Event handling method, device, electronic device and storage medium

Abstract

This invention provides an event handling method, which includes: importing real-time monitoring data of a target city into a preset digital twin city model for simulation and prediction processing to obtain event simulation results and event prediction results for the target city; determining, based on the event simulation results and event prediction results, whether a preset emergency event exists, wherein the emergency event is an emergency event awaiting execution by an embodied robot; if an emergency event exists, matching the embodied robot and its action parameters in the digital twin city model to perform strategy simulation processing to obtain an emergency event handling strategy; and scheduling the target embodied robot based on the handling strategy to enable the target embodied robot to handle the emergency event. By simulating and predicting the target city using a digital twin city model, ongoing or potential emergency events in the target city can be detected in a timely manner, and combined with the scheduling of embodied robots, the efficiency of urban governance can be improved.

Description

Technical Field

[0001] This invention relates to the fields of smart cities and embodied intelligence, and more particularly to an event handling method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the rapid development of artificial intelligence and smart cities, urban governance faces higher demands for intelligence, aiming to free up more labor in the process. This primarily involves increasing the use of robots for urban governance. Traditional robot scheduling is task-driven. However, task discovery, uploading, and generation all rely on manual processes. After a task is discovered and uploaded manually, it is assigned to the corresponding robot for execution. This scheduling method is highly dependent on the efficiency of manual task uploading. In scenarios involving the governance of megacities, robot scheduling efficiency is not high, especially in emergency response where timely discovery and handling are crucial. Therefore, a solution to improve the efficiency of governance in megacities is urgently needed. Summary of the Invention

[0003] This invention provides an event handling method, aiming to offer a solution for improving the governance efficiency of megacities. By simulating and predicting the target city using a digital twin city model, ongoing or potential emergency events can be detected in a timely manner. Through the scheduling of embodied robots, the efficiency and accuracy of handling emergency events in the target city are improved, thereby enhancing urban governance efficiency.

[0004] In a first aspect, embodiments of the present invention provide an event handling method, the method comprising the following steps:

[0005] Real-time monitoring data of the target city is imported into a preset digital twin city model for simulation and prediction processing to obtain event simulation results and event prediction results of the target city. The digital twin city model is constructed based on the physical space of the target city and includes a static three-dimensional model and a dynamic three-dimensional model.

[0006] Based on the event simulation results and the event prediction results, it is determined whether there is a preset emergency event, which is an emergency event waiting for the embodied robot to execute.

[0007] If the emergency event exists, the embodied robot and its action parameters are matched in the digital twin city model to perform strategy simulation processing, thereby obtaining the emergency event handling strategy, which includes the target embodied robot for handling the emergency event.

[0008] The target avatar robot is scheduled based on the aforementioned handling strategy so that it can handle the emergency event.

[0009] Optionally, before importing the real-time monitoring data of the target city into a preset digital twin city model for simulation and prediction processing, the method further includes:

[0010] Construct a static 3D model of the target city based on its physical space;

[0011] A dynamic 3D model of the target city is constructed based on the dynamic data of the target city, and the dynamic 3D model is driven by the monitoring data;

[0012] Based on the static 3D model and the dynamic 3D model, a digital twin city model of the target city is obtained by combining them.

[0013] Optionally, the step of importing real-time monitoring data of the target city into a preset digital twin city model for simulation and prediction processing to obtain event simulation results and event prediction results for the target city includes:

[0014] Import real-time monitoring data of the target city into the dynamic 3D model and drive the dynamic 3D model.

[0015] The target city is simulated using the dynamic 3D model under driving conditions to obtain real-time simulation data of the target city;

[0016] The real-time simulation data is subjected to first event detection processing to obtain the event simulation results of the target city;

[0017] The target city is predicted in a future time period by using the dynamic three-dimensional model under driving conditions to obtain the predicted data of the target city.

[0018] The predicted data is subjected to a second event detection process to obtain the event prediction results for the target city in the future time period.

[0019] Optionally, the event simulation results include at least one simulated event, the event prediction results include at least one predicted event, and determining whether a preset emergency event exists based on the event simulation results and the event prediction results includes:

[0020] In at least one of the simulation events, determine whether there is a simulation event in which the embodied robot was not scheduled to handle it;

[0021] If there is a simulation event that is not handled by the embodied machine, then a preset emergency event is determined, and the unhandled simulation event is determined as an emergency event.

[0022] And, in at least one of the predicted events, determine whether there is a predicted event that requires dispatching the embodied robot to handle;

[0023] If there is a predicted event that requires the avatar robot to handle, then a preset emergency event is determined, and the predicted event that requires the avatar robot to handle is determined as an emergency event.

[0024] Optionally, if the emergency event exists, the action parameters of the embodied robot and the embodied robot are matched in the digital twin city model to perform strategy simulation processing, thereby obtaining a strategy for handling the emergency event, including:

[0025] Determine the location of the emergency event within the digital twin city model;

[0026] Based on the event location, all the avatars within a preset range are matched as candidate avatars, and the action parameters of the candidate avatars are obtained, wherein the action parameters are the drive data of the candidate avatars;

[0027] With the goal of minimizing the cost of handling the emergency, a strategy simulation is performed to obtain the strategy for handling the emergency.

[0028] Optionally, the step of performing strategy simulation processing with the objective of minimizing the cost of handling the emergency to obtain the emergency handling strategy includes:

[0029] In the digital twin city model, the environmental distribution that the candidate embodied robot needs to experience to reach the event location is determined;

[0030] Based on the action parameters and the environmental distribution, the driving cost of the candidate embodied robot is calculated;

[0031] And, based on the level of the emergency event, determine the event development cost of the emergency event;

[0032] With the goal of minimizing the driving cost and the event development cost, a strategy simulation is performed to obtain the emergency response strategy.

[0033] Optionally, scheduling the target embodied robot based on the handling strategy to enable the target embodied robot to handle the emergency event includes:

[0034] Based on the aforementioned disposal strategy, a disposal task for the target embodied robot is generated, the disposal task including the target embodied robot's task route and task instructions;

[0035] The disposal task is sent to the target avatar robot so that the target avatar robot can execute the disposal task and complete the disposal of the emergency.

[0036] Secondly, embodiments of the present invention also provide an event handling device, the event handling device comprising:

[0037] The first processing module is used to import real-time monitoring data of the target city into a preset digital twin city model for simulation and prediction processing, and obtain the event simulation results and event prediction results of the target city. The digital twin city model is constructed based on the physical space of the target city and includes a static three-dimensional model and a dynamic three-dimensional model.

[0038] The second processing module is used to determine whether there is a preset emergency event based on the event simulation results and the event prediction results. The emergency event is an emergency event waiting for the embodied robot to execute.

[0039] The third processing module is used to match the embodied robot and the action parameters of the embodied robot in the digital twin city model to perform strategy simulation processing if the emergency event exists, so as to obtain the emergency event handling strategy, the handling strategy including the target embodied robot for handling the emergency event;

[0040] An event handling module is used to schedule the target embodied robot based on the handling strategy, so that the target embodied robot can handle the emergency event.

[0041] Thirdly, embodiments of the present invention provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the event handling method provided in embodiments of the present invention.

[0042] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps in the event handling method provided in the embodiments of the invention.

[0043] In this embodiment of the invention, real-time monitoring data of the target city is imported into a preset digital twin city model for simulation and prediction processing to obtain event simulation results and event prediction results for the target city. The digital twin city model is constructed based on the physical space of the target city and includes a static 3D model and a dynamic 3D model. Based on the event simulation and prediction results, it is determined whether a preset emergency event exists, which is an emergency event waiting for the embodied robot to execute. If an emergency event exists, the embodied robot and its action parameters are matched in the digital twin city model to perform strategy simulation processing, resulting in an emergency event handling strategy. The handling strategy includes a target embodied robot for handling the emergency event. Based on the handling strategy, the target embodied robot is scheduled to handle the emergency event. By simulating and predicting the target city using the digital twin city model, ongoing or potential emergency events in the target city can be detected in a timely manner. Through the scheduling of embodied robots, the efficiency and accuracy of handling emergency events in the target city are improved, thereby improving urban governance efficiency. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart of an event handling method provided in an embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram of the structure of an event handling device provided in an embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0048] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] like Figure 1 As shown, Figure 1 This is a flowchart of an event handling method provided in an embodiment of the present invention, including:

[0050] 101. Import the real-time monitoring data of the target city into the preset digital twin city model for simulation and prediction processing to obtain the event simulation results and event prediction results of the target city.

[0051] In this embodiment of the invention, the aforementioned event handling method can be applied to an urban governance platform. This platform can be built on a server or distributed server and includes functional applications supporting intelligent urban governance, such as a digital twin city model, monitoring equipment communication interfaces, and avatar robot communication interfaces. The urban governance platform communicates with monitoring equipment deployed in the target city through the monitoring equipment communication interface to obtain monitoring data collected by the equipment. It also communicates with avatar robots deployed in the target city through the avatar robot communication interface to distribute disposal tasks to the corresponding avatar robots, enabling them to execute these tasks. Through this urban governance platform, large-scale urban governance can be achieved using monitoring equipment and avatar robots.

[0052] The aforementioned real-time monitoring data can be collected by surveillance equipment deployed in the target city. This real-time monitoring data can include pedestrian data, vehicle data, weather data, etc. The aforementioned surveillance equipment can be surveillance cameras, weather sensors, or other monitoring devices capable of dynamic data acquisition. The aforementioned real-time monitoring data can be streaming data collected by the surveillance equipment, or structured or semi-structured data resulting from structured processing of the streaming data collected by the surveillance equipment.

[0053] It should be noted that the aforementioned digital twin city model is a digital model constructed based on the target city, specifically a virtual model built in cyberspace that completely corresponds to the physical city. This model can reflect the entire operational process of entities within the physical city. The digital twin city model in this embodiment of the invention is mainly used for event discovery and governance strategy formulation in urban governance. Therefore, compared to general digital twin city models, the selection of monitoring equipment can be more specialized.

[0054] A digital twin city model is constructed based on the physical space of the target city. It includes a static 3D model and a dynamic 3D model. The static 3D model primarily reflects the existence of static entities in the target city, such as buildings, roads, roadside facilities, parks, and trees—immovable entities. The dynamic 3D model primarily reflects the operational processes of dynamic entities in the target city, such as pedestrians, vehicles, and animals—movable entities.

[0055] The simulation process described above is primarily based on simulating dynamic entities using a dynamic 3D model, with the real-time monitoring data serving as the driving data for these dynamic entities. Specifically, behavioral and spatial data of the dynamic entities can be extracted from the monitoring data and used as driving data for the dynamic entities, which is then used to drive the simulation processing of the dynamic 3D model within the digital twin city model.

[0056] City-level simulation processing is performed on real-time monitoring data using a digital twin city model. During the simulation, the model detects whether any events are occurring or pending. If an event is occurring, it is used as the simulation result; if an event is pending, it is used as the prediction result. When the simulation result is output, it includes at least one simulated event that is currently occurring. When the prediction result is output, it includes at least one predicted event that is pending.

[0057] It is understandable that the above event prediction results are simulations of future events, meaning that the events currently occurring are simulated events at the current moment. The above event prediction results are also predictions of future events, meaning that the events to be occurred are events that may occur in the future.

[0058] 102. Based on the event simulation results and event prediction results, determine whether there are any pre-set emergency events.

[0059] In this embodiment of the invention, the aforementioned emergency event is an emergency event awaiting execution by the embodied robot. After obtaining the event simulation results and event prediction results, the simulated events in the event simulation results and the predicted events in the event prediction results can be classified, and it can be determined whether the simulated events and predicted events are preset emergency events based on the classification results.

[0060] The aforementioned emergency events can specifically include traffic congestion, traffic violations, crowd gatherings, overflowing garbage, and street vendors, all of which require the embodied robot to take action. There can be one or more of these emergency events.

[0061] 103. If an emergency occurs, the action parameters of the embodied robot and the embodied robot are matched in the digital twin city model to perform strategy simulation processing and obtain the emergency response strategy.

[0062] In this embodiment of the invention, when an emergency occurs, it is necessary to dispatch an embodied robot to the incident location for handling. During the dispatching process, factors such as different levels of emergency events, a large number of embodied robots, different distribution locations, different data required for handling the event, different task route planning, and different environments at the incident location may affect the handling effect of the emergency. Therefore, strategy simulation can be performed for each emergency event based on the above-mentioned emergency event handling factors to obtain the optimal handling strategy for each emergency event. The handling strategy includes the target embodied robot for handling the emergency event and may also include the scheduling strategy of the target embodied robot.

[0063] 104. Based on the handling strategy, the target embodied robot is scheduled so that the target embodied robot can handle emergency events.

[0064] In this embodiment of the invention, after obtaining the disposal strategy, the disposal strategy can be converted into a corresponding task. The city governance platform issues the task to the target embodied robot in the form of a task, so that the target embodied robot can perform the corresponding task and thus complete the disposal of the emergency.

[0065] In this embodiment of the invention, real-time monitoring data of the target city is imported into a preset digital twin city model for simulation and prediction processing to obtain event simulation results and event prediction results for the target city. The digital twin city model is constructed based on the physical space of the target city and includes a static 3D model and a dynamic 3D model. Based on the event simulation and prediction results, it is determined whether a preset emergency event exists, which is an emergency event waiting for the embodied robot to execute. If an emergency event exists, the embodied robot and its action parameters are matched in the digital twin city model to perform strategy simulation processing, resulting in an emergency event handling strategy. The handling strategy includes a target embodied robot for handling the emergency event. Based on the handling strategy, the target embodied robot is scheduled to handle the emergency event. By simulating and predicting the target city using the digital twin city model, ongoing or potential emergency events in the target city can be detected in a timely manner. Through the scheduling of embodied robots, the efficiency and accuracy of handling emergency events in the target city are improved, thereby improving urban governance efficiency.

[0066] It should be noted that the event handling method provided in this embodiment of the invention can be applied to electronic devices such as mobile phones, tablets, computers, and servers that are capable of event handling.

[0067] It is understood that in the specific implementation of this application, data such as monitoring data, map data, and city data are involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required. Furthermore, the collection, use, and processing of related data, as well as the training, deployment, and invocation of various models, must comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0068] Optionally, before importing the real-time monitoring data of the target city into the preset digital twin city model for simulation and prediction processing, a static three-dimensional model of the target city can be constructed based on the physical space of the target city; a dynamic three-dimensional model of the target city can be constructed based on the dynamic data of the target city, and the dynamic three-dimensional model is driven by the monitoring data; based on the static three-dimensional model and the dynamic three-dimensional model, a digital twin city model of the target city can be obtained by combining them.

[0069] In this embodiment of the invention, the physical space of the target city can be composed of immovable entities such as buildings, roads, roadside facilities, parks, and trees. These immovable entities are also called static entities. The static 3D model is mainly used to reflect the existence of static entities in the target city. The corresponding static 3D model can be constructed using 3D modeling software. The static 3D model is the basic model of the digital twin city model, representing the fixed structure of the target city in cyberspace.

[0070] The aforementioned dynamic data can be the shape data of movable entities such as pedestrians, vehicles, and animals. These movable entities are also called dynamic entities. Corresponding dynamic 3D models can be constructed for different types of dynamic entities. Each type of dynamic entity has one dynamic 3D model. In use, if there are multiple dynamic entities of the same type, multiple dynamic 3D models can be generated by copying. The dynamic 3D models are mainly used to reflect the operation process of dynamic entities in the target city.

[0071] After obtaining the static and dynamic 3D models, they can be combined to obtain a basic digital twin city model. The dynamic 3D model can be added or removed based on the number of dynamic entities in the real-time monitoring data, and driven by the behavioral and spatial data of the dynamic entities in the real-time monitoring data.

[0072] By constructing static and dynamic 3D models, the digital twin city model can perform operational status detection by combining the fixed structure of the static 3D model during simulation. This allows for simulation of the dynamic entity's operation process in conjunction with the environment, making the simulation more accurate and consequently leading to more accurate event detection.

[0073] Optionally, in the step of importing real-time monitoring data of the target city into a preset digital twin city model for simulation and prediction processing to obtain event simulation results and event prediction results of the target city, the real-time monitoring data of the target city can be imported into a dynamic 3D model and driven; the target city can be simulated using the dynamic 3D model under the driven state to obtain real-time simulation data of the target city; a first event detection process can be performed on the real-time simulation data to obtain event simulation results of the target city; the target city can be predicted using the dynamic 3D model under the driven state in the future time period to obtain prediction data of the target city; and a second event detection process can be performed on the prediction data to obtain event prediction results of the target city in the future time period.

[0074] In this embodiment of the invention, the simulation processing described above is mainly based on simulating dynamic entities using a dynamic 3D model, with the real-time monitoring data serving as the driving data for the dynamic entities. Specifically, behavioral and spatial data of the dynamic entities can be extracted from the monitoring data, and this behavioral and spatial data can be used as the driving data for the dynamic entities to drive the dynamic 3D model to run in the digital twin city model, and the running status of the dynamic 3D model can be monitored, thereby achieving digital simulation of the target city.

[0075] By using the monitored dynamic 3D model's operational status data as real-time simulation data for the target city, and employing an event detection model to perform first-event detection on this data, the event simulation results for the target city can be obtained. This event detection model can be a neural network-based detection model.

[0076] By using Kalman filtering or a time-series prediction network to predict the global operational status data, the predicted data for the target city can be obtained. Then, by using the event detection model described above to perform a second event detection on the predicted data, the event prediction results for the target city can be obtained.

[0077] It should be noted that event detection through a digital twin city model allows for centralized event discovery within the model itself, enabling timely detection of both ongoing and potential events, thereby improving the efficiency of emergency response. Furthermore, the aforementioned event prediction is based on global operational status data from the digital twin city model, followed by event detection, which enhances the accuracy of the predicted event results.

[0078] Optionally, in the step of determining whether a preset emergency event exists based on the event simulation results and the event prediction results, it can be determined whether there is a simulation event in at least one simulation event that is not handled by the embodied robot; if there is a simulation event that is not handled by the embodied robot, then it is determined that a preset emergency event exists, and the unhandled simulation event is identified as an emergency event; and, in at least one predicted event, it can be determined whether there is a predicted event that requires the embodied robot to be handled; if there is a predicted event that requires the embodied robot to be handled, then it is determined that a preset emergency event exists, and the predicted event that requires the embodied robot to be handled is identified as an emergency event.

[0079] In this embodiment of the invention, for simulated events, since the simulated event is an ongoing event, it may have already been handled by a robot, i.e., a simulated event that has been handled by a robot, or it may be a sudden event that has not yet been handled by a robot, i.e., an unhandled simulated event. When at least one simulated event exists that has not been handled by a robot, it indicates that a preset emergency event exists, and the unhandled simulated event can be identified as an emergency event.

[0080] For predicted events, since these are events that have not yet occurred, such as traffic congestion within 10 minutes or trash can A overflowing within 5 minutes, requiring the deployment of embodied robots for handling, these can be considered pre-set emergency events. Therefore, predicted events requiring the deployment of embodied robots for handling can be identified as emergency events.

[0081] In one possible embodiment, to avoid duplicate confirmation, predicted events can be marked so that predicted events marked as emergency events will not be repeatedly confirmed as new emergency events. This can effectively reduce the systematic error of predicted events, thereby reducing the false detection rate of emergency events.

[0082] Optionally, in the step of matching embodied robots and their action parameters in the digital twin city model to perform strategy simulation processing and obtain the emergency response strategy if an emergency occurs, the location of the emergency in the digital twin city model can be determined; based on the event location, all embodied robots within a preset range are matched as candidate embodied robots, and the action parameters of the candidate embodied robots are obtained, which are the driving data of the candidate embodied robots; with the goal of minimizing the cost of handling the emergency, strategy simulation processing is performed to obtain the emergency response strategy.

[0083] In this embodiment of the invention, the number of the above-mentioned emergency events is one or more. For each emergency event, the event location can be determined in the digital twin city model. Each location in the digital twin city model has a corresponding real location in the physical space of the target city.

[0084] After obtaining the location of the emergency, the location can be used as the search center to search for available avatar robots within a preset range. If no available avatar robots are found within the preset range, the search range will be expanded to continue searching for available avatar robots.

[0085] The aforementioned action parameters can be parameters such as the power parameters and energy consumption parameters of the embodied robot.

[0086] After identifying available avatar robots, these are designated as candidate robots. When there are multiple candidate robots, their numbers and routes need to be planned to handle emergencies at the lowest possible cost. The cost of handling emergencies includes the cost of dispatching avatar robots and the cost of the emergency's development. The more avatar robots dispatched and the longer the routes, the higher the dispatch cost; conversely, the longer the emergency lasts, the greater the development cost. Since a larger number of avatar robots results in a shorter emergency resolution time, it is evident that the cost of dispatching avatar robots is negatively correlated with the development cost of the emergency. Therefore, the cost of dispatching emergency robots should be balanced with the development cost of the emergency to minimize the overall cost of handling the emergency.

[0087] Specifically, strategies for handling emergency events can be simulated in digital twin city models using algorithms such as decision trees and game theory models.

[0088] Optionally, in the step of performing strategy simulation processing with the goal of minimizing the cost of handling the emergency, to obtain the emergency handling strategy, the following steps can be taken: in the digital twin city model, determine the environmental distribution that the candidate embodied robot needs to experience to reach the event location; calculate the driving cost of the candidate embodied robot based on the action parameters and environmental distribution; and determine the event development cost of the emergency according to the level of the emergency; and perform strategy simulation processing with the goal of minimizing the driving cost and the event development cost to obtain the emergency handling strategy.

[0089] In this embodiment of the invention, the aforementioned environmental distribution may include the distribution of environments such as roads, obstacles, and weather. The driving cost of the embodied robot can be determined based on the action parameters and the environmental distribution, and the driving cost curves under different environmental distributions can be predetermined. Specifically, the correlation between action parameters, environmental distribution, and driving cost can be set. This can be understood as the cost required for the embodied robot to perform a certain number of tasks. The driving cost mainly includes costs incurred due to maintenance, energy consumption, computing power, etc.

[0090] The costs of the aforementioned events can be determined based on the event level. Specifically, each type of emergency event is classified into different levels. The higher the level, the more severe the subsequent development of the emergency event. For example, without intervention, traffic congestion will worsen during peak hours, and a fire will grow larger over time. Therefore, corresponding levels can be set, and the losses caused by the emergency event at different times under different levels can be used as costs to form a time cost curve for the emergency event.

[0091] It should be noted that the higher the emergency level, the steeper the corresponding time cost curve, which can be understood as a greater change in slope. Conversely, the lower the emergency level, the flatter the corresponding time cost curve, which can be understood as a smaller change in slope.

[0092] Based on the aforementioned driving cost curve and time cost curve, and with the goal of minimizing both driving cost and event development cost, a game theory algorithm is used for strategy simulation to find the solution that reaches Nash equilibrium. The strategy that reaches Nash equilibrium is then determined as the emergency response strategy. This approach ensures that the emergency does not exceed the scope of handling and does not consume excessive resources of the embodied robot.

[0093] Optionally, in the step of scheduling the target embodied robot based on the handling strategy to enable the target embodied robot to handle the emergency, a handling task for the target embodied robot can be generated based on the handling strategy. The handling task includes the task route and task instructions of the target embodied robot. The handling task is then sent to the target embodied robot so that the target embodied robot can execute the handling task and complete the handling of the emergency.

[0094] In this embodiment of the invention, after obtaining the emergency response strategy, the actions and behaviors that the target embodied robot needs to perform when responding to the emergency can be instructed to obtain task instructions, and the planned route of the target embodied robot can be converted into a task route, thereby obtaining the response task of the target embodied robot.

[0095] like Figure 2 As shown, embodiments of the present invention also provide an event handling device, comprising:

[0096] The first processing module 201 is used to import real-time monitoring data of the target city into a preset digital twin city model for simulation and prediction processing, and obtain the event simulation results and event prediction results of the target city. The digital twin city model is constructed based on the physical space of the target city and includes a static three-dimensional model and a dynamic three-dimensional model.

[0097] The second processing module 202 is used to determine whether there is a preset emergency event based on the event simulation results and the event prediction results, wherein the emergency event is an emergency event waiting for the embodied robot to execute.

[0098] The third processing module 203 is used to match the embodied robot and the action parameters of the embodied robot in the digital twin city model to perform strategy simulation processing if the emergency event exists, so as to obtain the emergency event handling strategy, the handling strategy including the target embodied robot for handling the emergency event;

[0099] The event handling module 204 is used to schedule the target embodied robot based on the handling strategy, so that the target embodied robot can handle the emergency event.

[0100] Optionally, the device further includes:

[0101] The first construction module is used to construct a static three-dimensional model of the target city based on the physical space of the target city;

[0102] The second construction module is used to construct a dynamic three-dimensional model of the target city based on the dynamic data of the target city, and the dynamic three-dimensional model is driven by the monitoring data.

[0103] The combination module is used to combine the static 3D model and the dynamic 3D model to obtain a digital twin city model of the target city.

[0104] Optionally, the first processing module 201 is further configured to import real-time monitoring data of the target city into the dynamic three-dimensional model and drive the dynamic three-dimensional model; perform simulation processing on the target city through the dynamic three-dimensional model in the driven state to obtain real-time simulation data of the target city; perform a first event detection processing on the real-time simulation data to obtain event simulation results of the target city; perform prediction processing on the target city in a future time period through the dynamic three-dimensional model in the driven state to obtain prediction data of the target city; and perform a second event detection processing on the prediction data to obtain event prediction results of the target city in the future time period.

[0105] Optionally, the event simulation result includes at least one simulated event, and the event prediction result includes at least one predicted event. The second processing module 202 is further configured to determine, among the at least one simulated event, whether there is a simulated event for which the embodied robot was not scheduled to handle; if there is a simulated event for which the embodied robot was not scheduled to handle, then a preset emergency event is determined to exist, and the unhandled simulated event is determined to be an emergency event; and, among the at least one predicted event, whether there is a predicted event for which the embodied robot needs to be scheduled to handle; if there is a predicted event for which the embodied robot needs to be scheduled to handle, then a preset emergency event is determined to exist, and the predicted event for which the embodied robot needs to be scheduled to handle is determined to be an emergency event.

[0106] Optionally, the third processing module 203 is further configured to determine the location of the emergency event in the digital twin city model; based on the event location, match all the avatar robots within a preset range as candidate avatar robots, and obtain the action parameters of the candidate avatar robots, wherein the action parameters are the driving data of the candidate avatar robots; with the goal of minimizing the cost of handling the emergency event, perform strategy simulation processing to obtain the handling strategy of the emergency event.

[0107] Optionally, the third processing module 203 is further configured to, in the digital twin city model, determine the environmental distribution that the candidate embodied robot needs to experience to reach the event location; calculate the driving cost of the candidate embodied robot based on the action parameters and the environmental distribution; determine the event development cost of the emergency event according to the level of the emergency event; and perform strategy simulation processing with the goal of minimizing the driving cost and the event development cost to obtain the emergency event handling strategy.

[0108] Optionally, the event handling module 204 is further configured to generate a handling task for the target avatar robot based on the handling strategy, the handling task including the task route and task instructions of the target avatar robot; and to send the handling task to the target avatar robot so that the target avatar robot can execute the handling task and complete the handling of the emergency event.

[0109] It should be noted that the event handling device provided in this embodiment of the invention can be applied to devices such as smartphones, computers, and servers that are capable of performing event handling methods.

[0110] The event handling device provided in this embodiment of the invention can implement all the processes implemented by the regional retention method in the above-described method embodiments, and can achieve the same beneficial effects. To avoid repetition, it will not be described again here.

[0111] like Figure 3 As shown, this embodiment of the invention also provides an electronic device, characterized in that it includes a processor, which can execute any of the above-described event handling methods.

[0112] Specifically, it includes a processor 301 and a memory 302, as well as a computer program stored in the memory 302 and capable of running on the processor 301 to execute event handling methods, wherein:

[0113] The processor 301 executes the calculator program containing the event handling methods stored in memory 302, and performs the following steps:

[0114] Real-time monitoring data of the target city is imported into a preset digital twin city model for simulation and prediction processing to obtain event simulation results and event prediction results of the target city. The digital twin city model is constructed based on the physical space of the target city and includes a static three-dimensional model and a dynamic three-dimensional model.

[0115] Based on the event simulation results and the event prediction results, it is determined whether there is a preset emergency event, which is an emergency event waiting for the embodied robot to execute.

[0116] If the emergency event exists, the embodied robot and its action parameters are matched in the digital twin city model to perform strategy simulation processing, thereby obtaining the emergency event handling strategy, which includes the target embodied robot for handling the emergency event.

[0117] The target avatar robot is scheduled based on the aforementioned handling strategy so that it can handle the emergency event.

[0118] Optionally, before importing the real-time monitoring data of the target city into a preset digital twin city model for simulation and prediction processing, the method executed by the processor 301 further includes:

[0119] Construct a static 3D model of the target city based on its physical space;

[0120] A dynamic 3D model of the target city is constructed based on the dynamic data of the target city, and the dynamic 3D model is driven by the monitoring data;

[0121] Based on the static 3D model and the dynamic 3D model, a digital twin city model of the target city is obtained by combining them.

[0122] Optionally, the processor 301 executes the step of importing real-time monitoring data of the target city into a preset digital twin city model for simulation and prediction processing to obtain event simulation results and event prediction results for the target city, including:

[0123] Import real-time monitoring data of the target city into the dynamic 3D model and drive the dynamic 3D model.

[0124] The target city is simulated using the dynamic 3D model under driving conditions to obtain real-time simulation data of the target city;

[0125] The real-time simulation data is subjected to first event detection processing to obtain the event simulation results of the target city;

[0126] The target city is predicted in a future time period by using the dynamic three-dimensional model under driving conditions to obtain the predicted data of the target city.

[0127] The predicted data is subjected to a second event detection process to obtain the event prediction results for the target city in the future time period.

[0128] Optionally, the event simulation result includes at least one simulated event, the event prediction result includes at least one predicted event, and the process executed by processor 301 to determine whether a preset emergency event exists based on the event simulation result and the event prediction result includes:

[0129] In at least one of the simulation events, determine whether there is a simulation event in which the embodied robot was not scheduled to handle it;

[0130] If there is a simulation event that is not handled by the embodied machine, then a preset emergency event is determined, and the unhandled simulation event is determined as an emergency event.

[0131] And, in at least one of the predicted events, determine whether there is a predicted event that requires dispatching the embodied robot to handle;

[0132] If there is a predicted event that requires the avatar robot to handle, then a preset emergency event is determined, and the predicted event that requires the avatar robot to handle is determined as an emergency event.

[0133] Optionally, the processor 301 executes the step of matching the embodied robot and its action parameters in the digital twin city model to perform strategy simulation processing if the emergency event exists, to obtain a strategy for handling the emergency event, including:

[0134] Determine the location of the emergency event within the digital twin city model;

[0135] Based on the event location, all the avatars within a preset range are matched as candidate avatars, and the action parameters of the candidate avatars are obtained, wherein the action parameters are the drive data of the candidate avatars;

[0136] With the goal of minimizing the cost of handling the emergency, a strategy simulation is performed to obtain the strategy for handling the emergency.

[0137] Optionally, the processor 301 performs strategy simulation processing with the goal of minimizing the cost of handling the emergency event, to obtain a handling strategy for the emergency event, including:

[0138] In the digital twin city model, the environmental distribution that the candidate embodied robot needs to experience to reach the event location is determined;

[0139] Based on the action parameters and the environmental distribution, the driving cost of the candidate embodied robot is calculated;

[0140] And, based on the level of the emergency event, determine the event development cost of the emergency event;

[0141] With the goal of minimizing the driving cost and the event development cost, a strategy simulation is performed to obtain the emergency response strategy.

[0142] Optionally, the scheduling of the target embodied robot based on the handling strategy executed by the processor 301 to enable the target embodied robot to handle the emergency event includes:

[0143] Based on the aforementioned disposal strategy, a disposal task for the target embodied robot is generated, the disposal task including the target embodied robot's task route and task instructions;

[0144] The disposal task is sent to the target avatar robot so that the target avatar robot can execute the disposal task and complete the disposal of the emergency.

[0145] It should be noted that the electronic device provided in the embodiments of the present invention can be applied to devices such as smartphones, computers, and servers that can perform event handling methods.

[0146] The electronic device provided in this embodiment of the invention can implement all the processes of the regional retention method in the above method embodiments, and can achieve the same beneficial effects. To avoid repetition, it will not be described again here.

[0147] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the various processes of the event handling method provided in this invention and achieves the same technical effect. To avoid repetition, it will not be described again here.

[0148] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The computer-readable storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0149] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. An incident handling method, characterized in that, The method includes the following steps: Real-time monitoring data of the target city is imported into a preset digital twin city model for simulation and prediction processing to obtain event simulation results and event prediction results of the target city. The digital twin city model is constructed based on the physical space of the target city and includes a static three-dimensional model and a dynamic three-dimensional model. Based on the event simulation results and the event prediction results, it is determined whether there is a preset emergency event, which is an emergency event waiting for the embodied robot to execute. If the emergency event exists, the embodied robot and its action parameters are matched in the digital twin city model to perform strategy simulation processing, thereby obtaining the emergency event handling strategy, which includes the target embodied robot for handling the emergency event. The target embodied robot is scheduled based on the aforementioned handling strategy so that it can handle the emergency event. The process involves importing real-time monitoring data of the target city into a pre-set digital twin city model for simulation and prediction processing, resulting in event simulation and prediction results for the target city, including: Import real-time monitoring data of the target city into the dynamic 3D model and drive the dynamic 3D model. The target city is simulated using the dynamic 3D model under driving conditions to obtain real-time simulation data of the target city; The real-time simulation data is subjected to first event detection processing to obtain the event simulation results of the target city; The target city is predicted in a future time period by using the dynamic three-dimensional model under driving conditions to obtain the predicted data of the target city. The predicted data is subjected to a second event detection process to obtain the event prediction results for the target city in the future time period.

2. The incident handling method as described in claim 1, characterized in that, Before importing the real-time monitoring data of the target city into a preset digital twin city model for simulation and prediction processing, the method further includes: Construct a static 3D model of the target city based on its physical space; A dynamic 3D model of the target city is constructed based on the dynamic data of the target city, and the dynamic 3D model is driven by the monitoring data; Based on the static 3D model and the dynamic 3D model, a digital twin city model of the target city is obtained by combining them.

3. The incident handling method as described in claim 1, characterized in that, The event simulation results include at least one simulated event, and the event prediction results include at least one predicted event. The step of determining whether a preset emergency event exists based on the event simulation results and the event prediction results includes: In at least one of the simulation events, determine whether there is a simulation event in which the embodied robot was not scheduled to handle it; If there is a simulation event that is not handled by the embodied machine, then a preset emergency event is determined to exist, and the unhandled simulation event is determined to be an emergency event. And, in at least one of the predicted events, determine whether there is a predicted event that requires dispatching the embodied robot to handle; If there is a predicted event that requires the avatar robot to handle, then a preset emergency event is determined, and the predicted event that requires the avatar robot to handle is determined as an emergency event.

4. The incident handling method as described in claim 1, characterized in that, If the emergency event exists, the embodied robot and its action parameters are matched in the digital twin city model to perform strategy simulation processing, thereby obtaining the emergency event handling strategy, including: Determine the location of the emergency event within the digital twin city model; Based on the event location, all the avatars within a preset range are matched as candidate avatars, and the action parameters of the candidate avatars are obtained, wherein the action parameters are the drive data of the candidate avatars; With the goal of minimizing the cost of handling the emergency, a strategy simulation is performed to obtain the strategy for handling the emergency.

5. The incident handling method as described in claim 4, characterized in that, The strategy simulation process, aimed at minimizing the cost of handling the emergency, yields a strategy for handling the emergency, including: In the digital twin city model, the environmental distribution that the candidate embodied robot needs to experience to reach the event location is determined; Based on the action parameters and the environmental distribution, the driving cost of the candidate embodied robot is calculated; And, based on the level of the emergency event, determine the event development cost of the emergency event; With the goal of minimizing the driving cost and the event development cost, a strategy simulation is performed to obtain the emergency response strategy.

6. The incident handling method as described in any one of claims 1 to 5, characterized in that, The scheduling of the target embodied robot based on the handling strategy, so that the target embodied robot can handle the emergency event, includes: Based on the aforementioned disposal strategy, a disposal task for the target embodied robot is generated, the disposal task including the target embodied robot's task route and task instructions; The disposal task is sent to the target avatar robot so that the target avatar robot can execute the disposal task and complete the disposal of the emergency.

7. An event handling device, characterized in that, The event handling device includes: The first processing module is used to import real-time monitoring data of the target city into a preset digital twin city model for simulation and prediction processing, and obtain the event simulation results and event prediction results of the target city. The digital twin city model is constructed based on the physical space of the target city and includes a static three-dimensional model and a dynamic three-dimensional model. The second processing module is used to determine whether there is a preset emergency event based on the event simulation results and the event prediction results. The emergency event is an emergency event waiting for the embodied robot to execute. The third processing module is used to match the embodied robot and the action parameters of the embodied robot in the digital twin city model to perform strategy simulation processing if the emergency event exists, so as to obtain the emergency event handling strategy, the handling strategy including the target embodied robot for handling the emergency event; An event handling module is used to schedule the target embodied robot based on the handling strategy, so that the target embodied robot can handle the emergency event; The first processing module is further configured to import real-time monitoring data of the target city into the dynamic 3D model and drive the dynamic 3D model; perform simulation processing on the target city through the dynamic 3D model in the driven state to obtain real-time simulation data of the target city; perform a first event detection processing on the real-time simulation data to obtain event simulation results of the target city; perform prediction processing on the target city in a future time period through the dynamic 3D model in the driven state to obtain prediction data of the target city; and perform a second event detection processing on the prediction data to obtain event prediction results of the target city in the future time period.

8. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the event handling method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the event handling method as described in any one of claims 1 to 6.

Images