A management system and method for early warning and prevention of harmful biological disasters in urban green areas

Abstract

The present invention relates to the technical field of urban green space management, and specifically to an early warning prevention and control management system and method for urban green space pest disasters. The prevention and control management system includes a risk identification device and an early warning module. The risk identification device includes a partition risk identification module and an interactive risk identification module. The partition risk identification module is used to analyze the comprehensive risk value in the corresponding sub-region based on the big data in each divided sub-region. The interactive risk identification module is used to calculate the deep risk value based on the comprehensive risk value and the mutual interference coefficient of each sub-region. The early warning module is used to send an alarm signal when the deep risk value is higher than a preset threshold. The present invention identifies the multi-dimensional data of the green space, analyzes the types and population densities of pests existing in the green space area, and then analyzes the pest risk value of each green space area. According to the mutual interference between the areas, the deep risk value is obtained, and the prevention and control management has high accuracy, strong timeliness, and is more reliable.

Description

Technical Field

[0001] The present invention relates to the technical field of urban green space management, and in particular to an urban green space harmful biological disaster early warning prevention and control management system and an urban green space harmful biological disaster early warning prevention and control management method. Background Art

[0002] The urban green space pest disaster early warning and prevention management system is an intelligent early warning and prevention system based on big data, artificial intelligence and Internet of Things technologies. In the existing technology, the system deploys sensor equipment in urban green spaces to collect environmental data and pest information in real time, and uses data analysis and algorithms to identify and predict the activity patterns and potential risks of pests. Once abnormal activities or foreign invasions of pests are detected, the system will immediately issue an early warning signal to notify relevant departments for emergency response.

[0003] In the prior art, urban green space management systems generally carry out early warning management based on the mutual constraints between green space and harmful organisms, such as pressure-state-response. Since the information collected by the system is relatively cumbersome and requires more equipment to be installed, the cost of data collection is high, which also leads to poor timeliness. In addition, since the existing urban green space management systems often conduct overall assessments, it is difficult to evaluate different plant species and harmful organisms in each region without considering the potential interference between regions. Therefore, the output risk assessment accuracy is low and it is difficult to serve as a reliable evaluation standard. Summary of the invention

[0004] Based on this, it is necessary to propose an urban green space pest disaster early warning prevention and control management system and method to address the problems of low recognition accuracy and low reliability of the existing urban green space pest identification and early warning.

[0005] The present invention is achieved through the following technical solutions: an urban green space harmful biological disaster early warning prevention and control management system includes a collection device, a pre-processing device, a risk identification device, an early warning module and a management module.

[0006] The collection device is used to collect urban green space big data based on the management area.

[0007] The preprocessing device includes a data preprocessing module and a partitioning module. The preprocessing module is used to remove errors and duplicate data in big data. The partitioning module is used to divide the management area into multiple sub-areas, establish a data set for each sub-area, and add the data related to each sub-area to the corresponding data set.

[0008] The risk identification device includes a partition risk identification module and an interactive risk identification module. The partition risk identification module is used to analyze the comprehensive risk value in the corresponding sub-region according to the data of each data set. The interactive risk identification module is used to calculate the depth risk value according to the comprehensive risk value and mutual interference coefficient of each sub-region.

[0009] The early warning module is used to determine whether the depth risk value of each sub-area is higher than the preset threshold, and if so, an alarm signal is issued.

[0010] The management module is used to identify whether the prevention and control measures of each sub-area are completed on time. When the prevention and control measures of any sub-area are not completed on time, a prevention and control command is generated and sent to the corresponding operator.

[0011] The above-mentioned prevention and control management method fully considers the destructiveness caused by different types of pests to different types of green plants. By identifying the multi-dimensional data of green spaces, the types and population densities of pests in the green space are analyzed, and then the pest risk value of each green space area is analyzed. According to the mutual interference between the areas, the deep risk value is obtained, which can more accurately reflect the harmfulness of the pests in the current area. By collecting and processing data in real time, the early warning and treatment efficiency of pests can be improved, and the green space environment can be protected from being destroyed.

[0012] Furthermore, urban green space big data includes dynamic images, climate data, geological data and atmospheric data.

[0013] Furthermore, the zoning risk identification module includes a color recognition model, a dynamic recognition model, a geological recognition model, a gas recognition model and a comprehensive calculation module.

[0014] The color recognition model is used to identify the green color of each sub-area based on dynamic images, and then identify the first risk value p of the presence of pests through the change of green color. 1 , and determine the types and population density of pests.

[0015] The dynamic recognition model is used to identify the second risk value p of pests in each sub-area based on dynamic images. 2 , and determine the types and population density of pests.

[0016] The geological identification model is used to identify the geological changes in each sub-region based on geological data, and then identify the third risk value p of the presence of pests. 3 .

[0017] The gas identification model is used to identify the changes in gas content in each sub-region based on atmospheric data, and then identify the fourth risk value p where harmful organisms exist. 4 .

[0018] The comprehensive calculation module is used to calculate the comprehensive risk value of each sub-region according to the preset weight. Z The calculation formula is expressed as:

[0019]

[0020] In the formula, ω 1 ,ω 2 ,ω 3 ,ω 4 are the weights set respectively.

[0021] Furthermore, the interactive risk identification module includes a mapping table, an interference coefficient calculation module and a depth risk calculation module.

[0022] The mapping table is used to find the corresponding damage level R according to the identified pest species and plant species in each sub-region.

[0023] The interference coefficient calculation module is used to calculate the interference coefficient between each region based on the spacing, climate data and geological data of each sub-region. The interference coefficient k is expressed as:

[0024]

[0025] Where D is the preset standard spacing, d is the distance between two sub-areas, ρ 1 is the climate disturbance term, 2 is the geological disturbance term.

[0026] The depth risk calculation module is used to calculate the corresponding depth risk value according to the comprehensive risk value, hazard level and interference coefficient of each area. The depth risk value P D The calculation formula is expressed as:

[0027]

[0028] Where P Zi is the comprehensive risk value of the ith sub-region, N is the number of sub-regions, R j k is the degree of damage caused by pests in the jth sub-region to the i-th sub-region, j is the interference coefficient of the jth sub-region to the i-th sub-region, P Zj is the comprehensive risk value of the j-th sub-region.

[0029] Furthermore, the management module includes a daily management module and a risk management module.

[0030] The daily management module is used to: 1. Generate prevention and control commands according to the preset prevention and control plan and send them to the responsible personnel of each sub-area. 2. Receive the prevention and control logs uploaded by each sub-area, and then check the prevention and control completion progress of each sub-area. When a sub-area fails to complete the prevention and control plan on time, generate an alarm command and send it to the responsible personnel and superior responsible personnel of the corresponding sub-area.

[0031] The risk management module is used to: 1. According to the deep risk value in each sub-area, query the corresponding prevention and control measures in a pre-stored prevention and control plan table, and then generate a prevention and control command and send it to the responsible personnel of the corresponding sub-area. 2. According to the prevention and control log feedback from each sub-area, determine whether each sub-area has completed the prevention and control measures, and if any sub-area fails to complete the prevention and control plan on time, generate an alarm command and send it to the responsible personnel and superior responsible personnel of the corresponding sub-area.

[0032] The present invention also provides a method for early warning, prevention and control of harmful biological disasters in urban green spaces, comprising the following steps:

[0033] S1: Collect urban green space big data based on the management area. Urban green space big data includes dynamic images, climate data, geological data and atmospheric data.

[0034] S2: Preprocess the urban green space big data to remove erroneous and duplicate data, divide the management area into multiple sub-regions, and divide the urban green space big data into the data sets corresponding to each sub-region.

[0035] S3: Identify the risks of each sub-region and output the comprehensive risk value, pest species and population density of each sub-region. Calculate the deep risk value of each sub-region based on the risk value and mutual interference coefficient of each sub-region.

[0036] S4: Determine whether the depth risk value of each sub-area is higher than the preset threshold. If yes, send out an alarm signal and generate a corresponding prevention and control command to be sent to the corresponding sub-area responsible person.

[0037] Furthermore, in step S3, the comprehensive risk value is identified as follows:

[0038] S311: Extract frames from the dynamic image to obtain multiple green space images. Identify the green space images to obtain the green space color changes in each sub-area. Identify the first risk value p of the presence of harmful organisms based on the green space color changes. 1 .

[0039] S312: Capture the movement trajectory and body size of small organisms in the dynamic image, and then identify the type and population density of the harmful organisms, and identify the second risk value p of the corresponding sub-region according to the type and population density of the harmful organisms 2 .

[0040] S313: Identify the geological changes in each sub-region based on geological data, and then identify the third risk value p of the presence of harmful organisms 3 .

[0041] S314: Identify the change in gas content in each sub-region based on the atmospheric data, and then identify the fourth risk value p of the presence of harmful organisms 4 .

[0042] S315: Calculate the comprehensive risk value of each sub-region according to the preset weight. The comprehensive risk value P Z The calculation formula is expressed as:

[0043]

[0044] In the formula, ω 1 ,ω 2 ,ω 3 ,ω 4 are the weights set respectively.

[0045] Furthermore, in step S3, the calculation method of the depth risk value is as follows:

[0046] S321: Find the corresponding hazard level R according to the identified harmful organism types and plant types in each sub-region.

[0047] S322: Calculate the interference coefficient between each region based on the distance between each sub-region, climate data and geological data. The interference coefficient k is expressed as:

[0048]

[0049] Where D is the preset standard spacing, d is the distance between two sub-areas, ρ 1 is the climate disturbance term, 2 is the geological disturbance term.

[0050] S323: Calculate the corresponding depth risk value according to the comprehensive risk value, hazard level and interference coefficient of each area. The depth risk value P D The calculation formula is expressed as:

[0051]

[0052] Where P Zi is the comprehensive risk value of the ith sub-region, N is the number of sub-regions, R j k is the degree of damage caused by pests in the jth sub-region to the i-th sub-region, j is the interference coefficient of the jth sub-region to the i-th sub-region, P Zj is the comprehensive risk value of the j-th sub-region.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] The prevention and control management method of the present invention fully considers the destructiveness caused by different types of pests to different types of green plants. It identifies the multi-dimensional data of green space, analyzes the types and population densities of pests in the green space area, and then analyzes the pest risk value of each green space area. According to the mutual interference between the areas, the deep risk value is obtained, which can more accurately reflect the harmfulness of the pests in the current area. By collecting and processing data in real time, it can improve the early warning and treatment efficiency of pests and protect the green environment from being destroyed.

[0055] The present invention constructs different recognition models to identify the possible types of harmful organisms and their population density in green areas based on plant color changes, animal dynamic capture, geological changes, climate change, atmospheric changes, etc., and analyzes the possible risk values. A comprehensive risk value is obtained through weighted calculation. Compared with the existing pest risk identification, the present invention has a more comprehensive analysis of green space pests, a higher recognition accuracy, and a more valuable output risk value. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a schematic diagram of the framework structure of the urban green space harmful biological disaster early warning prevention and control management system in Example 1 of the present invention;

[0057] Figure 2 for Figure 1 Schematic diagram of the framework structure of the middle partition risk identification module;

[0058] Figure 3 A step diagram of the method for early warning, prevention and control of harmful biological disasters in urban green spaces in Embodiment 2 of the present invention;

[0059] Figure 4 for Figure 3 Diagram of the calculation steps of the comprehensive risk value;

[0060] Figure 5 for Figure 3 Diagram of the calculation steps of medium-depth risk value. DETAILED DESCRIPTION

[0061] 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.

[0062] It should be noted that when a component is referred to as being "mounted on" another component, it may be directly on the other component or there may be a central component. When a component is considered to be "set on" another component, it may be directly set on the other component or there may be a central component at the same time. When a component is considered to be "fixed to" another component, it may be directly fixed on the other component or there may be a central component at the same time.

[0063] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "or / and" used herein includes any and all combinations of one or more of the related listed items.

[0064] Example 1: Please refer to Figure 1 This embodiment provides an urban green space harmful biological disaster early warning prevention and control management system, including a collection device, a pre-processing device, a risk identification device, an early warning module and a management module.

[0065] The collection device is used to collect urban green space big data based on the management area. Urban green space big data includes dynamic images, climate data, geological data and atmospheric data. In practical applications, dynamic images can be obtained in real time by installing monitoring equipment, climate data can be directly exported based on the urban climate information release platform, and geological data and atmospheric data can be obtained in real time by installing corresponding sensors. In general, urban green space big data can be obtained directly through network shared data or by installing corresponding detection devices.

[0066] The preprocessing device includes a data preprocessing module and a partitioning module. The preprocessing module is used to remove errors and duplicate data in big data. For example, if the data obtained by network sharing contains duplicate and erroneous data, it can be deleted. Partial missing data can also be supplemented by the preprocessing module, or the data can be filtered, standardized, etc., so that the data can be further calculated or processed.

[0067] The partition module is used to divide the management area into multiple sub-regions, establish a data set for each sub-region, and add the data related to each sub-region to the corresponding data set. In this embodiment, the total management area is divided into multiple sub-regions according to the administrative area division of urban management. In practical applications, the urban green space big data can also be supplemented or corrected according to the data shared by each sub-region.

[0068] Please combine Figure 2The risk identification device includes a partition risk identification module and an interactive risk identification module. The partition risk identification module is used to analyze the comprehensive risk value in the corresponding sub-region according to the data of each data set. Specifically, the partition risk identification module includes a color recognition model, a dynamic recognition model, a geological recognition model, a gas recognition model and a comprehensive calculation module.

[0069] The color recognition model is used to identify the green color of each sub-area based on dynamic images, and then identify the first risk value p of the presence of pests through the change of green color. 1 , and determine the types and population density of pests. When pest populations appear in urban green spaces, the most obvious change is the change in plant color, such as yellowing of plant leaves, black and yellow-brown spots on branches, etc. Different populations of pests have different effects on plant color. By constructing a color recognition model and using known pest big data, training is performed on the color changes caused by pest populations on different plants to obtain a recognition model that meets the test accuracy. The real-time green plant images are then input into the color recognition model to identify the types and population densities of pests that may exist in the corresponding green space, and then determine the risk value for the sub-region. For example, the probability of the presence of pests in a sub-region is y. 1 The damage level to plants in this sub-region is R 1 , the population density is E 1 , then the risk value p of this sub-region 1 It can be expressed as:

[0070]

[0071] In the formula, E 0 It is the population density when pests cause the greatest harm to green plants.

[0072] The dynamic recognition model is used to identify the second risk value p of pests in each sub-area based on dynamic images. 2 , and determine the types and population density of pests. The motion trajectory of pests is identified by dynamic capture, and then the types of pests present are determined based on the habits of the organisms in the green space and the recognition of the appearance of the organisms. At the same time, the population density of pests in the corresponding area is predicted based on the number of pests captured in the dynamic image.

[0073] The geological identification model is used to identify the geological changes in each sub-region based on geological data, and then identify the third risk value p of the presence of pests. 3. Changes in geological data are mainly reflected in soil properties, such as soil acidity, heavy metal content, soil quality changes, etc. Similar to the color recognition model, a geological recognition basic model can be constructed, trained using known harmful biological big data, retaining the recognition model that meets the test accuracy, and then outputting the corresponding harmful biological species and population density based on the geological data obtained in real time, and then determining the third risk value for the sub-region.

[0074] The gas identification model is used to identify the changes in gas content in each sub-region based on atmospheric data, and then identify the fourth risk value p where harmful organisms exist. 4 Pests will also affect the content of various components in the air. By real-time monitoring of atmospheric changes in urban green spaces, the probability of the presence of pests in the corresponding area and the harmfulness of the group can be determined, and the fourth risk value can be output.

[0075] The comprehensive calculation module is used to calculate the comprehensive risk value of each sub-region according to the preset weight. Z The calculation formula is expressed as:

[0076]

[0077] In the formula, ω 1 ,ω 2 ,ω 3 ,ω 4 are the weights set respectively.

[0078] The interactive risk identification module is used to calculate the deep risk value based on the comprehensive risk value of each sub-region and the mutual interference coefficient.

[0079] Specifically, the interactive risk identification module includes a mapping table, an interference coefficient calculation module and a deep risk calculation module.

[0080] The mapping table is used to find the corresponding damage level R according to the identified pest types and plant types in each sub-area. The mapping table can be generated based on the known pest types and the degree of damage caused to different types of plants. In the mapping table, the damage level is calculated based on the degree of damage caused by pest types at a uniform density to plants of the same area. For example, a density of c per acre i For 1 acre of A i Plant-like, the damage caused is α i The hazard level R can be expressed as:

[0081]

[0082] The interference coefficient calculation module is used to calculate the interference coefficient between each region based on the spacing, climate data and geological data of each sub-region. The interference coefficient k is expressed as:

[0083]

[0084] Where D is the preset standard spacing, d is the distance between two sub-areas, ρ 1 is the climate disturbance term, 2 is the geological disturbance term.

[0085] The depth risk calculation module is used to calculate the corresponding depth risk value according to the comprehensive risk value, hazard level and interference coefficient of each area. The depth risk value P D The calculation formula is expressed as:

[0086]

[0087] Where P Zi is the comprehensive risk value of the ith sub-region, N is the number of sub-regions, R j k is the degree of damage caused by pests in the jth sub-region to the i-th sub-region, j is the interference coefficient of the jth sub-region to the i-th sub-region, P Zj is the comprehensive risk value of the j-th sub-region.

[0088] The early warning module is used to determine whether the depth risk value of each sub-region is higher than a preset threshold, and if so, an alarm signal is issued. In some embodiments, the depth risk value is graded, and different levels of alarm signals are generated for different levels of depth risk values, thereby issuing a more urgent alarm signal for the sub-region with a higher depth risk value.

[0089] The management module is used to identify whether the prevention and control measures of each sub-area are completed on time. When the prevention and control measures of any sub-area are not completed on time, a prevention and control command is generated and sent to the corresponding operator.

[0090] Specifically, the management module includes a daily management module and a risk management module.

[0091] The daily management module is used to: 1. Generate prevention and control commands according to the preset prevention and control plan and send them to the responsible personnel of each sub-area. 2. Receive the prevention and control logs uploaded by each sub-area, and then check the prevention and control completion progress of each sub-area. When a sub-area fails to complete the prevention and control plan on time, generate an alarm command and send it to the responsible personnel and superior responsible personnel of the corresponding sub-area.

[0092] The risk management module is used to: 1. According to the deep risk value in each sub-area, query the corresponding prevention and control measures in a pre-stored prevention and control plan table, and then generate a prevention and control command and send it to the responsible personnel of the corresponding sub-area. 2. According to the prevention and control log feedback from each sub-area, determine whether each sub-area has completed the prevention and control measures, and if any sub-area fails to complete the prevention and control plan on time, generate an alarm command and send it to the responsible personnel and superior responsible personnel of the corresponding sub-area.

[0093] The prevention and control management method of this embodiment fully considers the destructiveness caused by different types of pests to different types of green plants. It identifies the multi-dimensional data of green spaces, analyzes the types and population densities of pests in green areas, and then analyzes the pest risk value of each green area. According to the mutual interference between areas, a deep risk value is obtained, which can more accurately reflect the harmfulness of pests in the current area. By collecting and processing data in real time, it can improve the early warning and treatment efficiency of pests and protect the green environment from being destroyed.

[0094] Example 2: Please refer to Figure 3 This embodiment provides a method for early warning and prevention and control of urban green space pest disasters, which can be applied to the early warning and prevention and control management system of urban green space pest disasters in embodiment 1. The prevention and control management method includes the following steps:

[0095] S1: Collect urban green space big data based on the management area. Urban green space big data includes dynamic images, climate data, geological data and atmospheric data.

[0096] S2: Preprocess the urban green space big data to remove erroneous and duplicate data, divide the management area into multiple sub-regions, and divide the urban green space big data into the data sets corresponding to each sub-region.

[0097] S3: Conduct risk identification for each sub-region and output the comprehensive risk value, pest species and population density of each sub-region.

[0098] Please combine Figure 4 The identification method of the comprehensive risk value specifically includes the following steps:

[0099] S311: Extract frames from the dynamic image to obtain multiple green space images. Identify the green space images to obtain the green space color changes in each sub-area. Identify the first risk value p of the presence of harmful organisms based on the green space color changes. 1 .

[0100] S312: Capture the movement trajectory and body size of small organisms in the dynamic image, and then identify the type and population density of the harmful organisms, and identify the second risk value p of the corresponding sub-region according to the type and population density of the harmful organisms2 .

[0101] S313: Identify the geological changes in each sub-region based on geological data, and then identify the third risk value p of the presence of harmful organisms 3 .

[0102] S314: Identify the change in gas content in each sub-region based on the atmospheric data, and then identify the fourth risk value p of the presence of harmful organisms 4 .

[0103] S315: Calculate the comprehensive risk value of each sub-region according to the preset weight. The comprehensive risk value P Z The calculation formula is expressed as:

[0104]

[0105] In the formula, ω 1 ,ω 2 ,ω 3 ,ω 4 are the weights set respectively.

[0106] Please combine Figure 5 , calculate the depth risk value of each sub-region according to the risk value of each sub-region and the mutual interference coefficient. The calculation method of the depth risk value is as follows:

[0107] S321: Find the corresponding hazard level R according to the identified harmful organism types and plant types in each sub-region.

[0108] S322: Calculate the interference coefficient between each region based on the distance between each sub-region, climate data and geological data. The interference coefficient k is expressed as:

[0109]

[0110] Where D is the preset standard spacing, d is the distance between two sub-areas, ρ 1 is the climate disturbance term, 2 is the geological disturbance term.

[0111] S323: Calculate the corresponding depth risk value according to the comprehensive risk value, hazard level and interference coefficient of each area. The depth risk value P D The calculation formula is expressed as:

[0112]

[0113] Where P Zi is the comprehensive risk value of the ith sub-region, N is the number of sub-regions, R j k is the degree of damage caused by pests in the jth sub-region to the i-th sub-region,j is the interference coefficient of the jth sub-region to the i-th sub-region, P Zj is the comprehensive risk value of the jth sub-region

[0114] S4: Determine whether the depth risk value of each sub-area is higher than the preset threshold. If yes, send out an alarm signal and generate a corresponding prevention and control command to be sent to the corresponding sub-area responsible person.

[0115] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0116] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. An urban green space harmful biological disaster early warning prevention and control management system, characterized in that: include: A collection device for collecting urban green space big data based on the management area; the urban green space big data includes dynamic images, climate data, geological data and atmospheric data; A preprocessing device, comprising a data preprocessing module and a partitioning module; the preprocessing module is used to remove errors and duplicate data in the big data; The partitioning module is used to divide the management area into a plurality of sub-areas, establish a data set for each of the sub-areas, and add data related to each sub-area to the corresponding data set; A risk identification device, including a partition risk identification module and an interactive risk identification module; The sub-area risk identification module is used to analyze the comprehensive risk value in the corresponding sub-area according to the data of each data set; The interactive risk identification module is used to calculate the depth risk value according to the comprehensive risk value of each sub-region and the mutual interference coefficient; The partition risk identification module includes: A color recognition model is used to identify the green color of each sub-area according to the dynamic image, and then identify the first risk value p1 of the presence of harmful organisms through the change of the green color, and determine the type and population density of the harmful organisms; A dynamic recognition model is used to capture the movement trajectory and body size of small organisms in the dynamic image, thereby identifying the type and population density of the harmful organisms, and identifying the second risk value p2 of the corresponding sub-region according to the type and population density of the harmful organisms; A geological identification model, used to identify geological changes in each sub-region according to the geological data, and then identify a third risk value p3 of the presence of harmful organisms; A gas identification model, used to identify the change of gas content in each sub-region according to the atmospheric data, and then identify a fourth risk value p4 of the presence of harmful organisms; The comprehensive calculation module is used to calculate the comprehensive risk value of each sub-region according to the preset weight; the comprehensive risk value P Z The calculation formula is expressed as: ； In the formula, ω1, ω2, ω3, and ω4 are the set weights respectively; The interactive risk identification module includes: A mapping table is used to find the corresponding damage level R according to the identified pest species and plant species in each sub-region; The interference coefficient calculation module is used to calculate the interference coefficient between each region according to the spacing, climate data and geological data of each sub-region; the interference coefficient k is expressed as: ； Where D is the preset standard separation, d is the distance between two sub-regions, ρ1 is the climate interference term, and ρ2 is the geological interference term; The depth risk calculation module is used to calculate the corresponding depth risk value according to the comprehensive risk value, hazard degree and interference coefficient of each area. The depth risk value P D The calculation formula is expressed as: ； Where P Zi is the comprehensive risk value of the ith sub-region, N is the number of sub-regions, R j k is the degree of damage caused by pests in the jth sub-region to the i-th sub-region, j is the interference coefficient of the jth sub-region to the i-th sub-region, P Zj is the comprehensive risk value of the j-th sub-region; The early warning module is used to determine whether the depth risk value of each sub-area is higher than the preset threshold, and if so, an alarm signal is issued; The management module is used to identify whether the prevention and control measures of each sub-area are completed on time. When the prevention and control measures of any sub-area are not completed on time, a prevention and control command is generated and sent to the corresponding operator.

2. The urban green space harmful biological disaster early warning prevention and control management system according to claim 1 is characterized in that: The management module comprises: The daily management module is used to:

1. Generate prevention and control commands according to the preset prevention and control plan and send them to the responsible personnel of each sub-area; 2. Receive the prevention and control logs uploaded by each sub-area, and then check the prevention and control completion progress of each sub-area. When a sub-area fails to complete the prevention and control plan on time, generate an alarm command and send it to the responsible personnel and superior responsible personnel of the corresponding sub-area; The risk management module is used to:

1. According to the deep risk value in each sub-area, query the corresponding prevention and control measures in a pre-stored prevention and control plan table, and then generate a prevention and control command and send it to the responsible person of the corresponding sub-area; 2. According to the prevention and control log feedback from each sub-area, determine whether each sub-area has completed the prevention and control measures, and when any sub-area fails to complete the prevention and control plan on time, generate an alarm command and send it to the responsible person and superior responsible person of the corresponding sub-area.

3. A method for early warning and prevention management of harmful biological disasters in urban green spaces, which is applied to an early warning and prevention management system for harmful biological disasters in urban green spaces as claimed in any one of claims 1 to 2, characterized in that: The steps include: S1: Collecting urban green space big data based on the management area; the urban green space big data includes dynamic images, climate data, geological data and atmospheric data; S2: pre-processing the urban green space big data, removing erroneous data and duplicate data therein, dividing the management area into multiple sub-areas, and dividing the urban green space big data into data sets corresponding to each sub-area; S3: Identify the risk of each sub-region, and output the comprehensive risk value, pest species and population density of each sub-region; calculate the deep risk value of each sub-region according to the risk value and mutual interference coefficient of each sub-region; the identification method of the comprehensive risk value is as follows: S311: extracting frames from the dynamic image to obtain a plurality of green space images; identifying the green space images to obtain the green space color changes in each sub-area; and identifying the first risk value p1 of the presence of harmful organisms according to the green space color changes; S312: capturing the movement trajectory and body size of the small organisms in the dynamic image, thereby identifying the type and population density of the harmful organisms, and identifying the second risk value p2 of the corresponding sub-region according to the type and population density of the harmful organisms; S313: Identify the geological changes of each sub-region according to the geological data, and then identify the third risk value p3 of the presence of harmful organisms; S314: Identifying the change in gas content in each sub-region according to the atmospheric data, and then identifying a fourth risk value p4 of the presence of harmful organisms; S315: Calculate the comprehensive risk value of each sub-region according to the preset weight; the comprehensive risk value P Z The calculation formula is expressed as: ； In the formula, ω1, ω2, ω3, and ω4 are the set weights respectively; The calculation method of deep risk value is as follows: S321: Find the corresponding harm level R according to the identified harmful organisms and plant species in each sub-region; S322: Calculate the interference coefficient between each region based on the distance between each sub-region, climate data and geological data; the interference coefficient k is expressed as: ； Where D is the preset standard separation, d is the distance between two sub-regions, ρ1 is the climate interference term, and ρ2 is the geological interference term; S323: Calculate the corresponding depth risk value according to the comprehensive risk value, hazard level and interference coefficient of each area. The depth risk value P D The calculation formula is expressed as: ； Where P Zi is the comprehensive risk value of the ith sub-region, N is the number of sub-regions, R j k is the degree of damage caused by pests in the jth sub-region to the i-th sub-region, j is the interference coefficient of the jth sub-region to the i-th sub-region, P Zj is the comprehensive risk value of the j-th sub-region; S4: Determine whether the depth risk value of each sub-area is higher than the preset threshold. If yes, send out an alarm signal and generate a corresponding prevention and control command to be sent to the corresponding sub-area responsible person.

Images