Urban low-lying road section emergency supervision internet-of-things large model system and method and storage medium

Abstract

The invention provides an urban low-lying road section emergency supervision Internet of Things large model system and method and a storage medium, and belongs to the field of road monitoring. The emergency supervision management platform is configured to obtain driving data of a low-lying area through the emergency supervision object platform; determining ponding data based on the driving data; determining a traffic risk based on the ponding data; in response to the traffic risk greater than a first threshold, determining a drainage parameter; determining scheduling parameters based on the drainage parameters; and sending a scheduling packet containing the drainage parameters to the unmanned vehicle cluster through the heterogeneous communication network, controlling the unmanned vehicle carrying the drainage device to run to the low-lying area, and controlling the water pumping power of the drainage device to be adjusted to the water pumping power of the drainage parameters. The method can effectively reduce the traffic obstruction and accident risk caused by water accumulation, and improves the emergency response efficiency of urban low-lying road sections during heavy rainfall.

Description

Technical Field

[0001] This manual pertains to the field of road monitoring, and in particular to the IoT large-scale model system, methods, and storage media for emergency monitoring of low-lying urban road sections. Background Technology

[0002] During extreme weather events, low-lying urban roads are prone to flooding during heavy rainfall, leading not only to traffic paralysis and vehicle damage but also secondary disasters such as electrocution and drowning. Traditionally, flooding is addressed through manual inspections and static drainage systems. However, manual inspections are inefficient and pose safety risks; static drainage systems cannot reflect the overall flood distribution across the entire road, presenting limitations in complex urban environments; and manual warnings are coarse-grained, failing to differentiate between vehicle chassis heights or provide real-time water depth, making it difficult for drivers to determine if their vehicles can safely pass.

[0003] Therefore, it is hoped that an IoT big data model system, method and storage medium for emergency monitoring of low-lying urban road sections can be provided to promptly remind drivers of water accumulation in low-lying urban road sections and provide real-time warnings to vehicles and pedestrians to reduce traffic risks. Summary of the Invention

[0004] This specification provides one or more embodiments of an IoT large-scale model system for emergency monitoring of low-lying urban road sections. The emergency monitoring IoT large-scale model system includes an emergency monitoring user platform, an emergency monitoring management platform, and an emergency monitoring object platform connected in sequence; the emergency monitoring management platform is configured to execute emergency monitoring methods.

[0005] This specification provides one or more embodiments of an emergency monitoring method for low-lying urban road sections. The method is executed based on an emergency monitoring management platform and includes: acquiring driving data of low-lying areas through an emergency monitoring object platform; determining water accumulation data based on the driving data; determining traffic risk based on the water accumulation data; determining drainage parameters in response to the traffic risk exceeding a first threshold; determining scheduling parameters based on the drainage parameters; and, based on the scheduling parameters, sending a scheduling packet containing the drainage parameters to an unmanned vehicle cluster through a heterogeneous communication network, controlling unmanned vehicles equipped with drainage devices to drive to the low-lying area, and controlling the pumping power of the drainage devices to be adjusted to the pumping power of the drainage parameters.

[0006] This specification also provides a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes an emergency monitoring method for low-lying urban road sections.

[0007] This invention can effectively reduce traffic obstruction and accident risks caused by water accumulation, and improve the emergency response efficiency during heavy rainfall in low-lying urban road sections. Attached Figure Description

[0008] 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: Figure 1 This is a schematic diagram of the platform structure of a large-scale IoT model system for emergency monitoring of low-lying road sections, as shown in some embodiments of this specification. Figure 2 This is an exemplary flowchart of an emergency monitoring method for low-lying road sections, as shown in some embodiments of this specification. Figure 3 This is a schematic diagram of a water accumulation prediction model based on some embodiments of this specification; Figure 4 This is a schematic diagram illustrating the determination of driving warning and signal control commands according to some embodiments of this specification.

[0009] Figure label: Emergency monitoring IoT large-scale model system 100, emergency monitoring user platform 110, emergency monitoring service platform 120, emergency monitoring management platform 130, emergency monitoring sensor network platform 140, emergency monitoring object platform 150, water accumulation map 310, drainage parameters 320, drainage efficiency 330, water splash data 340, water accumulation prediction model 350, water accumulation data 360, vehicle driving risk 411, road risk 412, second threshold 420, driving warning 430, warning device 440, vehicle 450, third threshold 460, signal control command 470, traffic lights 480, electronic road signs 490. Detailed Implementation

[0010] 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.

[0011] Figure 1 This is a schematic diagram of the platform structure of a large-scale IoT model system for emergency monitoring of low-lying road sections, as shown in some embodiments of this specification.

[0012] In some embodiments, such as Figure 1 As shown, the emergency supervision IoT large-scale model system 100 includes an emergency supervision user platform 110, an emergency supervision service platform 120, an emergency supervision management platform 130, an emergency supervision sensor network platform 140, and an emergency supervision object platform 150, which are connected in sequence.

[0013] In some embodiments, one or more platforms in the Emergency Monitoring IoT Big Data Model System 100 can exchange information and / or data via a network. In some embodiments, the network can be any one or more of a wired network or a wireless network.

[0014] The emergency monitoring user platform 110 refers to a platform used for interaction with users. In some embodiments, the emergency monitoring user platform 110 can be used to provide data visualization and early warning push notifications. Users refer to higher-level emergency monitoring departments or city citizens.

[0015] In some embodiments, the emergency monitoring user platform 110 may include mobile phones, computers, mobile terminals, etc.

[0016] In some embodiments, the emergency monitoring user platform 110 can interact with the emergency monitoring management platform 130. For example, the emergency monitoring user platform 110 can receive driving warnings sent by the emergency monitoring management platform 130, or the emergency monitoring user platform 110 can send the distribution of manhole covers to the emergency monitoring management platform 130.

[0017] In some embodiments, the emergency monitoring user platform 110 is configured to acquire manhole cover distribution and rainfall.

[0018] The emergency monitoring service platform 120 refers to a platform used to transmit user instructions and control information. The emergency monitoring service platform 120 can interact with the emergency monitoring user platform 110 and the emergency monitoring management platform 130. For example, the emergency monitoring service platform 120 can receive the distribution of manhole covers sent by the emergency monitoring user platform 110 and send the distribution to the emergency monitoring management platform 130.

[0019] In some embodiments, the emergency monitoring service platform 120 may include an edge computing gateway, middleware server, switch, or any combination thereof.

[0020] The emergency monitoring and management platform 130 refers to a platform used to monitor and manage data related to the emergency monitoring IoT big data model system 100. The emergency monitoring and management platform 130 can interact with the emergency monitoring user platform 110 and the emergency monitoring sensor network platform 140.

[0021] In some embodiments, the emergency monitoring and management platform 130 may include a processor and a storage device. The processor may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), a microcontroller, or any combination thereof.

[0022] In some embodiments, the emergency monitoring and management platform 130 may be configured to: acquire driving data of low-lying areas through the emergency monitoring object platform 150; determine water accumulation data based on the driving data; determine traffic risks based on the water accumulation data; determine drainage parameters in response to traffic risks exceeding a first threshold; determine scheduling parameters based on the drainage parameters; and, based on the scheduling parameters, send a scheduling packet containing drainage parameters to the unmanned vehicle cluster through a heterogeneous communication network, and control the unmanned vehicles equipped with drainage devices to drive to the low-lying areas, and control the pumping power of the drainage devices to be adjusted to the pumping power of the drainage parameters.

[0023] The emergency monitoring sensor network platform 140 refers to a functional platform for sensor communication. In some embodiments, the emergency monitoring sensor network platform 140 can be configured as a communication network and gateway, etc., to perform one or more functions including network management, protocol management, command management, and data parsing. For example, the emergency monitoring sensor network platform 140 may include heterogeneous communication networks, edge computing chips, edge protocol gateways, network security firewalls, etc., or any combination thereof. A heterogeneous communication network refers to a communication network used for transmitting scheduling packets. A heterogeneous communication network may include a LoRa-WAN heterogeneous communication network.

[0024] In some embodiments, the emergency monitoring sensor network platform 140 can interact with the emergency monitoring management platform 130 and the emergency monitoring object platform 150 to transmit data such as driving data and water accumulation data. For example, the emergency monitoring sensor network platform 140 can receive driving data uploaded by the emergency monitoring object platform 150 or send dispatch packets to the emergency monitoring object platform 150.

[0025] The emergency monitoring platform 150 refers to a functional platform used for collecting data or executing instructions. In some embodiments, the emergency monitoring platform 150 may include various devices. These devices include vehicle data acquisition equipment, drainage devices, vehicles, unmanned vehicle clusters, traffic signal equipment, early warning devices, etc.

[0026] Driving data acquisition equipment refers to devices used to acquire driving data. For example, driving data acquisition equipment may include location positioning devices (such as GPS positioning systems, BeiDou positioning systems, etc.), speed monitoring devices (such as radar speedometers, vehicle-mounted millimeter-wave radar, etc.), and roadside sensing units (such as cameras, lidar, rain sensors, etc.). In some embodiments, location positioning devices can be used to acquire vehicle driving trajectories. Speed ​​monitoring devices can be used to acquire vehicle speeds. Roadside sensing units can be used to collect traffic flow, vehicle type distribution, water splash data, and rainfall, etc. In some embodiments, location positioning devices and speed monitoring devices can be installed inside vehicles or on both sides of roads, and roadside sensing units can be installed on both sides of roads.

[0027] Drainage devices are equipment used to remove water accumulated in low-lying road sections. For example, drainage devices can include hydraulic drainage equipment, vacuum water pumps, etc.

[0028] A vehicle refers to a social vehicle that travels on roads. Vehicles can include various vehicle types. In some embodiments, different vehicle types correspond to different vehicle chassis heights.

[0029] An autonomous vehicle swarm refers to a group of vehicles comprising multiple autonomous vehicles. These autonomous vehicles may be equipped with drainage systems. In some embodiments, the autonomous vehicle swarm can dispatch autonomous vehicles to perform drainage tasks based on a scheduling package.

[0030] Traffic signal equipment refers to devices used on roads to guide vehicle movement. Examples include traffic lights and electronic road signs. Electronic road signs may include LED displays and audible / visual alarms.

[0031] Warning devices are devices used to send driving warnings to vehicles. For example, warning devices may include navigation maps.

[0032] For more information about the above platforms, please refer to [link / reference]. Figures 2-4 And related explanations.

[0033] In some embodiments of this specification, the emergency monitoring IoT big data system can form an information operation closed loop between 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 low-lying road section monitoring.

[0034] It should be noted that the above description of the emergency monitoring IoT large model system 100 is for ease of description only and should not limit this specification to the scope of the embodiments described.

[0035] Figure 2 This is an exemplary flowchart illustrating an emergency monitoring method for low-lying road sections according to some embodiments of this specification. Figure 2 As shown, process 200 includes steps 210-260. In some embodiments, process 200 is executed by an emergency monitoring and management platform.

[0036] Step 210: Obtain driving data in low-lying areas through the emergency monitoring platform.

[0037] Low-lying areas refer to roads that are lower than the surrounding road surfaces. For example, low-lying areas can include underpasses, road sections at the bottom of slopes, tunnels, etc.

[0038] In some embodiments, the boundary of the low-lying area can be the outline of a road that is lower than the surrounding road surface. For example, the outline of a tunnel.

[0039] In some embodiments, low-lying areas can be managed by the emergency monitoring and management platform based on default presets.

[0040] Driving data refers to data related to vehicle movement. In some embodiments, driving data may include vehicle speed, driving trajectory, etc.

[0041] In some embodiments, the emergency monitoring and management platform can acquire driving data through driving data acquisition devices.

[0042] For example, the emergency monitoring and management platform can obtain driving trajectory through GPS positioning system and vehicle speed through vehicle speed sensor.

[0043] For more information on vehicle data acquisition equipment, please refer to [link / reference]. Figure 1 Related descriptions.

[0044] Step 220: Determine water accumulation data based on driving data.

[0045] Water accumulation data refers to data related to water accumulation in low-lying areas. In some embodiments, water accumulation data may include water depth, etc.

[0046] In some embodiments, the emergency monitoring and management platform can determine the actual number of vehicles in low-lying areas based on driving trajectories, and determine the driving ratio based on the actual number of vehicles in low-lying areas and the number of vehicles traveling up and down. It is known that there are two cases: the driving ratio is greater than the ratio threshold and the driving ratio is not greater than the ratio threshold. In response to the driving ratio being less than or equal to the ratio threshold, the emergency monitoring and management platform can determine the water accumulation data based on vehicle speed by querying a first preset table.

[0047] Actual vehicle traffic refers to the number of vehicles that actually pass through the low-lying road section. In some embodiments, the emergency monitoring and management platform can determine whether a vehicle has passed through the low-lying area based on its driving trajectory and determine the actual number of vehicles that have passed through the low-lying area.

[0048] The number of vehicles traveling up and down refers to the number of vehicles passing through the roads upstream and downstream of the low-lying area. In some embodiments, the emergency monitoring and management platform can determine whether a vehicle has passed through the roads upstream and downstream of the low-lying area based on its driving trajectory, and determine the number of vehicles traveling up and down the roads upstream and downstream of the low-lying area.

[0049] In some embodiments, the percentage of vehicles traveling can be determined by the ratio between the actual number of vehicles traveling and the number of vehicles traveling up and down.

[0050] The percentage threshold refers to the minimum percentage of vehicles allowed in a low-lying area when there is no standing water. In some embodiments, the percentage threshold can be preset by a technician based on experience.

[0051] The first preset table may include the relationship between vehicle speed and water depth. There is a negative correlation between vehicle speed and water depth. In some embodiments, the first preset table may be preset by a technician based on experience.

[0052] It should be noted that the total number of vehicles passing through low-lying areas and their upstream and downstream roads generally tends to remain stable within the same time period. When there is water accumulation in low-lying areas, some vehicles will choose other roads connecting the upstream and downstream roads to travel, and the number of vehicles passing through low-lying areas will be less than the number of vehicles passing through low-lying areas when there is no water accumulation.

[0053] Understandably, if the proportion of vehicles traveling is less than or equal to a threshold, the emergency monitoring and management platform can determine that there is water accumulation in the low-lying area, and some vehicles will choose to travel on other roads connected by upstream and downstream roads. If the proportion of vehicles traveling is 0, meaning that no vehicles are currently passing through the low-lying area, the emergency monitoring and management platform can determine that the water accumulation data is the preset water accumulation data. The preset water accumulation data refers to the maximum water depth in the low-lying area. In some embodiments, the preset water accumulation data is greater than the maximum water accumulation data in the first preset table, and the preset water accumulation data can be preset by technical personnel based on experience.

[0054] For more information on determining water accumulation data, please refer to [link / reference]. Figure 3 And its related descriptions.

[0055] Step 230: Determine traffic risks based on water accumulation data.

[0056] Traffic risk refers to a parameter that measures the safety hazard posed by road flooding in low-lying areas. In some embodiments, traffic risk can be represented by a numerical value. The higher the value, the higher the traffic risk.

[0057] In some embodiments, the emergency monitoring and management platform can determine traffic risks based on water accumulation data by querying a second preset table. The second preset table includes the relationship between water accumulation data and traffic risks. There is a positive correlation between water accumulation data and traffic risks. In some embodiments, the second preset table can be generated by the emergency monitoring and management platform based on a default preset.

[0058] In some embodiments, the emergency monitoring and management platform can obtain road traffic flow and vehicle height distribution within a preset range through the emergency monitoring object platform; determine vehicle driving risk based on vehicle height distribution and water accumulation data; determine road risk based on road traffic flow and water accumulation data within a preset range; and determine traffic risk based on vehicle driving risk, road risk, and the current time period.

[0059] The preset range refers to the area that includes low-lying areas.

[0060] In some embodiments, the preset range has the same shape as the corresponding low-lying area. The boundary of the preset range can be the geometry of the low-lying area extended outward by a preset distance.

[0061] In some embodiments, the preset range is related to rainfall.

[0062] The greater the rainfall, the greater the preset distance the low-lying area's boundary will extend outwards, and the larger the preset range will be. More information about the preset distance can be found in the related description below.

[0063] Rainfall refers to the amount of rainfall in low-lying areas. In some embodiments, the emergency monitoring and management platform can obtain rainfall data in various ways. For example, the platform can directly obtain rainfall data from external data sources (such as local meteorological bureau databases). Alternatively, it can obtain rainfall data using rain sensors installed in low-lying areas. More information about rain sensors can be found in [link to relevant documentation]. Figure 1 Related descriptions.

[0064] In some embodiments of this specification, the preset range is adjusted based on the rainfall. When the rainfall increases, it is beneficial to cover the upstream low-lying areas and potential chain flooding areas in advance, avoiding false warnings caused by "monitoring blind spots". When the rainfall decreases, it is beneficial to reduce redundant computing and communication overhead, improve the endurance and bandwidth utilization of edge nodes, and significantly improve emergency response speed and resource support efficiency.

[0065] In some embodiments, the emergency monitoring and management platform can determine a preset range based on low-lying areas and preset distances.

[0066] The preset distance refers to the distance between the boundary of the preset range and the boundary of the low-lying area.

[0067] In some embodiments, the emergency monitoring and management platform can determine a preset distance based on rainfall by querying a third preset table. The third preset table includes the correspondence between rainfall and preset distances. There is a positive correlation between rainfall and preset distances; the greater the rainfall, the greater the preset distance. In some embodiments, the third preset table can be preset by technical personnel based on experience.

[0068] For example, the emergency monitoring and management platform can define the boundary of a preset range as the boundary of a low-lying area after extending the boundary outward by a preset distance.

[0069] Road traffic flow refers to the number of vehicles passing through a road within a preset range per unit of time.

[0070] In some embodiments, the emergency monitoring and management platform can obtain road traffic flow data through vehicle data collection equipment.

[0071] For example, the emergency monitoring and management platform can use the number of vehicles passing by the vehicle data collection equipment within a unit of time (e.g., 1 minute, 30 minutes) as the road traffic flow.

[0072] For more information on vehicle data acquisition equipment, please refer to [link / reference]. Figure 1 Related descriptions.

[0073] Vehicle height distribution refers to the chassis height of vehicles within a preset range. Chassis height refers to the distance between the vehicle's chassis and the ground.

[0074] In some embodiments, for each vehicle passing through a low-lying area, the emergency monitoring and management platform can determine the vehicle type through the emergency monitoring object platform, and based on the vehicle type, determine the chassis height by querying the type-chassis preset table; based on the chassis heights of multiple vehicles passing through low-lying areas, determine the vehicle height distribution. The type-chassis preset table can include the relationship between vehicle type and chassis height. In some embodiments, the type-chassis preset table can be generated by the emergency monitoring and management platform based on default presets.

[0075] For example, for each vehicle passing through a low-lying area, the emergency monitoring and management platform can acquire vehicle images through roadside sensing units (such as cameras), and based on the vehicle images, determine the vehicle type corresponding to the vehicle image through image recognition algorithms (such as object detection algorithms); based on the vehicle type, determine the chassis height by querying the type-chassis preset table; group the number of vehicles passing through the low-lying area based on the chassis height, determine the number of vehicles corresponding to each chassis height, and determine the vehicle height distribution by multiple chassis heights and their corresponding vehicle numbers.

[0076] Vehicle driving risk refers to the risk of a vehicle malfunctioning when driving through low-lying areas. Malfunctions that may occur can include loss of control, skidding, engine stalling, etc. In some embodiments, vehicle driving risk can be represented numerically. The higher the numerical value, the higher the vehicle driving risk, and the greater the likelihood of the vehicle malfunctioning when driving through low-lying areas.

[0077] In some embodiments, the emergency monitoring and management platform can determine vehicle driving risks based on vehicle height distribution and water accumulation data.

[0078] For example, the emergency monitoring and management platform can compare vehicle height distribution with water accumulation data. If the number of vehicles with a chassis height less than the water depth is greater in the vehicle height distribution, the greater the risk of vehicle driving.

[0079] Road risk refers to the risk that flooding will damage roads. In some embodiments, road risk can be represented by a numerical value. The higher the value, the greater the road risk, and the greater the likelihood that flooding will cause damage to the road.

[0080] In some embodiments, there are known scenarios where water accumulation data exceeds a depth threshold and does not exceed a depth threshold. In response to water accumulation data exceeding the depth threshold, the emergency monitoring and management platform can determine road risk based on road traffic flow. The depth threshold refers to the maximum depth of water accumulation that will not damage the road. In some embodiments, the depth threshold can be preset by technicians based on experience.

[0081] In some embodiments, road traffic volume is directly proportional to road risk.

[0082] The current time period refers to the time period at which the current moment occurs. In some embodiments, the emergency monitoring and management platform can divide the daily time into multiple time periods based on traffic conditions. Traffic conditions refer to the concentration of vehicle traffic on the road. For example, the emergency monitoring and management platform can divide the daily time into four time periods: morning peak period (07:00-09:00), daytime off-peak period (09:01-16:59), evening peak period (17:00-19:00), and nighttime off-peak period (19:01-06:59).

[0083] In some embodiments, the emergency monitoring and management platform can determine traffic risks by weighted summation based on road risks and vehicle driving risks. The weights can be determined by the emergency monitoring and management platform based on default presets.

[0084] In some embodiments, the weights of road risks in the weighted average are related to the current time period.

[0085] For example, if the current time period is the morning or evening rush hour, the emergency monitoring and management platform can reduce the weight of road risks to allow vehicles to pass appropriately and avoid large-scale traffic congestion caused by road flooding.

[0086] In some embodiments of this specification, traffic risks are determined based on vehicle driving risks, road risks, and the current time period. This helps to fully consider traffic conditions at different times and avoid large-scale congestion. By considering road wear and tear and vehicle passage risks, a more comprehensive assessment basis is provided for subsequent assessment of traffic risks and solutions to road problems caused by water accumulation.

[0087] In some embodiments, traffic risk is also related to the rate of change of risk.

[0088] Risk change rate refers to the rate at which the risk of vehicle operation changes.

[0089] In some embodiments, the risk change rate can be determined from water accumulation data over a preset period of time.

[0090] For example, an emergency monitoring and management platform can determine the rate of water level reduction based on water accumulation data over a preset period, and then determine the risk change rate based on this rate of reduction. The rate of water level reduction refers to the speed at which the water depth decreases per unit time.

[0091] In some embodiments, the accuracy of the water reduction rate is positively correlated with the length of a preset time period.

[0092] In some embodiments, the emergency monitoring and management platform can also determine traffic risk by weighted summation based on road risk, vehicle driving risk, and risk change rate. The weights can be determined by the emergency monitoring and management platform based on default presets.

[0093] In some embodiments of this specification, adjusting traffic risk based on the rate of risk change is beneficial for responding quickly to emergency drainage when the risk increases rapidly, reducing the social costs caused by unnecessary road closures and other controls when the rate of change decreases or leveles off, improving the stability and reliability of early warnings, and preventing false alarms caused by a single instantaneous peak.

[0094] In some embodiments, traffic risks are also related to electricity risks.

[0095] In some embodiments, the emergency monitoring and management platform can also determine traffic risks based on a weighted average of vehicle driving risks, road risks, and electricity risks. The weighting can be determined by the emergency monitoring and management platform based on default presets.

[0096] Electrical risk refers to the risk of electrical equipment near low-lying areas leaking electricity during rain. This equipment can include high-voltage electrical boxes, traffic lights, electronic road signs, etc.

[0097] In some embodiments, electricity risk is related to the distribution of electrical equipment and water accumulation data.

[0098] In some embodiments, the emergency monitoring and management platform can determine electricity consumption risks based on the distribution of electrical equipment and water accumulation data. The distribution of electrical equipment refers to the types and quantities of electrical equipment within a preset range.

[0099] For example, an emergency monitoring and management platform can determine electricity risk based on the distribution of electrical equipment and water accumulation data by matching it with an electricity risk pre-set table. The electricity risk pre-set table can include the relationship between the distribution of electrical equipment, water depth, and electricity risk. The distribution of electrical equipment and water depth are positively correlated with electricity risk. In some embodiments, the electricity risk pre-set table can be determined by technical personnel based on historical data.

[0100] Historical data may include historical electricity consumption risks, historical water depth, and historical distribution of electrical equipment. In some embodiments, historical data may be obtained through actual measurements by technicians. For example, technicians may, within a preset range, count the types and quantities of electrical equipment, manually measure the electricity level in the water, and determine the electricity consumption risk based on experience.

[0101] In some embodiments of this specification, the relationship between electrical risks and traffic risks is considered, which can fully take into account safety hazards such as electric shock, better assess traffic risks, and reduce the risk of electric shock.

[0102] Step 240: In response to the traffic risk exceeding the first threshold, determine the drainage parameters.

[0103] The first threshold refers to the minimum traffic risk required to generate drainage parameters for drainage.

[0104] In some embodiments, the first threshold may be determined by the emergency monitoring and management platform based on a default preset.

[0105] Drainage parameters refer to the parameters that control the drainage of a drainage device. In some embodiments, drainage parameters include the distribution of drainage devices and the pumping power of each drainage device.

[0106] Drainage device distribution refers to the location and number of drainage devices within a predetermined area. Pumping power refers to the power of the drainage device during operation.

[0107] For more information on drainage systems, please refer to [link / reference]. Figure 1 Related descriptions.

[0108] In some embodiments, there are known situations where the traffic risk is greater than a first threshold and not greater than the first threshold. In response to the traffic risk being greater than the first threshold, the emergency monitoring and management platform can obtain drainage parameters preset by technicians based on experience from the storage device.

[0109] In some embodiments, the emergency monitoring and management platform can also determine drainage efficiency based on water accumulation data, candidate drainage parameters, traffic risks, and road traffic flow within a preset range, using an efficiency prediction model; and, based on drainage efficiency, determine drainage parameters. For information regarding the distribution of drainage devices and pumping power, please refer to the preceding description.

[0110] Candidate drainage parameters are parameters that can be used to perform drainage tasks.

[0111] In some embodiments, the emergency monitoring and management platform may use historical data to select drainage parameters used in historical drainage processes as candidate drainage parameters.

[0112] Drainage efficiency refers to the rate at which a drainage device pumps water per unit time. For example, drainage efficiency can be expressed as the volume of water pumped out by the drainage device per unit time.

[0113] In some embodiments, the emergency monitoring and management platform can determine drainage efficiency based on the decrease in water depth per unit time.

[0114] An efficiency prediction model is a model used to determine drainage efficiency. In some embodiments, the efficiency prediction model can be a machine learning model, such as a combination of one or more graph neural network (GNN) models or other custom models.

[0115] In some embodiments, the input to the efficiency prediction model may include water accumulation data, candidate drainage parameters, traffic risk, and road traffic flow within a preset range, and the output may include drainage efficiency corresponding to the candidate drainage parameters.

[0116] In some embodiments, the efficiency prediction model can be obtained by training a large number of first training samples with first training labels. A set of first training samples may include sample water accumulation data, sample drainage parameters, sample traffic risks, and sample road traffic flow within a preset range. The first training label corresponding to a set of first training samples represents the sample drainage efficiency of the sample drainage parameters.

[0117] The first training sample can be determined based on historical data. Historical data includes historical water accumulation data, historical drainage parameters, historical traffic risks, and historical road traffic flow within a preset range. For each set of first training samples, technicians can actually measure the rate of decrease in water depth per unit time and determine the actual drainage efficiency corresponding to the first training sample in the historical data as the first training label.

[0118] In some embodiments, the emergency monitoring and management platform can perform multiple rounds of iterative training on the initial efficiency prediction model based on multiple sets of first training samples with first training labels, until the iteration termination condition is met, thus obtaining a trained efficiency prediction model. At least one round of iterative training includes: selecting one or more first training samples from the training dataset; inputting the one or more first training samples into the initial efficiency prediction model to obtain the model prediction output corresponding to the one or more first training samples; substituting the model prediction output corresponding to the one or more first training samples, and the first training labels corresponding to the one or more first training samples, into a predefined loss function formula to calculate the value of the loss function; iteratively updating the model parameters in the initial efficiency prediction model based on the value of the loss function until the iteration termination condition is met, thus ending the iteration and obtaining a trained efficiency prediction model. The iterative updating of the model parameters of the initial efficiency prediction model can be performed using various methods, such as gradient descent. The iteration termination condition can include loss function convergence or the number of iterations reaching an iteration threshold. The iteration termination condition can be loss function convergence, the number of iterations reaching a preset threshold, or the loss function value being less than a preset threshold.

[0119] In some embodiments, a candidate drainage parameter can correspond to a drainage efficiency. The emergency monitoring and management platform can determine the candidate drainage parameter corresponding to the highest drainage efficiency as the drainage parameter based on multiple drainage efficiencies.

[0120] It should be noted that directly maximizing the pumping power of all drainage devices can achieve the highest drainage efficiency. However, continuous operation at maximum pumping power will cause battery / fuel consumption to increase exponentially. In extreme rainstorm scenarios where autonomous vehicle swarms need to be on standby for extended periods, it is easy to run out of energy before the pumping is completed. Furthermore, once the water depth decreases to a certain level, the improvement in drainage efficiency from high pumping power tends to plateau, while energy consumption continues to increase linearly or even quadratically, easily leading to high energy consumption and low gain.

[0121] In some embodiments of this specification, based on water accumulation data, candidate drainage parameters, traffic risks, and road traffic flow within a preset range, drainage efficiency is determined through an efficiency prediction model; then, drainage parameters are determined, and the coordinated operation of multiple drainage devices can be considered to balance the relationship between pumping efficiency and energy consumption. The optimal layout coordinates and power levels of each drainage device are dynamically calculated, and the pumping power is adjusted in real time to avoid underpowered or wasted power, thereby improving drainage efficiency and reducing road closure time.

[0122] Step 250: Determine scheduling parameters based on drainage parameters.

[0123] Scheduling parameters refer to parameters used to schedule autonomous vehicles. In some embodiments, scheduling parameters may include the autonomous vehicles that need to perform drainage tasks, and the locations where the autonomous vehicles need to perform drainage tasks.

[0124] In some embodiments, the emergency monitoring and management platform can determine scheduling parameters based on low-lying areas and unmanned vehicle clusters.

[0125] For example, the emergency monitoring and management platform can filter unmanned vehicles (UGVs) based on low-lying areas and a preset radius. It can identify a preset number of UGVs that are not currently in operation within a preset radius centered on the low-lying area and determine which UGVs need to be dispatched there. The platform can also determine the specific location where UGVs need to be dispatched based on the load status of the drainage network within the low-lying area and the preset radius. Understandably, if the drainage network in the low-lying area is already at full capacity, adding more UGVs to drain water from that network will not improve drainage efficiency. In this case, the platform can dispatch UGVs to a location near the low-lying area where the drainage network is less overloaded, thus diverting the accumulated water from the low-lying area to the less overloaded network and reducing the load on the drainage network in the low-lying area. The drainage network refers to the underground pipe network used for drainage in an urban area. The preset radius can include multiple drainage networks.

[0126] For example, if the number of unmanned vehicles not in operation within the low-lying area and the preset radius does not meet the preset number, the emergency monitoring and management platform can increase the preset radius until the number of unmanned vehicles not in operation within the low-lying area and the preset radius meets the preset number.

[0127] In some embodiments, the emergency monitoring and management platform can determine the unmanned vehicles (UAVs) that need to be dispatched to low-lying areas and the location where the UAVs will be dispatched as dispatch parameters. The preset radius refers to the pre-set distance for dispatching UAVs. The preset quantity refers to the pre-set number of UAVs to be dispatched. In some embodiments, the preset radius and preset quantity can be determined by the emergency monitoring and management platform based on default presets.

[0128] It should be noted that when water accumulates in low-lying areas, in the initial stages of flooding, the emergency monitoring and management platform can open only some conventional drainage outlets (such as sewers) or to a small degree to prevent a sudden surge of water from washing away sediment in the sewer network and causing downstream blockages. Simultaneously, unmanned vehicles (UAVs) can be dispatched to low-lying areas for active pumping to increase drainage capacity. Multiple UAVs equipped with drainage devices can be deployed within an area and centrally managed by the emergency monitoring and management platform. For example, drainage devices at the lowest elevation can be prioritized and their pumping power increased; or when a drainage network is nearing full capacity, the drainage device at that location can be temporarily shut off, diverting drainage pressure to other, less overloaded networks, thus achieving dynamic balance and optimization of the overall drainage load in the area.

[0129] Step 260: Based on the scheduling parameters, a scheduling packet containing drainage parameters is sent to the unmanned vehicle swarm via a heterogeneous communication network. The unmanned vehicles equipped with drainage devices are then controlled to travel to low-lying areas, and the pumping power of the drainage devices is adjusted to the pumping power specified in the drainage parameters. For more information on unmanned vehicle swarms, please refer to [link to relevant documentation]. Figure 1 Related descriptions.

[0130] A scheduling packet is a data packet that controls an unmanned vehicle to perform a drainage task. In some embodiments, a scheduling packet may include drainage parameters and scheduling parameters.

[0131] In some embodiments, the emergency monitoring and management platform can generate data packets based on drainage parameters and scheduling parameters, and identify the data packets as scheduling packets.

[0132] In some embodiments, the emergency monitoring and management platform can send dispatch packets to the unmanned vehicle cluster through a heterogeneous communication network, determine the unmanned vehicles that need to be dispatched based on the dispatch packets, and control the unmanned vehicles that need to be dispatched to drive to low-lying areas.

[0133] In some embodiments, the emergency monitoring and management platform can send scheduling packets to the unmanned vehicle cluster through a heterogeneous communication network, and adjust the pumping power of the drainage device on the unmanned vehicle based on the drainage parameters in the scheduling packet, and control the drainage device to drain the low-lying area based on the pumping power.

[0134] In some embodiments of this specification, water accumulation data is determined based on driving data; traffic risks are then determined; drainage parameters and scheduling parameters are determined; and scheduling packets are sent to the unmanned vehicle cluster through a heterogeneous communication network based on the scheduling parameters, and the unmanned vehicles are controlled to drive to low-lying areas for drainage. This helps reduce the risk of vehicles and pedestrians passing through low-lying areas, avoids the risk of pedestrians or vehicles accidentally falling into the drainage system due to constantly open drainage outlets, reduces the blockage of the drainage system by daily garbage, reduces maintenance costs and the risk of blockage during the rainy season, effectively isolates odor overflow and mosquito breeding, realizes on-demand drainage, and effectively maximizes the role of the drainage device.

[0135] It should be noted that the above description of process 200 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 process 200 under the guidance of this specification. However, these modifications and changes remain within the scope of this specification.

[0136] Figure 3 This is a schematic diagram of a water accumulation prediction model based on some embodiments of this specification.

[0137] In some embodiments, the emergency monitoring and management platform can obtain manhole cover distribution and rainfall through the emergency monitoring user platform, construct a water accumulation map 310 based on driving data, rainfall and manhole cover distribution; and predict water accumulation data 360 based on the water accumulation map 310 and the water accumulation prediction model 350.

[0138] More information on rainfall and driving data can be found at [link / reference]. Figure 2 And its related descriptions.

[0139] Manhole cover distribution refers to the location and quantity of manhole covers within a predetermined range.

[0140] In some embodiments, the emergency monitoring and management platform can obtain the distribution of manhole covers through the emergency monitoring user platform.

[0141] For example, users can directly input the distribution of manhole covers through the emergency monitoring user platform.

[0142] For example, an emergency monitoring and management platform can obtain the distribution of manhole covers through storage devices.

[0143] For more information on rainfall, please refer to [link / reference]. Figure 2 Related descriptions.

[0144] A water accumulation graph can be a directed graph containing nodes and edges. In some embodiments, a water accumulation graph includes multiple nodes, and an edge exists between any two nodes. The edges in a water accumulation graph can point from a node with a higher elevation to a node with a lower elevation.

[0145] Nodes can include first-class nodes and second-class nodes.

[0146] The first type of node refers to a low-lying area. In some embodiments, the node characteristics of the first type of node include the size of the low-lying area, the location of the low-lying area, rainfall, and driving data.

[0147] In some embodiments, a water accumulation map includes a first type of node.

[0148] The second type of node refers to a manhole cover. In some embodiments, the node characteristics of the second type of node include the location and size of the manhole cover.

[0149] An edge is used to connect any two nodes. In some embodiments, the edge characteristics may include the distance between the two endpoints of the edge and the elevation difference.

[0150] In some embodiments, the emergency monitoring and management platform can construct a water accumulation map based on driving data, rainfall, and manhole cover distribution.

[0151] A flooding prediction model is a model used to determine flooding data. In some embodiments, the flooding prediction model can be a machine learning model, such as one or more combinations of a graph neural network (GNN) model or other custom models.

[0152] In some embodiments, the input to the waterlogging prediction model may include a waterlogging map, and the output may include waterlogging data of the first type of nodes.

[0153] In some embodiments, the flooding prediction model can be obtained by training a large number of second training samples with second training labels. The second training samples may include flooding maps. The second training label corresponding to the second training samples is the flooding data.

[0154] The second training sample can be determined based on historical data. Historical data includes historical water accumulation data, historical drainage parameters, historical traffic risks, and historical road traffic flow within a preset range. For each second training sample, technicians can use water level sensors (such as radar water level gauges, pressure water level gauges, ultrasonic water level gauges, etc.) to actually measure the water accumulation depth of the first type of node under the conditions of the second training sample, and determine the actual water accumulation depth of the first type of node corresponding to the second training sample as the second training label.

[0155] In some embodiments, the training of the waterlogging prediction model is similar to the training of the efficiency prediction model. For information on training the efficiency prediction model, please refer to [link to relevant documentation]. Figure 2 Related descriptions.

[0156] In some embodiments, the inputs to the water accumulation prediction model also include drainage parameters 320, drainage efficiency 330, and water splash data 340 of the drainage device.

[0157] Water splash data refers to the data on the pattern of water splashes caused by vehicle wheels. For example, water splash data can include the size and shape of the splashes.

[0158] In some embodiments, the emergency monitoring and management platform can obtain water splash data through the emergency monitoring object platform.

[0159] For example, emergency monitoring and management platforms can use cameras to capture data on the water splashes from vehicle wheels as they pass through low-lying areas. More information about cameras can be found at [link to relevant documentation]. Figure 1 Related descriptions.

[0160] In some embodiments, the second training sample may further include sample drainage parameters of the drainage device, sample drainage efficiency, and sample water splash data.

[0161] In some embodiments of this specification, considering the drainage parameters, drainage efficiency, and water splash data of the drainage device can make the determined water accumulation data more closely reflect the actual situation.

[0162] In some embodiments of this specification, the drainage effect of manhole covers on low-lying areas is fully considered due to the factor of rainfall injecting water into low-lying areas. At the same time, the water accumulation map is constructed to take into account the entire spatial structure, which makes the determined water accumulation data closer to the actual situation. By determining the water accumulation data through the water accumulation prediction model, the prediction error can be reduced and the prediction effect can be improved.

[0163] Figure 4 This is a schematic diagram illustrating the determination of driving warning and signal control commands according to some embodiments of this specification.

[0164] In some embodiments, it is known that vehicle driving risk 411 has two states: above the second threshold 420 and below the second threshold 420; and road risk 412 has two states: above the third threshold 460 and below the third threshold 460. In response to vehicle driving risk 411 being above the second threshold 420, the emergency monitoring and management platform can determine driving warning 430 and push driving warning 430 to multiple vehicles 450 through warning device 440; and in response to road risk 412 being above the third threshold 460, the emergency monitoring and management platform can generate signal control command 470.

[0165] For more information on early warning devices, please refer to [link / reference]. Figure 1 Related descriptions.

[0166] The second threshold refers to the minimum vehicle driving risk required to determine a driving warning.

[0167] In some embodiments, the second threshold may be determined by the emergency monitoring and management platform based on a default preset.

[0168] Driving warnings refer to alerts sent to a vehicle. For example, driving warnings may include warning icons on a navigation map.

[0169] In some embodiments, driving warnings can be generated by the emergency monitoring and management platform based on default presets.

[0170] For example, the emergency monitoring and management platform can pre-set driving warnings when the risk of vehicle travel is high in each low-lying area.

[0171] In some embodiments, there are known situations where the vehicle driving risk is either higher than a second threshold or lower than the second threshold. In response to a vehicle driving risk exceeding the second threshold, the emergency monitoring and management platform can send a real-time driving warning to the vehicle via a warning device. For example, in response to a vehicle driving risk in a low-lying area exceeding the second threshold, the emergency monitoring and management platform can send a pre-set driving warning for that low-lying area to the vehicle via a warning device.

[0172] The third threshold refers to the minimum road risk required to generate signal control instructions.

[0173] In some embodiments, the first threshold is less than the second threshold and less than the third threshold.

[0174] In some embodiments, the third threshold may be determined by the emergency monitoring and management platform based on a default preset.

[0175] Signal control instructions are instructions used to control traffic signal equipment to display warning information.

[0176] In some embodiments, the signal control command 470 may be configured to control multiple traffic lights 480 to display specific colors during specific time periods, and / or control electronic road signs 490 to display specific content during preset time periods.

[0177] For example, if the road risk is high during the current time period, the emergency monitoring and management platform can send signal control instructions to traffic lights to turn them red, and / or send signal control instructions to electronic road signs to display "No Entry Due to Flooding".

[0178] For more information on traffic signal equipment, please refer to [link / reference]. Figure 1 Related descriptions.

[0179] In some embodiments, the emergency monitoring and management platform can generate signal control instructions based on road risks.

[0180] In some embodiments of this specification, a warning device pushes driving warnings to multiple vehicles and generates signal control commands, which can provide early warnings to vehicles, reduce the incidence of vehicle accidents, reduce congestion in low-lying areas, and ensure traffic efficiency and safety redundancy.

[0181] This specification provides one or more embodiments of a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions from the storage medium, the computer executes an emergency monitoring method.

[0182] 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.

Claims

1. A large-scale IoT model system for emergency monitoring of low-lying urban road sections, characterized in that, The emergency monitoring IoT big data model system includes an emergency monitoring management platform; The emergency monitoring and management platform is configured as follows: Vehicle data in low-lying areas can be obtained through the emergency monitoring platform; The water accumulation data is determined based on the driving data; Traffic risks are determined based on the aforementioned water accumulation data; In response to the traffic risk exceeding a first threshold, drainage parameters are determined; Based on the drainage parameters, the scheduling parameters are determined; and, Based on the scheduling parameters, a scheduling packet containing the drainage parameters is sent to the unmanned vehicle cluster through a heterogeneous communication network, and the unmanned vehicles equipped with drainage devices are controlled to drive to the low-lying area, and the pumping power of the drainage devices is adjusted to the pumping power of the drainage parameters.

2. The system according to claim 1, characterized in that, The emergency monitoring and management platform is further configured as follows: Data on manhole cover distribution and rainfall can be obtained through the emergency monitoring user platform; Based on the driving data, the rainfall, and the distribution of manhole covers, a water accumulation map is constructed; and, Based on the water accumulation map, the water accumulation data is predicted using a water accumulation prediction model, which is a machine learning model.

3. The system according to claim 1, characterized in that, The emergency monitoring and management platform is further configured as follows: The emergency monitoring platform obtains road traffic flow and vehicle height distribution within a preset range; Based on the vehicle height distribution and the water accumulation data, the vehicle driving risk is determined; Based on the road traffic flow and water accumulation data within the preset range, road risks are determined; as well as, The traffic risk is determined based on the vehicle driving risk, the road risk, and the current time period.

4. The system according to claim 3, characterized in that, The emergency monitoring and management platform is further configured as follows: In response to the vehicle driving risk being higher than a second threshold, a driving warning is determined, and the driving warning is pushed to multiple vehicles through the warning device; In response to the road risk exceeding a third threshold, a signal control instruction is generated, which is configured to control multiple traffic lights to display preset colors during a preset time period and / or control electronic road signs to display preset content during a preset time period.

5. The system according to claim 1, characterized in that, The drainage parameters include the distribution of drainage devices and the pumping power of each drainage device. The emergency monitoring and management platform is further configured as follows: Based on the water accumulation data, candidate drainage parameters, traffic risks, and road traffic flow within a preset range, the drainage efficiency is determined using an efficiency prediction model; and, The drainage parameters are determined based on the drainage efficiency.

6. A method for emergency monitoring of low-lying urban road sections, characterized in that, The method is executed based on an emergency monitoring and management platform and includes: Vehicle data in low-lying areas can be obtained through the emergency monitoring platform; The water accumulation data is determined based on the driving data; Traffic risks are determined based on the aforementioned water accumulation data; In response to the traffic risk exceeding a first threshold, drainage parameters are determined; Based on the drainage parameters, the scheduling parameters are determined; and, Based on the scheduling parameters, a scheduling packet containing the drainage parameters is sent to the unmanned vehicle cluster through a heterogeneous communication network, and the unmanned vehicles equipped with drainage devices are controlled to drive to the low-lying area, and the pumping power of the drainage devices is adjusted to the pumping power of the drainage parameters.

7. The method according to claim 6, characterized in that, The determination of water accumulation data based on the driving data includes: Data on manhole cover distribution and rainfall can be obtained through the emergency monitoring user platform; Based on the driving data, the rainfall, and the distribution of manhole covers, a water accumulation map is constructed; and, Based on the water accumulation map, the water accumulation data is predicted using a water accumulation prediction model, which is a machine learning model.

8. The method according to claim 6, characterized in that, The determination of traffic risks based on the water accumulation data includes: The emergency monitoring platform obtains road traffic flow and vehicle height distribution within a preset range; Based on the vehicle height distribution and the water accumulation data, the vehicle driving risk is determined; Based on the road traffic flow and water accumulation data within the preset range, road risk is determined; and, The traffic risk is determined based on the vehicle driving risk, the road risk, and the current time period.

9. The method according to claim 6, characterized in that, The drainage parameters include the distribution of drainage devices and the pumping power of each drainage device. The determination of the drainage parameters in response to the traffic risk exceeding a first threshold includes: Based on the water accumulation data, candidate drainage parameters, traffic risks, and road traffic flow within a preset range, the drainage efficiency is determined using an efficiency prediction model; and, The drainage parameters are determined based on the drainage efficiency.

10. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the emergency monitoring method for low-lying urban road sections as described in any one of claims 6-9.

Images