Urban tree encroachment emergency supervision system and method based on internet of things large model

Abstract

The present application relates to the technical field of multi-modal remote sensing, and particularly relates to an urban tree encroachment emergency supervision system and method based on an Internet of Things large model, which comprises the following steps: determining a potential target area; obtaining monitoring data corresponding to the potential target area; determining a trimming area based on the monitoring data and generating comprehensive trimming parameters corresponding to the trimming area; generating trimming instructions based on the comprehensive trimming parameters and sending them to intelligent trimming equipment; based on the trimming instructions, controlling the intelligent trimming equipment to control an intelligent trimming robot and / or a UAV to go to the trimming area based on the comprehensive trimming parameters, and controlling the valve of an inhibitor injection pump carried by the intelligent trimming robot to open and close to accurately inject soil, and / or driving a mechanical shear mounted on the UAV to physically cut off branches, so as to trim trees in the trimming area. The present application can realize prospective prevention and control and collaborative governance of the conflict risk between urban greening and infrastructure.

Description

Technical Field

[0001] This specification relates to the field of multimodal remote sensing technology, and in particular to an emergency monitoring system and method for urban tree encroachment based on a large Internet of Things (IoT) model. Background Technology

[0002] With the deepening of urbanization in my country, urban greening, as an important part of ecological civilization construction, is constantly increasing in scale and complexity. However, in the context of the coexistence of green vegetation and urban infrastructure, the expansion of tree root systems and the growth of tree canopies pose potential threats to underground pipelines, power lines, traffic signs, and other facilities. Specifically, tree roots may entangle, compress, or even penetrate underground pipelines during their natural growth process, causing not only physical damage but also accelerating pipeline corrosion and aging, leading to a series of operational failures such as gas leaks, water supply interruptions, communication signal attenuation, and power short circuits. At the same time, tall and lush branches and leaves can easily obstruct traffic signs and encroach on the safety distance of high-voltage lines, posing hidden dangers to public transportation safety and the stability of power supply.

[0003] Currently, the interaction between green vegetation and urban infrastructure relies heavily on manual inspections and experience-based judgments, lacking systematic and refined identification and assessment methods. Due to the highly concealed nature of vegetation growth and its long-term effects, traditional management models struggle to achieve early detection, accurate quantification, and trend prediction of potential encroachment risks, let alone support precise and proactive early warning and intervention.

[0004] Based on this, we hope to provide an emergency monitoring system and method for urban tree encroachment based on a large Internet of Things model. This system will integrate multimodal sensing data and rely on big data analysis and artificial intelligence technologies to create an intelligent monitoring and management system that can proactively prevent and collaboratively manage the risks of conflict between urban greening and infrastructure. Summary of the Invention

[0005] This specification provides one or more embodiments of an emergency monitoring system for urban tree encroachment based on an Internet of Things (IoT) big data model, including an emergency monitoring management platform configured to execute an emergency monitoring method for urban tree encroachment based on an IoT big data model.

[0006] This specification provides one or more embodiments of an emergency monitoring method for urban tree encroachment based on an Internet of Things (IoT) big data model. Implemented based on the urban tree encroachment emergency monitoring system, the method includes: determining potential target areas, where the potential target areas are pre-defined observation areas where trees may encroach on infrastructure; acquiring monitoring data corresponding to the potential target areas, the monitoring data reflecting the distribution of trees and infrastructure within the potential target areas; determining pruning areas based on the monitoring data and generating comprehensive pruning parameters corresponding to the pruning areas, the comprehensive pruning parameters including the pruning sequence and pruning sub-parameters of the pruning areas; generating pruning instructions based on the comprehensive pruning parameters and sending them to intelligent pruning equipment; and controlling the intelligent pruning equipment based on the pruning instructions to control an intelligent pruning robot and / or a drone to proceed to the pruning area, and controlling the opening and closing of the valve of an inhibitor injection pump carried by the intelligent pruning robot to precisely inject into the soil, and / or driving the mechanical shears mounted on the drone to physically cut branches, thereby pruning the trees within the pruning area.

[0007] This specification provides one or more embodiments of an emergency monitoring device for urban tree encroachment based on an Internet of Things (IoT) big data model, including a processor for executing the emergency monitoring method for urban tree encroachment as described in any of the preceding embodiments.

[0008] This specification provides one or more embodiments of a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the emergency monitoring method for urban tree encroachment as described in any of the above embodiments.

[0009] This specification has at least the following technical effects in one or more embodiments: (1) By pre-delineating potential target areas and using automated monitoring and intelligent maintenance equipment, proactive and intelligent closed-loop management of urban tree encroachment risk can be achieved, improving the efficiency and accuracy of urban greening maintenance supervision, effectively reducing the cost of manual inspection and the safety hazards of infrastructure failure due to tree encroachment; (2) By integrating easily obtainable ground tree branch distribution data with monitoring data of underground potential areas with high uncertainty, a collaborative monitoring system connecting the ground and underground can be constructed, using the ground situation to corroborate and correct the judgment of underground risks, improving the accuracy and reliability of underground tree encroachment risk prediction, and effectively reducing the misjudgment rate that may be caused by a single data source; (3) By integrating future weather conditions and the physical parameters of the infrastructure itself into the machine learning model, the risk assessment is upgraded from static geometric analysis to dynamic and forward-looking comprehensive prediction. The system can predict and prioritize the handling of vulnerable facility points facing higher risks under extreme weather conditions, realizing the leap from "passive response" to "proactive prevention", greatly improving the scientificity and forward-looking nature of emergency management. Attached Figure Description

[0010] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0011] Figure 1 This is a schematic diagram of an emergency monitoring and management platform according to some embodiments of this specification; Figure 2 This is an exemplary flowchart of an emergency monitoring method for urban tree encroachment, as shown in some embodiments of this specification; Figure 3 This is an exemplary schematic diagram of the trimming process of the first trimming area according to some embodiments of this specification; Figure 4 This is an exemplary schematic diagram of the trimming process for the second trimming area according to some embodiments of this specification. Detailed Implementation

[0012] To more clearly illustrate the technical solutions of the embodiments in this specification, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely some examples or embodiments of this specification. For those skilled in the art, these drawings can be applied to other similar scenarios without creative effort. Unless obvious from the context or otherwise specified, the same reference numerals in the drawings represent the same structures or operations.

[0013] It should be understood that the terms “system,” “device,” “unit,” and / or “module” used herein are one way to distinguish different components, elements, parts, sections, or assemblies at different levels. However, if other terms can achieve the same purpose, they may be replaced by other expressions.

[0014] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0015] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0016] Figure 1 This is an exemplary structural diagram of an emergency monitoring system for urban tree encroachment based on a large-scale Internet of Things model, as shown in some embodiments of this specification.

[0017] In some embodiments, such as Figure 1 As shown, the urban tree encroachment emergency monitoring system based on the Internet of Things (hereinafter referred to as the system) may include an emergency monitoring and management platform 130.

[0018] The Emergency Monitoring and Management Platform 130 refers to a digital monitoring and management platform for monitoring tree encroachment emergencies. Tree encroachment emergencies refer to sudden, destructive, and harmful tree encroachment incidents.

[0019] In some embodiments, the emergency monitoring and management platform 130 may be configured in a processor and / or server. The processor and / or server may process data and / or information acquired from other platforms. Based on this data, information, and / or processing results, the processor and / or server may execute program instructions to perform one or more functions described in this application.

[0020] In some embodiments, the emergency monitoring and management platform 130 includes interconnected sub-platforms and a data center. The sub-platforms can process data and / or information acquired from the data center.

[0021] In some embodiments, the sub-platform includes at least one of an emergency prevention sub-platform, an emergency monitoring sub-platform, a risk prevention sub-platform, and an emergency response sub-platform.

[0022] The emergency prevention sub-platform refers to a management platform for assessing and preventing tree encroachment emergencies.

[0023] The emergency monitoring sub-platform refers to a platform used to monitor, collect, and analyze data on tree encroachment emergency events.

[0024] The risk prevention sub-platform refers to a platform for identifying potential risks, assessing risk levels, and implementing risk reduction strategies.

[0025] The emergency response sub-platform refers to a platform used to coordinate, dispatch, and execute emergency plans after a tree encroachment emergency occurs.

[0026] In some embodiments, a data center includes a database, a data processing model library, and computing units.

[0027] Databases are used to collect, store, and manage large amounts of data related to emergency management. Examples include MySQL, PostgreSQL, InfluxDB, and Prometheus.

[0028] A data processing model library refers to a collection of data processing models used for emergency management data processing. In some embodiments, data processing models may include data update models, damage prediction models, etc. For an explanation of data update models, see [link to documentation]. Figure 3 For details regarding the damage prediction model, please refer to [link / reference]. Figure 4 And its contents.

[0029] A computing unit is a functional module used to perform arithmetic, logical, and other instruction operations. Computing units may include, but are not limited to, central processing units (CPUs).

[0030] In some embodiments, the system further includes an emergency monitoring user platform 110, an emergency monitoring service platform 120, an emergency monitoring sensor network platform 140, and an emergency monitoring perception and control platform 150.

[0031] An emergency monitoring user platform refers to an interactive platform for emergency management personnel and the public. In some embodiments, the emergency monitoring user platform may include at least one user interaction device, such as a mobile phone or computer.

[0032] An emergency monitoring service platform refers to a platform that provides emergency monitoring services. In some embodiments, the emergency monitoring service platform can be configured as a server that can interact with emergency monitoring user platforms and emergency monitoring management platforms (such as data centers). For example, after the public discovers an emergency incident involving tree encroachment, they use the emergency monitoring user platform to report the incident to the emergency monitoring service platform. The emergency monitoring service platform then reports the relevant incident and its impact assessment to the emergency monitoring management platform to facilitate response and decision-making by management departments.

[0033] An emergency monitoring sensor network platform refers to a platform for sensing and communicating emergency monitoring information in smart cities. It facilitates bidirectional data exchange and transmission between the emergency monitoring management platform (such as a data center) and the emergency monitoring perception and control platform. For example, an emergency monitoring sensor network platform may include communication equipment, servers, and various gateway devices. Smart city emergency monitoring information may include monitoring data of the target area, target events, and comprehensive adjustment parameters. For an explanation of the monitoring data and comprehensive adjustment parameters of the target area, please refer to [link to relevant documentation]. Figure 2 And its contents.

[0034] An emergency monitoring and control platform refers to an information processing platform for safety monitoring of various objects involved in emergency management. These objects can include motor vehicle lanes, underground pipelines, transportation hubs, etc. The platform can incorporate various monitoring, sensing, and interactive devices, such as cameras, drones, high-precision GPS, bioelectric sensors, and ground-penetrating radar.

[0035] In some embodiments of this specification, the urban tree encroachment emergency monitoring system can form an information operation closed loop among various functional platforms and operate in a coordinated and regular manner under the unified management of the emergency monitoring management platform, thereby realizing the informatization and intelligentization of tree encroachment emergency monitoring.

[0036] Figure 2 This is an exemplary flowchart illustrating an emergency monitoring method for urban tree encroachment, based on some embodiments of this specification. Figure 2 As shown, the process includes steps 210-250 below. In some embodiments, the process may be executed by an emergency monitoring and management platform.

[0037] Step 210: Identify potential target areas.

[0038] A potential target area refers to a pre-defined observation area where trees may potentially encroach on infrastructure. In some embodiments, the potential target area may include the ground area surrounding urban green belts and the underground area surrounding urban green belts, etc.

[0039] Infrastructure refers to a variety of facilities in an urban area. In some embodiments, infrastructure may include above-ground infrastructure (e.g., traffic signs on the ground) and underground infrastructure (e.g., underground pipe networks).

[0040] Step 220: Obtain monitoring data corresponding to the potential target area.

[0041] Monitoring data refers to data reflecting the current status, dynamic changes, and distribution of trees and infrastructure within a potential target area. In some embodiments, monitoring data may include first monitoring data, second monitoring data, and third monitoring data. The methods for acquiring different monitoring data vary. For more information, please refer to [link to relevant documentation]. Figures 3-4 Related descriptions.

[0042] Step 230: Determine the trimming area based on the monitoring data and generate the comprehensive trimming parameters corresponding to the trimming area.

[0043] A trimmed area refers to a potential target area that requires physical intervention (e.g., trimming). In some embodiments, a trimmed area may include areas in urban greenbelts where tree branches and leaves obstruct traffic signs, or areas in urban greenbelts where tree roots become entangled in pipe networks, etc.

[0044] The comprehensive trimming parameters refer to the trimming parameters used when trimming a potential target area. In some embodiments, the comprehensive trimming parameters may include the trimming order and trimming sub-parameters of the trimmed area.

[0045] The repair sequence refers to the planned repair order for all currently identified repair areas.

[0046] Pruning sub-parameters refer to the specific pruning parameters corresponding to each pruning area. In some embodiments, pruning sub-parameters may include the precise three-dimensional coordinates of the branches to be pruned when aboveground encroachment occurs, the length or range of pruning, the volume of canopy to be removed, etc., as well as the precise geographical location, operation method (e.g., injecting inhibitors or applying ultrasound), dosage and concentration of inhibitors, frequency and duration of ultrasound waves, etc., when suppressing underground encroachment occurs.

[0047] In some embodiments, the emergency monitoring and management platform can determine the repair area and generate comprehensive repair parameters based on multiple methods.

[0048] In some embodiments, the emergency monitoring and management platform can determine the trimming area and generate comprehensive trimming parameters based on the first vector database.

[0049] In some embodiments, the first vector database includes multiple sets of reference demand feature vectors and their corresponding reference trimming sub-parameters. For example, the emergency monitoring and management platform can construct reference demand feature vectors based on historical monitoring data of historical trimmed areas, and use the trimming sub-parameters corresponding to the historical trimmed areas that meet a first preset trimming condition as the reference trimming sub-parameters corresponding to the reference demand feature vectors. In some embodiments, the first preset trimming condition can be that after trimming the historical trimmed area through the trimming sub-parameters, no tree encroachment occurs for a continuous first preset period of time. In some embodiments, the first preset time can be preset based on human experience.

[0050] The emergency monitoring and management platform can construct demand feature vectors based on monitoring data of potential target areas. Based on these demand feature vectors, it retrieves target vectors from a first vector database. The target vectors are reference demand feature vectors whose vector similarity to the demand feature vectors is greater than a first preset similarity threshold. The vector similarity can be negatively correlated with the vector distance between the demand feature vector and the reference demand feature vector, and the vector distance can be determined based on cosine distance, etc. The first preset similarity threshold is set based on human experience.

[0051] In some embodiments, for a target region corresponding to a desired feature vector, if a corresponding target vector exists in the first vector database, then the target region is the trimmed region. In some embodiments, the trimming sub-parameters of the trimmed region can be determined based on the reference trimming sub-parameters of the target vector with the highest similarity to it.

[0052] In some embodiments, the emergency monitoring and management platform can sort the regions in descending order based on the highest vector similarity value corresponding to each trimmed region, and use this order as the trimming order of the trimmed regions; based on the trimming order and the trimming sub-parameters corresponding to each trimmed region, a comprehensive trimming parameter is constructed.

[0053] Step 240: Based on the comprehensive trimming parameters, generate trimming instructions and send them to the intelligent trimming device.

[0054] Intelligent trimming equipment refers to intelligent devices that perform trimming operations. In some embodiments, intelligent trimming equipment may include intelligent trimming robots, drones, linear actuators, high-frequency sound wave generators, etc.

[0055] Trimming commands refer to instructions that control intelligent trimming equipment to perform trimming operations. In some embodiments, trimming commands may include instructions to control the opening and closing of valves on the inhibitor injection pump mounted on the intelligent trimming robot, or to drive mechanical shears mounted on a drone to physically cut tree branches.

[0056] Step 250: Based on the trimming instructions, control the intelligent trimming equipment to move the intelligent trimming robot and / or drone to the trimming area based on the comprehensive trimming parameters, and control the opening and closing of the valve of the inhibitor injection pump carried by the intelligent trimming robot to inject the soil precisely, and / or drive the mechanical shears mounted on the drone to physically cut off the branches in order to trim the trees in the trimming area.

[0057] In some embodiments of this specification, by pre-delineating potential target areas and employing automated monitoring and intelligent pruning equipment, proactive and intelligent closed-loop management of the risk of urban tree encroachment can be achieved, improving the efficiency and accuracy of urban greening maintenance supervision, effectively reducing the cost of manual inspections and the safety hazards of infrastructure failures caused by tree encroachment.

[0058] It should be noted that the above description of the process is for illustrative purposes only and does not limit the scope of this specification. Those skilled in the art can make various modifications and changes to the process under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0059] Figure 3 This is an exemplary flowchart illustrating the trimming of the first trimming region according to some embodiments of this specification.

[0060] like Figure 3 As shown, the process for repairing the first repair area includes the following steps. In some embodiments, the process for repairing the first repair area may be executed by an emergency monitoring and management platform.

[0061] In some embodiments, the potential target area includes one or more above-ground potential areas and one or more underground potential areas. See [link to description of potential target areas] Figure 2 And its description.

[0062] Step 310: Obtain the first monitoring data of the potential underground area.

[0063] A potential above-ground area refers to an area on the ground where trees may encroach on infrastructure. Examples include driveways and transportation hubs. In some embodiments, the potential above-ground area includes tree branches. Tree branches refer to the portion of a tree's trunk or stem that is above ground.

[0064] A potential underground area refers to an area below ground where trees may encroach on infrastructure. Examples include underground pipe networks. In some embodiments, the potential underground area includes underground tree root systems and underground infrastructure. Underground tree root systems refer to the root portion of a tree located below ground level. Underground infrastructure includes infrastructure located below ground level, such as gas pipelines, water supply networks, and fiber optic cables.

[0065] The primary monitoring data refers to relevant monitoring data for underground potential areas. This data reflects the distribution of tree root systems and underground infrastructure within these areas.

[0066] In some embodiments, the emergency monitoring and management platform can acquire initial monitoring data based on an intelligent trim robot equipped with high-precision GPS, ground-penetrating radar (GPR), or bioelectric potential sensors.

[0067] For example, the emergency monitoring and management platform can use the antenna of ground-penetrating radar to continuously transmit and receive electromagnetic waves into potential underground areas to collect GPR data in real time; use GPS to label the collected GPR data with geographical location and timestamps to obtain GPS trajectory data; control intelligent trimming robots to upload the collected GPR data and GPS trajectory data to the emergency monitoring and management platform in real time or in batches; match the uploaded GPR data with GPS trajectory data to generate GPR profile maps with geographical location and timestamps, and use GPR processing software to identify the content categories, horizontal positions, and burial depths in the GPR profile maps.

[0068] In some embodiments, content categories may include pipelines and root systems. Pipelines can be used to characterize the distribution of underground infrastructure, and root systems can be used to characterize the distribution of tree root systems. The emergency monitoring and management platform can label signals with hyperbolic characteristics in the GPR profile as pipelines, and label more chaotic and irregular clusters of reflected signals in the GPR profile as root systems. Existing technologies can be selected for GPR processing software, which will not be elaborated upon here. For an explanation of the intelligent trimming robot, see [link to documentation]. Figure 2 And its contents.

[0069] Step 320: Based on the first monitoring data, determine whether the underground potential area is the first repair area.

[0070] The first correction zone refers to the repair area below ground level.

[0071] In some embodiments, the emergency monitoring and management platform can acquire the location and depth information of pipelines and root systems respectively, and integrate them into a 3D map. Based on the integrated 3D map, it calculates the 3D spatial distance between each root system and the nearest pipeline. In response to the existence of at least one 3D spatial distance less than or equal to a trimming distance threshold in a potential underground area, the potential underground area is identified as a first trimming area. The trimming distance threshold can be preset based on historical experience.

[0072] Step 330: In response to the underground potential area being the first trimming area, determine the first trimming sub-parameter of the first trimming area based on the first monitoring data.

[0073] Given two scenarios—that an underground potential area is the first adjustment area and that an underground potential area is not the first adjustment area—the emergency monitoring and management platform can determine the first adjustment sub-parameter of the underground potential area when it is determined to be the first adjustment area.

[0074] The first trimming sub-parameter refers to the parameters related to the injection of growth inhibitors when trimming the first trimming area. In some embodiments, the first trimming sub-parameter includes one or more soil areas to be treated and first treatment parameters for the soil areas to be treated. The first treatment parameters include the dosage, concentration, and injection depth of the growth inhibitor.

[0075] The soil area to be treated refers to the soil area that needs to be injected with growth inhibitors. In some embodiments, the emergency monitoring and management platform can acquire a three-dimensional map determined based on the first monitoring data, divide the profile of the three-dimensional map into multiple candidate soil areas; calculate the root density of the same candidate soil area at multiple time points, and determine the root growth rate based on the difference in root density at multiple time points; acquire multiple three-dimensional spatial distances between the root system and the pipeline in each candidate soil area, and determine the three-dimensional spatial distance with the smallest distance value as the minimum distance, wherein if the root system is in direct contact with the pipeline, the minimum distance is 0; and determine the candidate soil area whose root density meets the first treatment condition and the root growth rate or whose minimum distance meets the second treatment condition as the soil area to be treated.

[0076] The first processing condition may include: root density greater than a preset density threshold. The second processing condition may include: root growth rate greater than a preset growth rate or minimum distance less than a preset minimum distance. The preset density threshold, preset growth rate, and preset minimum distance can be preset based on historical experience.

[0077] Root density refers to the density of roots within a soil region. In some embodiments, the emergency monitoring and management platform can determine the percentage of root area to the total profile area in each candidate soil region, and define this percentage as the root density of the candidate soil region.

[0078] Root growth rate refers to the rate at which roots grow within a soil area. In some embodiments, the emergency monitoring and management platform can obtain the difference in root density between a first time point and a second time point, as well as the time difference between the first time point and the second time point, and determine the root growth rate as the ratio of the difference in root density to the time difference. Both the first time point and the second time point are historical time points, with the first time point preceding the second time point. The interval between the two can be preset based on human experience, such as 1 day.

[0079] Growth inhibitors are agents used to control the root growth of trees. Examples include trifluralin, pyrimidine alcohol, and paclobutrazol.

[0080] In some embodiments, the emergency monitoring and management platform can determine the first treatment parameters of the soil area to be treated based on the root density, root growth rate and minimum distance of the soil area to be treated through a first preset table.

[0081] The first preset table is a mapping table of root density, root growth rate, minimum distance between roots and pipelines, and the first treatment parameter.

[0082] The first preset table can be constructed using historical data or human experience. In some embodiments, the historical data may include historical data that meets a first preferred condition. The first preferred condition may include: after the soil area to be treated is adjusted by the first treatment parameters, within a preset time period, the minimum distance between the roots and the pipeline in the soil area to be treated is greater than the adjustment distance threshold. The preset time period may be preset based on historical experience.

[0083] Step 340: Following the first trimming sequence, for the first trimming area, based on the first trimming sub-parameters, control the intelligent trimming robot to inject growth inhibitors into the soil area to be treated in the first trimming area.

[0084] The first correction order refers to the order in which the soil areas to be treated are processed within the first trimming area. In some embodiments, the processor can obtain the distance between the intelligent trimming device and each soil area to be treated, sort the distances from closest to furthest, and determine the sorting result as the first trimming order.

[0085] In some embodiments, the emergency monitoring and management platform can control the intelligent trimming robot to navigate to a designated location according to a first trimming sequence; control the linear actuator to press the injection probe down into the soil area to be treated until the depth sensor reports that the injection depth has been reached; and control the precision metering pump to inject growth inhibitors according to the dosage and concentration in the first correction sub-parameter.

[0086] In some embodiments of this specification, by determining the soil area to be treated, the risk of underground root encroachment can be accurately located; by quantifying the risk of underground root encroachment and generating a first trimming sub-parameter including dosage, concentration, and injection depth, targeted and minimally invasive precise inhibition of tree roots can be achieved. This not only effectively controls the risk of underground encroachment but also minimizes the negative impact of growth inhibitors on the overall health of trees and the surrounding environment, avoiding the high costs and social interference of traditional excavation operations.

[0087] In some embodiments, the emergency monitoring and management platform can also, according to the first trimming sequence, control the high-frequency acoustic wave generator to send target acoustic waves to the soil area to be treated based on the first trimming sub-parameters in the first trimming area.

[0088] High-frequency sound waves may alter soil structure, increase soil porosity, and promote the uniform distribution of growth inhibitors in the soil, making them easier for the soil or plant roots to absorb in the target area. In existing technologies, sound waves of specific frequencies have an impact on plant growth; for example, specific frequencies can promote or inhibit specific cell activities, thereby indirectly helping to control plant growth; or, for example, specific frequencies can have a synergistic effect with growth inhibitors. Furthermore, soil microorganisms are crucial for plant growth, and high-frequency sound waves may affect the soil microbial community, thereby indirectly influencing plant growth.

[0089] In some embodiments, high-frequency sound waves can be sound waves with frequencies exceeding 4000 Hz.

[0090] In some embodiments, the first trimming sub-parameter further includes a second treatment parameter for the soil area to be treated. The second treatment parameter includes the target frequency, amplitude, and duration of the target sound wave. In some embodiments, the emergency monitoring and management platform can determine the second treatment parameter for the soil area to be treated based on the root density, root growth rate, and minimum distance of the soil area to be treated, using a second preset table.

[0091] The second preset table is a mapping table of root density, root growth rate, minimum distance between roots and pipelines, and the second treatment parameter. The second preset table can be constructed using historical data or human experience. In some embodiments, historical data may include historical data that meets the second preferred condition. The second preferred condition may include: after the soil area to be treated is adjusted by the second treatment parameter, within a preset time period, the minimum distance between the roots and pipelines in the soil area to be treated is greater than a adjustment distance threshold. For related explanations of the preset time and adjustment distance threshold, please refer to the relevant description in step 330 above.

[0092] The target acoustic wave refers to the acoustic wave emitted to the soil area to be treated. In some embodiments, the target acoustic wave may be emitted by a high-frequency acoustic wave generator.

[0093] A high-frequency acoustic generator is a device that interferes with or inhibits plant root growth by emitting mechanical sound waves of a specific frequency. For example, a high-frequency acoustic generator can emit ultrasonic waves of 40–60 kHz into the soil around a pipe to interfere with root growth.

[0094] In some embodiments, the emergency monitoring and management platform can control a high-frequency sound wave generator to emit target sound waves according to the target frequency, amplitude, and duration of action to suppress the root system of trees.

[0095] In some embodiments of this specification, by combining biological inhibitors with targeted acoustic suppression, a more efficient and durable trimming pattern can be constructed, which more thoroughly interferes with root growth, improves the suppression effect and durability of a single trimming operation, and thus reduces the frequency and total cost of long-term maintenance.

[0096] In some embodiments, the emergency monitoring and management platform can acquire second monitoring data of the underground potential area; and update the first monitoring data based on the first monitoring data and the second monitoring data; and determine whether the underground potential area is the first remediation area based on the updated first monitoring data.

[0097] The second monitoring data refers to the branch and trunk distribution data of trees on the ground corresponding to the underground subsurface area. In some embodiments, the second monitoring data may include high-precision image data of trees on the ground, their growth intensity, and their growth range.

[0098] In some embodiments, the emergency monitoring and management platform can acquire high-precision image data using drones.

[0099] Growth intensity refers to the vigor of a tree and is used to quantify the tree's health status and the level of photosynthetic activity.

[0100] In some embodiments, the emergency monitoring and management platform can use a multispectral camera mounted on a drone to simultaneously capture the reflectance data of trees on the ground in both the near-infrared (NIR) and red (Red) bands. Healthy plant chlorophyll strongly absorbs red light used for photosynthesis, while its leaf cell structure strongly reflects near-infrared light. Therefore, the higher the NIR reflectance and the lower the Red reflectance, the healthier the plant, and the higher the Normalized Difference Vegetation Index (NDVI). The emergency monitoring and management platform can calculate the NDVI value of each pixel using the following formula: NDVI = (NIR - Red) / (NIR + Red). The platform can then statistically analyze the NDVI values ​​of all pixels covered by the tree canopy and use the average NDVI value as the growth intensity of the tree.

[0101] The growth range refers to the growth space of a tree, used to quantify the scale of the tree in physical space. In some embodiments, the emergency monitoring and management platform can segment high-resolution orthophotos based on segmentation algorithms, automatically identify and delineate the tree crown outline, and calculate the area of ​​the crown outline projected onto a 3D map. Since the area of ​​the crown outline is positively correlated with the development of the tree's root system, the emergency monitoring and management platform can determine the actual area of ​​the crown outline as the growth range. Segmentation algorithms may include U-Net, threshold segmentation algorithms, etc.

[0102] In some embodiments, the emergency monitoring and management platform can update the first monitoring data by querying a first vector library based on the first and second monitoring data. For example, the platform can construct a target feature vector based on the first and second monitoring data, query a second feature vector in the second vector library that meets the matching conditions as a reference vector, and determine the updated first monitoring data based on the label corresponding to the reference vector. Matching conditions include the highest similarity between vectors. Vector similarity is negatively correlated with vector distance. Vector distance includes Euclidean distance, etc.

[0103] In some embodiments, the second vector library can be pre-configured based on historical data, including multiple second feature vectors and a label corresponding to each second feature vector. The second feature vector refers to a feature vector constructed based on historical first and second monitoring data of historical underground potential areas. The label can be the updated first monitoring data corresponding to the second feature vector.

[0104] In some embodiments, the emergency monitoring and management platform can acquire first and second monitoring data of the soil in the potential underground area before trees are planted using drones and ground-penetrating radar, and acquire first monitoring data of the soil after trees are planted using ground-penetrating radar; the second monitoring data of the soil before trees are planted and the first monitoring data of the soil after trees are planted are used as a second feature vector, and the first monitoring data of the soil before trees are planted is used as the label corresponding to the second feature vector.

[0105] In some embodiments, the emergency monitoring and management platform can also determine the updated first monitoring data through a data update model, as detailed below.

[0106] In some embodiments, the emergency monitoring and management platform can construct a green infrastructure map based on the first monitoring data and the second monitoring data, the green infrastructure map including nodes and edges; based on the first monitoring data, the second monitoring data and the green infrastructure map, the updated first monitoring data is determined through a data update model.

[0107] A green infrastructure map refers to a map representing the status of green infrastructure and can be used to determine updated first monitoring data. In some embodiments, the green infrastructure map consists of nodes and edges, where nodes include a first node, a second node, and a third node, and edges are undirected edges.

[0108] In some embodiments, the emergency monitoring and management platform can determine the first node, the second node, the third node, and the edges connecting the nodes based on the first monitoring data and the second monitoring data, in order to construct a green infrastructure map.

[0109] The first node refers to a node representing underground infrastructure. Examples include underground pipelines, cables, and critical infrastructure points. Critical infrastructure points can include valves, manholes, and joints.

[0110] In some embodiments, the emergency monitoring and management platform can acquire pipelines from the first monitoring data and divide the continuous pipelines into multiple segments based on segmentation conditions, with each segment corresponding to a first node. Segmentation conditions may include: segmentation based on a preset segmentation distance, or segmentation based on critical infrastructure points. The preset segmentation distance can be determined manually, for example, 5 meters.

[0111] In some embodiments, the attributes of the first node may include node ID, facility category of underground infrastructure, three-dimensional coordinates of the node's starting point, center point, and ending point, etc.

[0112] In some embodiments, the attributes of the first node include physical parameters of the underground infrastructure.

[0113] Physical parameters refer to data related to the physical condition of underground infrastructure. Examples include pipeline diameter, service life of underground infrastructure, frequency of maintenance, and the date of the most recent maintenance.

[0114] In some embodiments of this specification, by assigning detailed physical parameters to the attributes of the first node in the green infrastructure map, the inherent vulnerability of underground infrastructure is introduced as a key variable into the data update model. This allows subsequent updates of the first monitoring data using the data update model to not only determine whether tree roots will come into contact with underground infrastructure, but also to predict whether such contact will cause serious consequences, thus making decisions more focused on actual potential losses.

[0115] The second node refers to the node representing the root system of underground trees.

[0116] In some embodiments, the emergency monitoring and management platform can acquire the root systems of trees from the first monitoring data, cluster multiple root systems that are less than the clustering distance and have similar characteristics to obtain root clusters, and identify the root clusters as second nodes. The emergency monitoring and management platform can also use the tree's main root as a second node. The clustering distance can be determined manually. Similar characteristics may include consistent root growth direction. In some embodiments, the emergency monitoring and management platform can determine the root growth direction based on image data, identifying root systems with consistent growth directions as multiple root systems with similar characteristics.

[0117] In some embodiments, the attributes of the second node may include node ID, three-dimensional coordinates of the centroid of the root cluster, root density, etc.

[0118] The third node refers to the node representing the trees on the ground.

[0119] In some embodiments, the emergency monitoring and management platform can determine the distribution of trees on the ground based on the second monitoring data, with each tree corresponding to a third node.

[0120] In some embodiments, the attributes of the third node include node ID, growth intensity, growth range, and average annual growth rate. Average annual growth rate refers to the average increase in the tree's growth range each year. The emergency monitoring and management platform can determine the average annual growth rate as the ratio of the difference between two growth ranges to the time difference between the two growth ranges.

[0121] In some embodiments, multiple nodes may be connected by edges. An edge may include a first edge, a second edge, and a third edge.

[0122] The first edge refers to the undirected edge representing the connection relationship between the first nodes. In some embodiments, when there is a physical connection between two underground infrastructures corresponding to two first nodes, the two first nodes are connected based on the first edge. For example, if two gas pipelines are interconnected, the first nodes corresponding to the two gas pipelines are connected based on the first edge.

[0123] The second edge refers to the undirected edge representing the correspondence between underground tree roots and above-ground trees. In some embodiments, when there is a physical connection between the underground tree roots corresponding to the second node and the above-ground tree corresponding to the third node, that is, the underground tree roots corresponding to the second node belong to the tree corresponding to the third node, then the second node and the third node are connected based on the second edge.

[0124] The third edge refers to an undirected edge representing the distance relationship between underground infrastructure and underground tree root systems. In some embodiments, when the distance between the underground tree root system corresponding to the second node and the underground infrastructure corresponding to the first node is less than a preset distance threshold, the second node and the first node are connected based on the third edge. The preset distance threshold can be determined based on human experience.

[0125] In some embodiments, the emergency monitoring and management platform can construct a green infrastructure map based on the first node, the second node, the third node, and the first, second, and third sides connecting the nodes.

[0126] In some embodiments, the emergency monitoring and management platform can determine the updated first monitoring data based on the first monitoring data, the second monitoring data, and the green infrastructure map through a data update model.

[0127] A data update model refers to a model used to determine the updated first monitoring data. In some embodiments, the data update model can be a machine learning model. For example, the structure of the data update model can be a graph neural network (GNN) model. In some embodiments, the input of the data update model may include first monitoring data, second monitoring data, and a greening infrastructure map, and the output may include the updated first monitoring data.

[0128] In some embodiments, the emergency monitoring and management platform can train and construct a data update model using a large number of training samples and corresponding training labels. In some embodiments, the emergency monitoring and management platform can acquire a training dataset, which includes multiple first training samples and a first training label corresponding to each first training sample, and the emergency monitoring and management platform can perform multiple rounds of iteration.

[0129] At least one iteration includes: selecting one or more first training samples from the training dataset; inputting the first training samples with the first training labels into the initial data update model; obtaining the output of the initial data update model; substituting the training labels of one or more training samples and the output of the initial data update model into a preset loss function; and iteratively updating the parameters of the initial data update model using gradient descent or other methods based on the value calculated by the loss function. Model training is complete when preset conditions are met, resulting in a trained data update model. Preset conditions may include loss function convergence, the number of iterations reaching a threshold, etc.

[0130] In some embodiments, the emergency monitoring and management platform can construct the first training sample and the corresponding first training label based on historical data in various ways.

[0131] In some embodiments, the emergency monitoring and management platform can identify multiple preferred monitoring samples from historical data and construct a first training sample and a corresponding first training label based on the preferred monitoring samples.

[0132] In some embodiments, the preferred monitoring samples include underground potential areas that meet the preferred conditions, and historical first monitoring data and historical second monitoring data corresponding to the underground potential areas. The emergency monitoring and management platform can construct a historical greening infrastructure map based on the historical first monitoring data and historical second monitoring data, and use the historical first monitoring data, historical second monitoring data, and historical greening infrastructure map as the first training samples. The preferred conditions may include: the number of times the underground potential area has been repaired exceeds a preset number of repairs. The preset number of repairs can be determined manually. The first training labels can be obtained through manual annotation. For example, operators can excavate underground potential areas that meet the preferred conditions. After the pipelines are dug up and the tree roots are exposed, a 3D laser scanner or a high-precision total station is used to map the exposed pipelines and roots. The actual distribution of tree roots and underground infrastructure is recorded manually, and the actual distribution of tree roots and underground infrastructure is used as the first training labels.

[0133] In some embodiments, the emergency monitoring and management platform can acquire multiple historical first monitoring data and historical second monitoring data, overlay, merge, and visualize these multiple historical first monitoring data and historical second monitoring data on the same three-dimensional map, and construct a historical greening infrastructure map based on the historical first monitoring data and historical second monitoring data. The historical first monitoring data, historical second monitoring data, and historical greening infrastructure map are used as the first training labels. The three-dimensional map and historical greening infrastructure map are then collaboratively interpreted by humans. For example, it is determined whether there are problems with the root system, and the root system is adjusted. The distribution of the adjusted tree root system and underground infrastructure is used as the first training label.

[0134] In some embodiments, the emergency monitoring and management platform can obtain historical accident reports, retrieve historical first and second monitoring data of the accident site prior to the incident, as well as the corresponding historical greening infrastructure map, and use them as the first training sample; based on photos and measurement data in historical accident reports and maintenance records, it can determine the distribution of tree roots and underground infrastructure after maintenance, and use the distribution of tree roots and underground infrastructure after maintenance as the first training label. Historical accident reports refer to reports of infrastructure damage accidents caused by tree root encroachment in cities. Infrastructure damage accidents can include pipe ruptures, cable failures, etc.

[0135] In some embodiments of this specification, by constructing a green infrastructure map containing multiple types of nodes above and below ground, a rich contextual information and complex relationships between entities are provided for the graph neural network. The graph neural network can perform deep reasoning based on the green infrastructure map, effectively capturing non-local correlation effects such as "how tree growth affects pipelines through the root system", thereby significantly improving the accuracy and comprehensiveness of the data update model in judging the risk of tree encroachment in complex scenarios, and providing a more reliable data foundation for subsequent decision-making on confirming the pruning area and pruning sub-parameters.

[0136] In some embodiments, the emergency monitoring and management platform can determine whether an underground potential area is a first repair area based on updated first monitoring data. The method for determining whether an underground potential area is a first repair area is described in step 320 and its related description.

[0137] In some embodiments of this specification, by fusing readily available data on the distribution of tree branches on the ground with monitoring data on potential underground areas with higher uncertainty, a collaborative monitoring system connecting the above-ground and underground can be constructed. This system uses the situation on the ground to corroborate and correct the judgment of underground risks, improving the accuracy and reliability of predicting the risk of underground tree encroachment and effectively reducing the misjudgment rate that may be caused by a single data source.

[0138] Figure 4 This is an exemplary schematic diagram illustrating the trimming process of the second trimming area according to some embodiments of this specification. Figure 4 As shown, the trimming process for the second trimming area includes steps 410-450. In some embodiments, the trimming process for the second trimming area may be executed by an emergency monitoring and management platform.

[0139] Step 410: Obtain third monitoring data of the potential area above ground.

[0140] The third monitoring data refers to the distribution data of trees and infrastructure on the ground corresponding to the potential area above ground. In some embodiments, the third monitoring data may include real-time high-precision image data of the potential area above ground, growth intensity, and growth range, etc.

[0141] In some embodiments, the real-time high-precision image data of the third monitoring data can be acquired based on drone photography. For example, a drone can be used to conduct high-precision aerial photography, quickly capturing a series of orthophotos, and then stitching them together in real time or afterward into a complete orthophoto map with precise geographic coordinates.

[0142] For information on how to obtain the growth intensity and growth range in the third monitoring data, please refer to the method for obtaining the second monitoring data.

[0143] For more information on potential above-ground areas, please refer to [link / reference]. Figure 3 Related descriptions.

[0144] Step 420: Based on the third monitoring data, determine whether a target event has occurred in the potential area on the ground.

[0145] A target event refers to an event in which trees encroach on infrastructure. In some embodiments, a target event may include an event in which trees obstruct or damage infrastructure. For example, leaves obscuring road signs, traffic lights, etc.

[0146] In some embodiments, the emergency monitoring and management platform can determine whether a target event has occurred in a potential area on the ground based on third-party monitoring data through various methods.

[0147] In some embodiments, the presence of trees obstructing infrastructure can be determined through manual observation. For example, leaves or branches may obscure road signs, causing incomplete display of road sign information when viewed from the front.

[0148] In some embodiments, the emergency monitoring and management platform can process orthophotos using existing image models (e.g., Mask R-CNN, U-Net, etc.) to automatically identify and "color-code" different elements in the image. For example, tree canopy areas (marked in green), power lines (marked in red), and traffic signs (marked in blue) can be segmented separately. After processing, a clear semantic segmentation map is obtained, in which all targets are accurately classified and located. Then, it is checked whether any pixel is simultaneously marked as "tree canopy area" and "power lines," "traffic signs," or other infrastructure. If at least one pixel is marked simultaneously, it is determined that encroachment has occurred.

[0149] Step 430: In response to the occurrence of a target event in the potential area on the ground, the potential area on the ground is identified as the second trimming area.

[0150] The second trimming area refers to the area on the ground that needs to be trimmed. In some embodiments, the second trimming area may include areas where foliage obscures traffic lights, etc.

[0151] Given two scenarios—that a target event has occurred in a potential area on the ground and that a target event has not yet occurred in a potential area on the ground—in some embodiments, in response to a target event occurring in a potential area on the ground, the emergency monitoring and management platform can determine the area where encroachment has occurred as the second remediation area.

[0152] Step 440: In response to the potential area on the ground being the second trimming area, the second trimming sub-parameter of the second trimming area is determined based on the third monitoring data.

[0153] The second trimming sub-parameter refers to the trimming parameter corresponding to the second trimming area. In some embodiments, the second trimming sub-parameter may include the cutting area (e.g., the physical location of the branch to be trimmed), etc.

[0154] Given that there are two scenarios—a potential above-ground area that is the second trimming area and a potential above-ground area that is not the second trimming area—in some embodiments, in response to a potential above-ground area being the second trimming area, the emergency monitoring and management platform can determine its corresponding second trimming sub-parameter based on various methods.

[0155] In some embodiments, the emergency monitoring and management platform can determine the second trimming area and generate the second trimming sub-parameters based on the third vector database.

[0156] In some embodiments, the third vector database includes multiple sets of reference demand feature vectors and their corresponding reference second trimming sub-parameters. For example, the emergency monitoring and management platform can construct reference demand feature vectors based on historical third monitoring data of historical second trimming areas, and use the second trimming sub-parameters corresponding to the historical second trimming areas that meet the third preset trimming conditions as the reference second trimming sub-parameters corresponding to the reference demand feature vectors. In some embodiments, the third preset trimming condition can be that after trimming the historical second trimming area through the second trimming sub-parameters, there is no tree encroachment for a continuous third preset time period. In some embodiments, the third preset time period can be preset based on human experience.

[0157] The emergency monitoring and management platform can construct demand feature vectors based on third-party monitoring data of potential areas above ground. Based on these demand feature vectors, it retrieves target vectors from a third-party vector database. The target vector is the reference demand feature vector with the highest vector similarity among those with a vector similarity greater than a third preset similarity threshold. Vector similarity can be negatively correlated with the vector distance between the demand feature vector and the reference demand feature vector, and this vector distance can be determined based on cosine distance, etc. The third preset similarity threshold is set based on human experience.

[0158] In some embodiments, the emergency monitoring and management platform can construct second trimming sub-parameters based on the shearing region corresponding to each second trimming region.

[0159] Step 450: Following the second trimming sequence, based on the second trimming sub-parameters, control the drone to trim the trees within the trimming area of ​​the second trimming area.

[0160] The second repair sequence refers to the repair order planned for the currently identified second repair area.

[0161] In some embodiments, the emergency monitoring and management platform can determine the second repair sequence based on multiple methods. In some embodiments, the emergency management platform can use the order of the drones' distance from each second repair area, from closest to furthest, as the second repair sequence for the second repair areas.

[0162] In some embodiments, the emergency monitoring and management platform can send instructions containing the image coordinates of the trimmed area to a drone based on a second trimming sequence. The drone flies over the target, uses its onboard camera to match the received image coordinates, locks the physical range of the trimmed area, and combines its own close-range sensors (e.g., visual or millimeter-wave radar) to accurately align with the target tree branch and perform trimming according to the second trimming sequence.

[0163] In some embodiments of this specification, by using drones for automated aerial monitoring and precise pruning operations, the risk of tree encroachment on the ground can be addressed remotely, unmannedly, and precisely, improving the safety and efficiency of high-altitude operations and effectively reducing the labor costs, safety risks, and impact on ground traffic required for traditional manual pruning.

[0164] In some embodiments, the emergency monitoring and management platform can predict the estimated time of damage based on third monitoring data and a damage prediction model; and determine a second repair sequence based on the estimated time of damage.

[0165] The estimated damage time refers to the duration over which trees cause substantial damage to above-ground infrastructure. In some embodiments, the estimated damage time can be one week, one month, etc. In some embodiments, the longer the estimated damage time, the earlier the second trimming order is placed.

[0166] The destruction prediction model can be a machine learning model, such as a recurrent neural network (RNN).

[0167] In some embodiments, the input to the damage prediction model may include third-party monitoring data, and the output of the damage prediction model may include an estimated time of damage.

[0168] In some embodiments, the damage prediction model can be trained using multiple second training samples with second labels. Each set of second training samples consists of historical third monitoring data of the potential area above the sample, and the corresponding second label represents the actual time of damage to the potential area above the sample.

[0169] In some embodiments, the potential area above ground of the second training sample can be determined based on the area that has been damaged in the historical third monitoring data. The historical third monitoring data of the sample is used as the second training sample, and the monitoring time is recorded as the first monitoring time. By querying the historical third monitoring data of the potential area above ground of the sample, the monitoring time corresponding to the most recent third monitoring data that has not caused damage is obtained and recorded as the second monitoring time. Then, the second label is determined based on the difference between the first monitoring time and the second monitoring time.

[0170] The training process for the destruction prediction model can be found in the training process of the data update model above.

[0171] In some embodiments of this specification, by introducing a damage prediction model to quantify the estimated damage time, task priorities can be determined based on the damage duration. This ensures that limited repair resources can be prioritized for allocation to the most urgent areas and those closest to where substantial damage will occur, thereby improving the efficiency of emergency response and resource utilization, and reducing the probability of serious damage incidents.

[0172] In some embodiments, the inputs to the damage prediction model may also include weather data for future periods and physical parameters of above-ground infrastructure.

[0173] Future weather data refers to weather conditions over a period of time. In some embodiments, future weather data may include air temperature, air humidity, rainfall, snowfall, etc. In some embodiments, future weather data may be obtained from the internet.

[0174] Physical parameters of above-ground infrastructure refer to the physical parameters of different types of infrastructure. In some embodiments, physical parameters of above-ground infrastructure may include the service life, material and model, number of maintenance visits, last maintenance date, span, etc. of power lines, as well as the sign content of traffic signs, the material of support poles, the designed visibility distance, the size and height of display boards, etc. In some embodiments, physical parameters of above-ground infrastructure may be obtained based on manual input and historical maintenance logs.

[0175] In some embodiments, each group of second training samples may further include weather data of the potential area above the sample during the second time period and physical parameters of the historical above-ground infrastructure of the sample, wherein the acquisition time period corresponding to the historical third monitoring data of the sample in the second training sample is the first time period, both the first time period and the second time period are historical time periods, and the first time period is before the second time period.

[0176] In some embodiments of this specification, by incorporating future weather conditions and the physical parameters of the infrastructure itself into a machine learning model, risk assessment is upgraded from static geometric analysis to dynamic and forward-looking comprehensive prediction. The system can predict and prioritize vulnerable facilities that face higher risks under extreme weather conditions, achieving a leap from "passive response" to "proactive prevention," and greatly improving the scientific nature and foresight of emergency management.

[0177] The basic concepts have been described above. Obviously, for those skilled in the art, the detailed disclosure above is merely illustrative and does not constitute a limitation of this specification. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements, and corrections to this specification. Such modifications, improvements, and corrections are suggested in this specification and therefore remain within the spirit and scope of the exemplary embodiments described herein.

[0178] Furthermore, this specification uses specific terms to describe embodiments thereof. For example, "an embodiment," "one embodiment," and / or "some embodiments" refer to a particular feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "an embodiment," "one embodiment," or "an alternative embodiment" in different locations throughout this specification do not necessarily refer to the same embodiment. Moreover, certain features, structures, or characteristics in one or more embodiments of this specification can be appropriately combined.

[0179] Furthermore, unless expressly stated in the claims, the order of processing elements and sequences, the use of numbers and letters, or other names described in this specification are not intended to limit the order of the processes and methods described herein. Although various examples have been discussed in the foregoing disclosure of some embodiments of the invention that are currently considered useful, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments; rather, the claims are intended to cover all modifications and equivalent combinations that conform to the spirit and scope of the embodiments described herein. For example, while the system components described above can be implemented using hardware devices, they can also be implemented solely using software solutions, such as installing the described system on existing servers or mobile devices.

[0180] Similarly, it should be noted that, in order to simplify the description disclosed herein and thus aid in the understanding of one or more embodiments of the invention, the foregoing description of embodiments in this specification may sometimes combine multiple features into a single embodiment, drawing, or description thereof. However, this method of disclosure does not imply that the subject matter of this specification requires more features than those mentioned in the claims. In fact, the embodiments contain fewer features than all the features of a single embodiment disclosed above.

[0181] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of embodiments are modified in some examples with the terms "approximately," "approximately," or "generally." Unless otherwise stated, "approximately," "approximately," or "generally" indicates that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may be changed depending on the characteristics required by individual embodiments. In some embodiments, numerical parameters should take into account specified significant digits and employ a general method of digit reservation. Although the numerical ranges and parameters used to confirm their breadth of range in some embodiments of this specification are approximate values, in specific embodiments, such values ​​are set as precisely as feasible.

[0182] For each patent, patent application, patent application publication, and other material such as articles, books, specifications, publications, and documents referenced in this specification, the entire contents of which are incorporated herein by reference. This excludes historical application documents that are inconsistent with or conflict with the content of this specification, as well as documents that limit the broadest scope of the claims in this specification (currently or subsequently appended to this specification). It should be noted that in the event of any inconsistency or conflict between the descriptions, definitions, and / or terminology used in the supplementary materials to this specification and the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0183] Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments described herein. Other variations may also fall within the scope of this specification. Therefore, alternative configurations of the embodiments described herein are intended to be illustrative rather than limiting, and should be considered consistent with the teachings of this specification. Accordingly, the embodiments described herein are not limited to those explicitly introduced and described herein.

Claims

1. An emergency monitoring system for urban tree encroachment based on a large-scale Internet of Things (IoT) model, characterized in that, The system includes an emergency monitoring and management platform, which comprises interconnected sub-platforms and a data center. The data center includes a database, a data processing model library, and computing units. The data processing model library is a collection of data processing models used for emergency management data processing. The data processing models include at least a damage prediction model, which is a recurrent neural network model. The damage prediction model is used to determine a second repair sequence for a second repair area, which is a potential area on the ground that needs to be repaired. The input of the damage prediction model includes third monitoring data, and the output of the damage prediction model includes an estimated time of damage. The emergency monitoring and management platform is configured as follows: Identify potential target areas, which are pre-defined observation areas where trees may encroach on infrastructure; The monitoring data corresponding to the potential target area is obtained. The monitoring data reflects the distribution of trees and infrastructure within the potential target area. The monitoring data includes first monitoring data, second monitoring data, and third monitoring data. The first monitoring data is the horizontal position and burial depth of the root system of the trees and underground infrastructure within the underground potential area, reflecting the distribution of the root system of the trees and underground infrastructure within the underground potential area. The second monitoring data is the branch distribution data of the trees on the ground corresponding to the underground potential area, including image data, growth intensity, and growth range of the trees on the ground. The third monitoring data refers to the distribution data of trees and infrastructure on the ground corresponding to the above-ground potential area, including image data, growth intensity, and growth range of the above-ground potential area. Based on the monitoring data, the trimming area is determined and the comprehensive trimming parameters corresponding to the trimming area are generated. The comprehensive trimming parameters include the trimming sequence of the trimming area and the trimming sub-parameters of the trimming area. The trimming sub-parameters include the three-dimensional coordinates of the branches to be trimmed when the branches encroach on the ground, the trimming length or range or the canopy volume to be removed, and the dosage, concentration and injection depth of the growth inhibitor when the branches encroach on the ground. Based on the comprehensive trimming parameters, a trimming instruction is generated and sent to the intelligent trimming device; Based on the trimming instructions, the intelligent trimming equipment controls the intelligent trimming robot and / or drone to move to the trimming area based on the comprehensive trimming parameters, and controls the opening and closing of the valve of the inhibitor injection pump carried by the intelligent trimming robot to inject the soil precisely, and / or drives the mechanical shears mounted on the drone to physically cut off the branches, so as to trim the trees in the trimming area.

2. The system according to claim 1, characterized in that, The potential target area includes one or more above-ground potential areas and one or more underground potential areas; The emergency monitoring and management platform is further configured as follows: Obtain the first monitoring data of the underground potential area; Based on the first monitoring data, it is determined whether the underground potential area is the first repair area; In response to the underground potential area being the first trimming area, a first trimming sub-parameter of the first trimming area is determined based on the first monitoring data. The first trimming sub-parameter includes one or more soil areas to be treated and a first treatment parameter of the soil areas to be treated. The first treatment parameter includes the dose, concentration, and injection depth of the growth inhibitor. In accordance with the first trimming sequence, the intelligent trimming robot injects the growth inhibitor into the soil area to be treated in the first trimming area based on the first trimming sub-parameters.

3. The system according to claim 2, characterized in that, The first trimming sub-parameter also includes a second treatment parameter for the soil area to be treated, the second treatment parameter including the target frequency, amplitude, and duration of the target sound wave: The emergency monitoring and management platform is further configured as follows: In accordance with the first trimming sequence, for the first trimming area, based on the first trimming sub-parameters, the high-frequency sound wave generator is controlled to send the target sound wave to the soil area to be treated.

4. The system according to claim 2, characterized in that, The emergency monitoring and management platform is further configured as follows: Obtain the second monitoring data of the underground potential area; Based on the first monitoring data and the second monitoring data, the first monitoring data is updated; Based on the updated first monitoring data, it is determined whether the underground potential area is the first repair area.

5. The system according to claim 1, characterized in that, The potential target area includes one or more above-ground potential areas and one or more underground potential areas; The emergency monitoring and management platform is further configured as follows: Acquire the third monitoring data of the potential area above ground; Based on the third monitoring data, it is determined whether a target event has occurred in the potential area above ground; the target event refers to an event in which trees encroach on infrastructure. In response to the occurrence of a target event in the above-ground potential area, the above-ground potential area is identified as the second trimming area; In response to the above-ground potential area being the second trimming area, a second trimming sub-parameter of the second trimming area is determined based on the third monitoring data, the second trimming sub-parameter including the shearing area; According to the second trimming sequence, the drone is controlled to trim the trees in the trimming area of ​​the second trimming area based on the second trimming sub-parameters.

6. A method for emergency monitoring of urban tree encroachment based on a large-scale Internet of Things (IoT) model, characterized in that, Based on the urban tree encroachment emergency monitoring system as described in claim 1, the method includes: Identify potential target areas, which are pre-defined observation areas where trees may encroach on infrastructure; Acquire monitoring data corresponding to the potential target area, wherein the monitoring data reflects the distribution of the trees and the infrastructure within the potential target area; Based on the monitoring data, the trimming area is determined and the comprehensive trimming parameters corresponding to the trimming area are generated. The comprehensive trimming parameters include the trimming order of the trimming area and the trimming sub-parameters of the trimming area. Based on the comprehensive trimming parameters, a trimming instruction is generated and sent to the intelligent trimming device; Based on the trimming instructions, the intelligent trimming equipment controls the intelligent trimming robot and / or drone to move to the trimming area based on the comprehensive trimming parameters, and controls the opening and closing of the valve of the inhibitor injection pump carried by the intelligent trimming robot to inject the soil precisely, and / or drives the mechanical shears mounted on the drone to physically cut off the branches, so as to trim the trees in the trimming area.

7. The method according to claim 6, characterized in that, The potential target area includes one or more above-ground potential areas and one or more underground potential areas; The acquisition of monitoring data corresponding to the potential target area includes: Acquire first monitoring data of the underground potential area, the first monitoring data reflecting the distribution of the root system of the trees and underground infrastructure in the underground potential area; The process of determining the trimming area based on the monitoring data and generating comprehensive trimming parameters corresponding to the trimming area includes: Based on the first monitoring data, it is determined whether the underground potential area is the first repair area; In response to the underground potential area being the first trimming area, a first trimming sub-parameter of the first trimming area is determined based on the first monitoring data. The first trimming sub-parameter includes one or more soil areas to be treated and a first treatment parameter of the soil areas to be treated. The first treatment parameter includes the dose, concentration, and injection depth of the growth inhibitor. The control of the valve opening and closing of the growth inhibitor injection pump mounted on the intelligent trimming robot for precise injection into the soil includes: In accordance with the first trimming sequence, the intelligent trimming robot injects the growth inhibitor into the soil area to be treated in the first trimming area based on the first trimming sub-parameters.

8. The method according to claim 7, characterized in that, The first trimming sub-parameter also includes a second treatment parameter for the soil area to be treated, the second treatment parameter including the target frequency, amplitude and duration of the target sound wave; The method further includes: In accordance with the first trimming sequence, for the first trimming area, based on the first trimming sub-parameters, the high-frequency sound wave generator is controlled to send the target sound wave to the soil area to be treated.

9. The method according to claim 7, characterized in that, The step of determining whether the underground potential area is the first remediation area based on the first monitoring data includes: Obtain second monitoring data of the underground potential area, wherein the second monitoring data is the branch distribution data of trees on the ground corresponding to the underground potential area; Based on the first monitoring data and the second monitoring data, the first monitoring data is updated; Based on the updated first monitoring data, it is determined whether the underground potential area is the first repair area.

10. The method according to claim 6, characterized in that, The potential target area includes one or more above-ground potential areas and one or more underground potential areas; The method further includes: Obtain third monitoring data of the potential above-ground area. Based on the third monitoring data, it is determined whether a target event has occurred in the potential area above ground; the target event refers to an event in which trees encroach on infrastructure. In response to the occurrence of a target event in the above-ground potential area, the above-ground potential area is identified as a second trimming area; In response to the above-ground potential area being the second trimming area, a second trimming sub-parameter of the second trimming area is determined based on the third monitoring data, the second trimming sub-parameter including the shearing area; Following the second trimming sequence, and based on the second trimming sub-parameters, the drone is controlled to trim the trees within the trimming area of ​​the second trimming area.

Images