priori and large errors in the early warning, which affects the accuracy of the system.

Method used

By obtaining seasonal and regional natural information, calculating temperature change rate and precipitation mutations, setting label groups and calculating pest and disease probability intervals, performing hierarchical early warnings, and dynamically adjusting the early warning strategy.

Benefits of technology

It enhances the scientificity and credibility of early warnings, helps managers quickly identify high-risk areas, optimize resource allocation, reduce potential losses, improve response efficiency, and achieve tiered early warning and flexible emergency management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118968323A_ABST
    Figure CN118968323A_ABST
Patent Text Reader

Abstract

The invention, which relates to the technical field of data processing, discloses an early warning system for forest plant diseases and insect pests, comprising an acquisition module, an analysis module and an early warning module, calculating the plant disease and insect pest probability corresponding to each label, and calculating the plant disease and insect pest probability interval corresponding to each label; and establishing a first mapping relationship between the label group and the pest and disease damage probability interval corresponding to the label group, and performing graded early warning according to a season ascending sorting result. According to the method, scientific decision making is enhanced by obtaining seasonal and regional natural information, potential loss is reduced by calculating the temperature change rate and the rainfall sudden change amount, optimizing resource allocation and matching a pest and disease damage record with a label group, the pest and disease damage probability and the confidence interval are calculated based on statistical analysis, the credibility of early warning information is enhanced, and the early warning efficiency is improved. The system can realize graded early warning, enhances the flexibility and effectiveness of emergency management, synthesizes natural information and pest and disease damage records, constructs a scientific and effective early warning mechanism, and reduces economic loss and ecological influence caused by pest and disease damage.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of data processing, and in particular to an early warning system for forest pests and diseases. Background Art

[0002] In recent years, the development of early warning of forest pests and diseases is moving towards technology, intelligence and systematization. An early warning system based on data analysis has been established to provide real-time risk assessment of pests and diseases to forestry managers, deploy sensors for soil, climate and plant growth status, monitor environmental changes in real time, predict the risk of pests and diseases, apply machine learning algorithms to analyze historical data, establish prediction models, and improve the early warning capabilities of pests and diseases.

[0003] At present, a Chinese invention patent with publication number CN 118334582 A discloses a digital monitoring and early warning method and system for pests and diseases. This method uses a graph convolutional network algorithm to construct a graph model of crop leaves, effectively captures the complex spatial relationship between leaves, and improves the recognition of pest and disease image features. The variational autoencoder provides an efficient image potential representation learning method in anomaly detection, which significantly improves the recognition rate. However, the related technology does not provide early warning of pests and diseases based on climatic conditions, lacks a priori warning, and is prone to cause tree damage. There is no compensation for prediction errors, which is not conducive to the accuracy of the system. Summary of the invention

[0004] The technical problem solved by the present invention is that the related technology does not provide early warning of pests and diseases according to climatic conditions, lacks the a priori nature of the warning, easily causes damage to trees, does not compensate for the prediction error, and is not conducive to the accuracy of the system.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an early warning system for forest pests and diseases, comprising an acquisition module, an analysis module and an early warning module; The acquisition module sets a season segmentation temperature, obtains a test spring and a test autumn according to the season segmentation temperature, obtains the duration of the test spring and the duration of the test autumn, obtains the name of the region where the tree is located, and matches the natural information of the region name within the duration of the test spring and the duration of the test autumn according to the name of the region where the tree is located; The analysis module calculates the average temperature change rate and precipitation mutation amount according to natural information, sets a temperature label according to the average temperature change rate, sets a precipitation label according to the precipitation mutation amount, sets a spring label and an autumn label according to the experimental spring duration and the experimental autumn duration, combines the labels to obtain a label group, obtains the pest and disease records within the experimental spring duration and the experimental autumn duration, obtains the label group corresponding to the pest and disease records, counts the number of occurrences of each label group corresponding to the pest and disease records, and records the number of occurrences of each label when no pest and disease records occur within the experimental spring duration and the experimental autumn duration, and records the number of occurrences of each label as the second number, calculates the pest and disease probability corresponding to each label according to the first number and the second number, and calculates the pest and disease probability interval corresponding to each label according to the confidence interval formula; The early warning module sorts the upper limits of the probability intervals of pests and diseases with the same season label in ascending order to obtain a seasonal ascending sorting result, establishes a first mapping relationship between the label group and the probability intervals of pests and diseases corresponding to the label group, and performs graded early warning according to the seasonal ascending sorting result.

[0006] As a preferred solution of the forest pest early warning system described in the present invention, the acquisition module sets a season segmentation temperature, the season segmentation temperature includes a spring segmentation temperature and an autumn segmentation temperature, and the setting logic of the season segmentation temperature includes: Obtain spring temperature and winter temperature, calculate the average value of spring temperature and the average value of winter temperature respectively, calculate the first sum of the average value of spring temperature and the average value of winter temperature, and set half of the first sum as spring split temperature; Obtaining the summer temperature and the autumn temperature, respectively calculating the average of the summer temperature and the average of the autumn temperature, calculating the second sum of the average of the summer temperature and the average of the autumn temperature, and setting half of the second sum as the autumn split temperature; According to the seasonal split temperature division, the test spring and test autumn are obtained, the time period from the spring split temperature to the average value of the summer temperature is set as the test spring, and the time period from the autumn split temperature to the average value of the winter temperature is set as the test autumn, and the test spring duration and test autumn duration are obtained respectively; Get the name of the region where the tree is located, call the climate database, input the region name into the climate database, match the corresponding natural information according to the region name, filter the natural information within the experimental spring period and the experimental autumn period as the information to be analyzed, and delete the remaining natural information, the natural information includes temperature and precipitation, the temperature is expressed as the temperature of a natural day, and the precipitation is expressed as the precipitation of a natural day.

[0007] As a preferred solution of the forest pest early warning system described in the present invention, the analysis module calculates the average temperature change rate and the precipitation mutation amount according to natural information, and the calculation logic of the average temperature change amount includes: Obtain the temperature in the information to be analyzed in the spring of the experiment or the temperature in the information to be analyzed in the autumn of the experiment, record it as the temperature to be analyzed, calculate the change rate of adjacent temperatures to be analyzed, calculate the average value of the change rates of adjacent temperatures to be analyzed, record it as the average temperature change rate, wherein the adjacent temperatures to be analyzed are represented as the temperatures of adjacent natural days in the time sequence; The calculation logic of the precipitation mutation amount includes: The temperature in the information to be analyzed in the spring of the experiment or the precipitation in the information to be analyzed in the autumn of the experiment is obtained, recorded as the precipitation to be analyzed, the difference between adjacent precipitations to be analyzed is calculated, and the difference between adjacent precipitations to be analyzed is set as the precipitation mutation amount.

[0008] As a preferred solution of the early warning system for forest pests and diseases described in the present invention, wherein: the analysis module sets a temperature label according to the average temperature change rate, sets a precipitation label according to the amount of precipitation mutation, sets a spring label and an autumn label according to the length of the experimental spring and the length of the experimental autumn, the temperature label includes large temperature change and normal temperature change, the precipitation label includes precipitation mutation and no precipitation mutation, the spring label includes long spring time, short spring time and normal spring time, and the autumn label includes long autumn time, short autumn time and normal autumn time; The setting logic of the temperature label includes setting the first value as the upper limit of the average temperature change rate, comparing the average temperature change rate with the first value, and when the average temperature change rate is greater than the first value, setting the temperature label to indicate a large temperature change, otherwise, setting the temperature label to indicate a large temperature change or a normal temperature change; The setting logic of the precipitation label includes: setting the second value as the upper limit of the precipitation difference, comparing the precipitation mutation amount with the second value, and when the precipitation mutation amount is greater than the second value, setting the precipitation label to precipitation mutation, otherwise, setting the precipitation label to precipitation no mutation; The setting logic of the spring label includes: obtaining the time period between the vernal equinox date and the summer solstice date, recording it as the first standard time period, comparing the test spring duration with the first standard time period, when the test spring duration is greater than the first standard time period, setting the spring label to long spring time, when the test spring duration is less than the first standard time period, setting the spring label to short spring time, and when the test spring duration is equal to the first standard time period, setting the spring label to normal spring time.

[0009] As a preferred solution of the forest pest early warning system described in the present invention, the setting logic of the autumn label includes: obtaining the time period between the autumnal equinox date and the winter solstice date, recording it as the second standard time period, comparing the test autumn duration with the second standard time period, when the test autumn duration is greater than the second standard time period, setting the autumn label to a long spring time, when the test autumn duration is less than the second standard time period, setting the autumn label to a short autumn time, and when the test autumn duration is equal to the second standard time period, setting the autumn label to a normal autumn time; Set long spring time to X1, short spring time to X2, normal spring time to X3, long autumn time to Y1, short autumn time to Y2, normal autumn time to Y3, large temperature change to M1, normal temperature change to M2, sudden precipitation change to N1, and no sudden precipitation change to N2.

[0010] As a preferred solution of the forest pest early warning system of the present invention, the analysis module combines the spring label or the autumn label, the corresponding temperature label and the corresponding precipitation label to obtain a label group, which is represented by X MN or Y MN , which means that if one of the X elements is selected, the sum of the M and N elements is at least 1, or if one of the Y elements is selected, the sum of the M and N elements is at least 1; Obtain pest and disease records during the spring and autumn periods of the experiment, count the total number of pest and disease records, obtain the label groups corresponding to the pest and disease records, count the number of occurrences of each label group corresponding to the pest and disease records, record it as the first number, count the number of occurrences of each label when no pest and disease records occur during the spring and autumn periods of the experiment, record it as the second number, calculate the pest and disease probability corresponding to each label based on the first number and the second number, and calculate the pest and disease probability interval corresponding to each label based on the confidence interval formula.

[0011] As a preferred solution of the forest pest early warning system described in the present invention, the calculation logic of the pest probability corresponding to each tag includes: The sum of the first number and the second number corresponding to the label is calculated, recorded as the total number of events, the ratio of the first number to the total number of events is calculated, and the ratio of the first number to the total number of events is set as the pest probability of the label.

[0012] As a preferred solution of the forest pest early warning system described in the present invention, the calculation logic of the pest probability interval corresponding to each tag includes: The confidence level is set to 95%, the probability of pests and diseases corresponding to the label is obtained, the standard error is calculated based on the probability of pests and diseases corresponding to the label, and the probability interval of pests and diseases corresponding to the label is calculated based on the standard error; The calculation expression of the standard error is: ; The calculation expression of the probability interval of pests and diseases is: ; in, is the standard error, is the probability of pests and diseases corresponding to the label, is the total number of events corresponding to the label, is the probability interval of pests and diseases.

[0013] As a preferred solution of the early warning system for forest pests and diseases described in the present invention, the warning module sorts the upper limits of the probability intervals of pests and diseases with the same season label in ascending order to obtain the seasonal ascending sorting results, grades the probability intervals of pests and diseases according to the seasonal ascending sorting results, sets the third value and the fourth value as the grading threshold, sets the probability interval of pests and diseases including the third value as the first grade interval, sets the probability interval of pests and diseases including the fourth value as the second grade interval, and sets the probability interval of pests and diseases not including the third value and the fourth value as the third grade interval, wherein the third value is greater than the fourth value, and the third value and the fourth value are both distributed between [0,1].

[0014] As a preferred solution of the early warning system for forest pests and diseases described in the present invention, the warning module establishes a first mapping relationship between a label group and a pest and disease probability interval corresponding to the label group, obtains the label group of the current detection time, obtains the pest and disease probability interval of the current detection time according to the first mapping relationship, obtains the level corresponding to the pest and disease probability interval of the current detection time, and issues warning signals of different brightness and colors; when the level corresponding to the pest and disease probability interval of the current detection time is a first level interval, an early warning signal light of a first color and a first brightness is issued; when the level corresponding to the pest and disease probability interval of the current detection time is a second level interval, an early warning signal light of a second color and a second brightness is issued; when the level corresponding to the pest and disease probability interval of the current detection time is a third level interval, an early warning signal light of a third color and a third brightness is issued, and the pest and disease probability interval of the current detection time is displayed through an OLED.

[0015] The beneficial effects of the present invention are as follows: by acquiring seasonal and regional natural information, the system can dynamically adjust early warning strategies for specific areas and seasons, thereby enhancing the scientific nature of decision-making; by calculating the temperature change rate and precipitation mutation, risk levels are set for different labels, helping managers to quickly identify high-risk areas, thereby optimizing resource allocation; the matching of pest and disease records with label groups enables the system to update data in a timely manner, provide real-time early warning information, and reduce potential losses; the probability and confidence interval of pests and diseases are calculated based on statistical analysis, thereby enhancing the credibility of early warning information and improving the response efficiency of managers; by sorting the probability of pests and diseases in ascending order, the system can implement graded early warning, take corresponding prevention and control measures for different risk levels, thereby enhancing the flexibility and effectiveness of emergency management; and by integrating natural information with pest and disease records, a scientific and effective early warning mechanism is constructed, thereby providing strong support for forest health management and helping to reduce the economic losses and ecological impacts caused by pests and diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A basic flow chart of an early warning system for forest pests and diseases provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0018] Example 1, reference Figure 1 , as an embodiment of the present invention, provides an early warning system for forest pests and diseases, including an acquisition module, an analysis module and an early warning module; The acquisition module sets a season segmentation temperature, obtains a test spring and a test autumn according to the season segmentation temperature, obtains the duration of the test spring and the duration of the test autumn, obtains the name of the region where the tree is located, and matches the natural information of the region name within the duration of the test spring and the duration of the test autumn according to the name of the region where the tree is located; The analysis module calculates the average temperature change rate and precipitation mutation amount according to natural information, sets a temperature label according to the average temperature change rate, sets a precipitation label according to the precipitation mutation amount, sets a spring label and an autumn label according to the experimental spring duration and the experimental autumn duration, combines the labels to obtain a label group, obtains the pest and disease records within the experimental spring duration and the experimental autumn duration, obtains the label group corresponding to the pest and disease records, counts the number of occurrences of each label group corresponding to the pest and disease records, and records the number of occurrences of each label when no pest and disease records occur within the experimental spring duration and the experimental autumn duration, and records the number of occurrences of each label as the second number, calculates the pest and disease probability corresponding to each label according to the first number and the second number, and calculates the pest and disease probability interval corresponding to each label according to the confidence interval formula; The early warning module sorts the upper limits of the probability intervals of pests and diseases with the same season label in ascending order to obtain a seasonal ascending sorting result, establishes a first mapping relationship between the label group and the probability intervals of pests and diseases corresponding to the label group, and performs graded early warning according to the seasonal ascending sorting result.

[0019] By acquiring seasonal and regional natural information, the present invention enables the system to dynamically adjust early warning strategies for specific areas and seasons, thereby enhancing the scientific nature of decision-making; by calculating the temperature change rate and precipitation mutation, risk levels are set for different labels, helping managers to quickly identify high-risk areas, thereby optimizing resource allocation; the matching of pest and disease records with label groups enables the system to update data in a timely manner, provide real-time early warning information, and reduce potential losses; the probability and confidence interval of pests and diseases are calculated based on statistical analysis, thereby enhancing the credibility of early warning information and improving the response efficiency of managers; by sorting the probability of pests and diseases in ascending order, the system can implement graded early warning, take corresponding prevention and control measures for different risk levels, thereby enhancing the flexibility and effectiveness of emergency management; by integrating natural information with pest and disease records, a scientific and effective early warning mechanism is constructed, which provides strong support for forest health management and helps to reduce the economic losses and ecological impacts caused by pests and diseases.

[0020] The acquisition module sets the seasonal segmentation temperature, the seasonal segmentation temperature includes the spring segmentation temperature and the autumn segmentation temperature, and the setting logic of the seasonal segmentation temperature includes: Obtain spring temperature and winter temperature, calculate the average value of spring temperature and the average value of winter temperature respectively, calculate the first sum of the average value of spring temperature and the average value of winter temperature, and set half of the first sum as spring split temperature; Obtaining the summer temperature and the autumn temperature, respectively calculating the average of the summer temperature and the average of the autumn temperature, calculating the second sum of the average of the summer temperature and the average of the autumn temperature, and setting half of the second sum as the autumn split temperature; According to the seasonal split temperature division, the test spring and test autumn are obtained, the time period from the spring split temperature to the average value of the summer temperature is set as the test spring, and the time period from the autumn split temperature to the average value of the winter temperature is set as the test autumn, and the test spring duration and test autumn duration are obtained respectively; Get the name of the region where the tree is located, call the climate database, input the region name into the climate database, match the corresponding natural information according to the region name, filter the natural information within the experimental spring period and the experimental autumn period as the information to be analyzed, and delete the remaining natural information, the natural information includes temperature and precipitation, the temperature is expressed as the temperature of a natural day, and the precipitation is expressed as the precipitation of a natural day.

[0021] In specific implementation, by calculating the average temperature of spring and winter, as well as the average temperature of summer and autumn, the system can scientifically determine the split temperature of spring and autumn. This method ensures the accuracy of season division, helps to improve the accuracy of subsequent analysis, and can flexibly adjust the season split temperature according to the climate characteristics of different regions, so as to adapt to regional differences and improve the pertinence and effectiveness of early warning. By calling the climate database, the system can quickly match the name of the region and filter out the natural information related to the spring and autumn of the experiment, making the acquisition of information to be analyzed more efficient and avoiding the interference of irrelevant data. Natural information, such as temperature and precipitation, is represented as daily data, making the subsequent analysis results easier to understand and visualize, facilitating forestry managers to make decisions, integrating the natural information of temperature and precipitation, and providing data support for risk assessment and early warning of pests and diseases, making the early warning more scientific and accurate.

[0022] The analysis module calculates the average temperature change rate and the precipitation mutation amount according to the natural information. The calculation logic of the average temperature change amount includes: Obtain the temperature in the information to be analyzed in the spring of the experiment or the temperature in the information to be analyzed in the autumn of the experiment, record it as the temperature to be analyzed, calculate the change rate of adjacent temperatures to be analyzed, calculate the average value of the change rates of adjacent temperatures to be analyzed, record it as the average temperature change rate, wherein the adjacent temperatures to be analyzed are represented as the temperatures of adjacent natural days in the time sequence; The calculation logic of the precipitation mutation amount includes: The temperature in the information to be analyzed in the spring of the experiment or the precipitation in the information to be analyzed in the autumn of the experiment is obtained, recorded as the precipitation to be analyzed, the difference between adjacent precipitations to be analyzed is calculated, and the difference between adjacent precipitations to be analyzed is set as the precipitation mutation amount.

[0023] In specific implementation, by calculating the average temperature change rate, the system can monitor and evaluate the changing trend of temperature in real time, provide important clues for the risk of pests and diseases, and help to detect abnormal climate in time. The calculation logic of precipitation mutation enables the system to identify mutations in precipitation in time. Mutations in precipitation are usually associated with the occurrence of pests and diseases, providing a sensitive monitoring tool for early warning. Through comprehensive analysis of temperature and precipitation changes, the system can establish a more comprehensive climate risk assessment model, providing a solid foundation for subsequent pest and disease forecasts. The logical design of the analysis module allows the system to be dynamically adjusted according to real-time data, so that the early warning system has strong adaptability and flexibility, and can cope with changes under different climatic conditions.

[0024] The analysis module sets a temperature label according to the average temperature change rate, sets a precipitation label according to the precipitation mutation amount, sets a spring label and an autumn label according to the experimental spring duration and the experimental autumn duration, wherein the temperature label includes a large temperature change and a normal temperature change, the precipitation label includes a precipitation mutation and a non-precipitation mutation, the spring label includes a long spring time, a short spring time and a normal spring time, and the autumn label includes a long autumn time, a short autumn time and a normal autumn time; The setting logic of the temperature label includes setting the first value as the upper limit of the average temperature change rate, comparing the average temperature change rate with the first value, and when the average temperature change rate is greater than the first value, setting the temperature label to indicate a large temperature change, otherwise, setting the temperature label to indicate a large temperature change or a normal temperature change; The setting logic of the precipitation label includes: setting the second value as the upper limit of the precipitation difference, comparing the precipitation mutation amount with the second value, and when the precipitation mutation amount is greater than the second value, setting the precipitation label to precipitation mutation, otherwise, setting the precipitation label to precipitation no mutation; The setting logic of the spring label includes: obtaining the time period between the vernal equinox date and the summer solstice date, recording it as the first standard time period, comparing the test spring duration with the first standard time period, when the test spring duration is greater than the first standard time period, setting the spring label to long spring time, when the test spring duration is less than the first standard time period, setting the spring label to short spring time, and when the test spring duration is equal to the first standard time period, setting the spring label to normal spring time.

[0025] In specific implementation, the setting of temperature and precipitation labels provides clear indications of climate change, helping managers to quickly identify potential risks, such as temperature changes or sudden changes in precipitation. Setting labels according to the length of the experimental spring and autumn enables the system to dynamically evaluate the impact of seasonal changes on pests and diseases, ensuring the timeliness of early warnings. The classification of labels, such as large temperature changes and sudden changes in precipitation, provides an intuitive basis for decision-making. Forestry managers can formulate response strategies more effectively. By setting standard time periods, the system can achieve more standardized comparisons and provide a reference framework for climate change analysis in different years or regions.

[0026] The setting logic of the autumn label includes: obtaining the time period between the autumnal equinox date and the winter solstice date, recording it as the second standard time period, comparing the test autumn duration with the second standard time period, when the test autumn duration is greater than the second standard time period, setting the autumn label to be long spring time, when the test autumn duration is less than the second standard time period, setting the autumn label to be short autumn time, when the test autumn duration is equal to the second standard time period, setting the autumn label to be normal autumn time; Set long spring time to X1, short spring time to X2, normal spring time to X3, long autumn time to Y1, short autumn time to Y2, normal autumn time to Y3, large temperature change to M1, normal temperature change to M2, sudden precipitation change to N1, and no sudden precipitation change to N2.

[0027] In the specific implementation, clear identifiers are used to make the meaning of each label clear at a glance, which is convenient for managers to quickly understand the climate change situation. Setting the labels as standardized symbols will help the modular management and data analysis of the system, and improve the efficiency and accuracy of data processing. By setting different labels, managers can more easily compare the spring and autumn seasons and identify the impact of climate change on forest health.

[0028] The analysis module combines the spring label or the autumn label, the corresponding temperature label and the corresponding precipitation label to obtain a label group, which is represented by X MN or Y MN , which means that if one of the X elements is selected, the sum of the M and N elements is at least 1, or if one of the Y elements is selected, the sum of the M and N elements is at least 1; Obtain pest and disease records during the spring and autumn periods of the experiment, count the total number of pest and disease records, obtain the label groups corresponding to the pest and disease records, count the number of occurrences of each label group corresponding to the pest and disease records, record it as the first number, count the number of occurrences of each label when no pest and disease records occur during the spring and autumn periods of the experiment, record it as the second number, calculate the pest and disease probability corresponding to each label based on the first number and the second number, and calculate the pest and disease probability interval corresponding to each label based on the confidence interval formula.

[0029] The calculation logic of the pest and disease probability corresponding to each label includes: The sum of the first number and the second number corresponding to the label is calculated, recorded as the total number of events, the ratio of the first number to the total number of events is calculated, and the ratio of the first number to the total number of events is set as the pest probability of the label.

[0030] The calculation logic of the pest and disease probability interval corresponding to each label includes: The confidence level is set to 95%, the probability of pests and diseases corresponding to the label is obtained, the standard error is calculated based on the probability of pests and diseases corresponding to the label, and the probability interval of pests and diseases corresponding to the label is calculated based on the standard error; The calculation expression of the standard error is: ; The calculation expression of the probability interval of pests and diseases is: ; in, is the standard error, is the probability of pests and diseases corresponding to the label, is the total number of events corresponding to the label, is the probability interval of pests and diseases.

[0031] In specific implementation, by combining spring and autumn labels with temperature and precipitation labels to form label groups, the system can comprehensively evaluate the relationship between climate change and the occurrence of pests and diseases, provide a more comprehensive risk assessment, and count the total number of pest and disease records and the frequency of occurrence of each label group. This helps to identify which climatic conditions are more likely to cause pests and diseases, thereby providing managers with data-driven decision support. By calculating the probability and confidence interval of pests and diseases, the reliability of the analysis results is enhanced, allowing managers to make well-founded judgments in the face of uncertainty. According to the probability of pests and diseases in different label groups, managers can dynamically adjust prevention and control strategies, focus on high-risk climatic conditions, and optimize resource allocation.

[0032] The early warning module sorts the upper limits of the probability intervals of pests and diseases with the same season label in ascending order to obtain a seasonal ascending sorting result, grades the probability intervals of pests and diseases according to the seasonal ascending sorting result, sets the third value and the fourth value as the grading threshold, sets the probability interval of pests and diseases including the third value as the first grade interval, sets the probability interval of pests and diseases including the fourth value as the second grade interval, and sets the probability interval of pests and diseases not including the third value and the fourth value as the third grade interval, wherein the third value is greater than the fourth value, and the third value and the fourth value are both distributed between [0,1].

[0033] In specific implementation, through ascending sorting and grading, the system can intuitively display different levels of pest and disease risk, making it easier for managers to understand and assess potential risks. The grading mechanism combined with the probability interval makes the decision-making process more scientific, and managers can make more reasonable judgments and response plans based on data.

[0034] The early warning module establishes a first mapping relationship between a label group and a disease and insect pest probability interval corresponding to the label group, obtains the label group of the current detection time, obtains the disease and insect pest probability interval of the current detection time according to the first mapping relationship, obtains the level corresponding to the disease and insect pest probability interval of the current detection time, and issues early warning signals of different brightness and colors. When the level corresponding to the disease and insect pest probability interval of the current detection time is a first level interval, an early warning signal light of a first color and a first brightness is issued. When the level corresponding to the disease and insect pest probability interval of the current detection time is a second level interval, an early warning signal light of a second color and a second brightness is issued. When the level corresponding to the disease and insect pest probability interval of the current detection time is a third level interval, an early warning signal light of a third color and a third brightness is issued, and the disease and insect pest probability interval of the current detection time is displayed through an OLED.

[0035] In specific implementation, by obtaining the label group and pest probability interval of the current detection time, the system can monitor the pest risk in real time and provide timely feedback information to managers. The warning signal lights of different brightness and colors make the risk level clear at a glance. Managers can quickly identify the risk level and take corresponding measures to improve response efficiency. Classifying the levels corresponding to the pest probability interval helps to clarify the characteristics of each risk level, so that managers can formulate prevention and control strategies more specifically. The pest probability interval of the current detection time is displayed on the OLED display, which enhances the clarity of information transmission.

[0036] By acquiring seasonal and regional natural information, the present invention enables the system to dynamically adjust early warning strategies for specific areas and seasons, thereby enhancing the scientific nature of decision-making; by calculating the temperature change rate and precipitation mutation, risk levels are set for different labels, helping managers to quickly identify high-risk areas, thereby optimizing resource allocation; the matching of pest and disease records with label groups enables the system to update data in a timely manner, provide real-time early warning information, and reduce potential losses; the probability and confidence interval of pests and diseases are calculated based on statistical analysis, thereby enhancing the credibility of early warning information and improving the response efficiency of managers; by sorting the probability of pests and diseases in ascending order, the system can implement graded early warning, take corresponding prevention and control measures for different risk levels, thereby enhancing the flexibility and effectiveness of emergency management; by integrating natural information with pest and disease records, a scientific and effective early warning mechanism is constructed, which provides strong support for forest health management and helps to reduce the economic losses and ecological impacts caused by pests and diseases.

[0037] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0038] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An early warning system for forest pests and diseases, characterized in that: It includes acquisition module, analysis module and early warning module; The acquisition module sets a season segmentation temperature, obtains a test spring and a test autumn according to the season segmentation temperature, obtains the duration of the test spring and the duration of the test autumn, obtains the name of the region where the tree is located, and matches the natural information of the region name within the duration of the test spring and the duration of the test autumn according to the name of the region where the tree is located; The analysis module calculates the average temperature change rate and precipitation mutation amount according to natural information, sets a temperature label according to the average temperature change rate, sets a precipitation label according to the precipitation mutation amount, sets a spring label and an autumn label according to the experimental spring duration and the experimental autumn duration, combines the labels to obtain a label group, obtains the pest and disease records within the experimental spring duration and the experimental autumn duration, obtains the label group corresponding to the pest and disease records, counts the number of occurrences of each label group corresponding to the pest and disease records, and records the number of occurrences of each label when no pest and disease records occur within the experimental spring duration and the experimental autumn duration, and records the number of occurrences of each label as the second number, calculates the pest and disease probability corresponding to each label according to the first number and the second number, and calculates the pest and disease probability interval corresponding to each label according to the confidence interval formula; The early warning module sorts the upper limits of the probability intervals of pests and diseases with the same season label in ascending order to obtain a seasonal ascending sorting result, establishes a first mapping relationship between the label group and the probability intervals of pests and diseases corresponding to the label group, and performs graded early warning according to the seasonal ascending sorting result.

2. The early warning system for forest pests and diseases as claimed in claim 1, characterized in that: The acquisition module sets the seasonal segmentation temperature, the seasonal segmentation temperature includes the spring segmentation temperature and the autumn segmentation temperature, and the setting logic of the seasonal segmentation temperature includes: Obtain spring temperature and winter temperature, calculate the average value of spring temperature and the average value of winter temperature respectively, calculate the first sum of the average value of spring temperature and the average value of winter temperature, and set half of the first sum as spring split temperature; Obtaining the summer temperature and the autumn temperature, respectively calculating the average of the summer temperature and the average of the autumn temperature, calculating the second sum of the average of the summer temperature and the average of the autumn temperature, and setting half of the second sum as the autumn split temperature; According to the seasonal split temperature division, the test spring and test autumn are obtained, the time period from the spring split temperature to the average value of the summer temperature is set as the test spring, and the time period from the autumn split temperature to the average value of the winter temperature is set as the test autumn, and the test spring duration and test autumn duration are obtained respectively; Get the name of the region where the tree is located, call the climate database, input the region name into the climate database, match the corresponding natural information according to the region name, filter the natural information within the experimental spring period and the experimental autumn period as the information to be analyzed, and delete the remaining natural information, the natural information includes temperature and precipitation, the temperature is expressed as the temperature of a natural day, and the precipitation is expressed as the precipitation of a natural day.

3. The early warning system for forest pests and diseases as claimed in claim 1, characterized in that: The analysis module calculates the average temperature change rate and the precipitation mutation amount according to the natural information. The calculation logic of the average temperature change amount includes: Obtain the temperature in the information to be analyzed in the spring of the experiment or the temperature in the information to be analyzed in the autumn of the experiment, record it as the temperature to be analyzed, calculate the change rate of adjacent temperatures to be analyzed, calculate the average value of the change rates of adjacent temperatures to be analyzed, record it as the average temperature change rate, wherein the adjacent temperatures to be analyzed are represented as the temperatures of adjacent natural days in the time sequence; The calculation logic of the precipitation mutation amount includes: The temperature in the information to be analyzed in the spring of the experiment or the precipitation in the information to be analyzed in the autumn of the experiment is obtained, recorded as the precipitation to be analyzed, the difference between adjacent precipitations to be analyzed is calculated, and the difference between adjacent precipitations to be analyzed is set as the precipitation mutation amount.

4. The early warning system for forest pests and diseases as claimed in claim 3, characterized in that: The analysis module sets a temperature label according to the average temperature change rate, sets a precipitation label according to the precipitation mutation amount, sets a spring label and an autumn label according to the experimental spring duration and the experimental autumn duration, wherein the temperature label includes a large temperature change and a normal temperature change, the precipitation label includes a precipitation mutation and a non-precipitation mutation, the spring label includes a long spring time, a short spring time and a normal spring time, and the autumn label includes a long autumn time, a short autumn time and a normal autumn time; The setting logic of the temperature label includes setting the first value as the upper limit of the average temperature change rate, comparing the average temperature change rate with the first value, and when the average temperature change rate is greater than the first value, setting the temperature label to indicate a large temperature change, otherwise, setting the temperature label to indicate a large temperature change or a normal temperature change; The setting logic of the precipitation label includes: setting the second value as the upper limit of the precipitation difference, comparing the precipitation mutation amount with the second value, and when the precipitation mutation amount is greater than the second value, setting the precipitation label to precipitation mutation, otherwise, setting the precipitation label to precipitation no mutation; The setting logic of the spring label includes: obtaining the time period between the vernal equinox date and the summer solstice date, recording it as the first standard time period, comparing the test spring duration with the first standard time period, when the test spring duration is greater than the first standard time period, setting the spring label to long spring time, when the test spring duration is less than the first standard time period, setting the spring label to short spring time, and when the test spring duration is equal to the first standard time period, setting the spring label to normal spring time.

5. The early warning system for forest pests and diseases as claimed in claim 4, characterized in that: The setting logic of the autumn label includes: obtaining the time period between the autumnal equinox date and the winter solstice date, recording it as the second standard time period, comparing the test autumn duration with the second standard time period, when the test autumn duration is greater than the second standard time period, setting the autumn label to be long spring time, when the test autumn duration is less than the second standard time period, setting the autumn label to be short autumn time, when the test autumn duration is equal to the second standard time period, setting the autumn label to be normal autumn time; Set long spring time to X1, short spring time to X2, normal spring time to X3, long autumn time to Y1, short autumn time to Y2, normal autumn time to Y3, large temperature change to M1, normal temperature change to M2, sudden precipitation change to N1, and no sudden precipitation change to N2.

6. The early warning system for forest pests and diseases as claimed in claim 5, characterized in that: The analysis module combines the spring label or the autumn label, the corresponding temperature label and the corresponding precipitation label to obtain a label group, which is represented by X MN or Y MN , which means that if one of the X elements is selected, the sum of the M and N elements is at least 1, or if one of the Y elements is selected, the sum of the M and N elements is at least 1; Obtain pest and disease records during the spring and autumn periods of the experiment, count the total number of pest and disease records, obtain the label groups corresponding to the pest and disease records, count the number of occurrences of each label group corresponding to the pest and disease records, record it as the first number, count the number of occurrences of each label when no pest and disease records occur during the spring and autumn periods of the experiment, record it as the second number, calculate the pest and disease probability corresponding to each label based on the first number and the second number, and calculate the pest and disease probability interval corresponding to each label based on the confidence interval formula.

7. The early warning system for forest pests and diseases as claimed in claim 6, characterized in that: The calculation logic of the pest and disease probability corresponding to each label includes: The sum of the first number and the second number corresponding to the label is calculated, recorded as the total number of events, the ratio of the first number to the total number of events is calculated, and the ratio of the first number to the total number of events is set as the pest probability of the label.

8. The early warning system for forest pests and diseases as claimed in claim 7, characterized in that: The calculation logic of the pest and disease probability interval corresponding to each label includes: The confidence level is set to 95%, the probability of pests and diseases corresponding to the label is obtained, the standard error is calculated based on the probability of pests and diseases corresponding to the label, and the probability interval of pests and diseases corresponding to the label is calculated based on the standard error; The calculation expression of the standard error is: ; The calculation expression of the probability interval of pests and diseases is: ; in, is the standard error, is the probability of pests and diseases corresponding to the label, is the total number of events corresponding to the label, is the probability interval of pests and diseases.

9. The early warning system for forest pests and diseases as claimed in claim 1, characterized in that: The early warning module sorts the upper limits of the probability intervals of pests and diseases with the same season label in ascending order to obtain a seasonal ascending sorting result, grades the probability intervals of pests and diseases according to the seasonal ascending sorting result, sets the third value and the fourth value as the grading threshold, sets the probability interval of pests and diseases including the third value as the first grade interval, sets the probability interval of pests and diseases including the fourth value as the second grade interval, and sets the probability interval of pests and diseases not including the third value and the fourth value as the third grade interval, wherein the third value is greater than the fourth value, and the third value and the fourth value are both distributed between [0,1].

10. The early warning system for forest pests and diseases as claimed in claim 9, characterized in that: The early warning module establishes a first mapping relationship between a label group and a disease and insect pest probability interval corresponding to the label group, obtains the label group of the current detection time, obtains the disease and insect pest probability interval of the current detection time according to the first mapping relationship, obtains the level corresponding to the disease and insect pest probability interval of the current detection time, and issues early warning signals of different brightness and colors. When the level corresponding to the disease and insect pest probability interval of the current detection time is a first level interval, an early warning signal light of a first color and a first brightness is issued. When the level corresponding to the disease and insect pest probability interval of the current detection time is a second level interval, an early warning signal light of a second color and a second brightness is issued. When the level corresponding to the disease and insect pest probability interval of the current detection time is a third level interval, an early warning signal light of a third color and a third brightness is issued, and the disease and insect pest probability interval of the current detection time is displayed through an OLED.