Smart city integrated emergency control method, Internet of Things large model system and medium

Abstract

The present invention provides a smart city integrated emergency control method, an Internet of Things large model system and a medium. The method includes: obtaining a plurality of emergency control data; the method retrieves the upload time, data type, and geographical area of ​​the plurality of emergency control data to generate a data group to be processed; according to the geographical range of the geographical area involved in the data group to be processed, the emergency control range corresponding to the temporary control area is marked in the interactive terminal of the smart city GIS system; according to the emergency control streets within the emergency control range and the crowd size corresponding to the emergency control streets, a first driving route is generated and sent to the emergency inspection vehicle; based on the driving needs of the emergency inspection vehicle and the traffic volume of the emergency control streets, the signal light phase is updated. This method can effectively improve the operating efficiency and the response speed to emergency events, and ensure the effectiveness of emergency control.

Description

Technical Field

[0001] The present invention relates to the field of smart city emergency management technology, and in particular to a smart city integrated emergency management method, an Internet of Things large model system, and a medium. Background Art

[0002] With the development of smart cities, urban emergency management also needs to be gradually improved. However, faced with a large amount of emergency control data from different sources, it is difficult to discover the correlation between different types of emergency control data by processing them independently. How to determine the relevant emergency control data and the geographical areas of emergency control is a problem that needs to be solved.

[0003] Therefore, providing a smart city integrated emergency management and control method, an Internet of Things large model system and a medium can effectively improve the operating efficiency and the response speed of emergency events, and ensure the effectiveness of emergency management and control. Summary of the Invention

[0004] One or more embodiments of the present invention provide a smart city integrated emergency management and control method, the method comprising: implementation based on a smart city integrated emergency management and control Internet of Things large model system; the method being executed based on an emergency supervision management platform, comprising: acquiring a plurality of emergency management and control data from the communication transmission network of the emergency supervision sensor network platform configured in a plurality of geographical areas, and storing the data in the memory of the general data center; retrieving the upload time, data type, and geographical area of ​​the plurality of emergency management and control data from the memory of the general data center to generate a data group to be processed; and performing a data collection operation on the data group to be processed in an interactive terminal of a smart city GIS system according to the geographical scope of the geographical area involved in the data group to be processed. The emergency control range corresponding to the temporary control area is marked, and the emergency control range corresponding to the temporary control area is displayed on the interface of the emergency control terminal; according to the emergency control streets within the emergency control range and the crowd size corresponding to the emergency control streets, a first driving route is generated and sent to the emergency patrol vehicle; the emergency patrol vehicle is controlled to execute the first driving route and conduct inspections; the signal light phase is updated in combination with the driving needs of the emergency patrol vehicle and the traffic flow conditions of the emergency control streets; the operation of the traffic lights within the emergency control range is controlled based on the updated signal light phase, and the signboards of the variable lanes within the emergency control range are controlled to update the driving direction.

[0005] One or more embodiments of the present invention provide a smart city integrated emergency control Internet of Things large model system, the system including an emergency supervision user platform, an emergency supervision service platform, an emergency supervision management platform, an emergency supervision sensor network platform and an emergency supervision object platform; the emergency supervision user platform includes a third-party terminal; the emergency supervision service platform includes a communication terminal; the emergency supervision management platform includes a processor, a main data center and an emergency sub-platform, the main data center is configured with a memory and a data processing model library, the emergency supervision management platform is configured to execute the above-mentioned smart city integrated emergency control method; the emergency supervision object platform is configured with sensors and memory; the emergency supervision object platform is configured to operate based on multiple emergency patrol vehicles and communication devices.

[0006] One or more embodiments of the present invention provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the above-mentioned smart city integrated emergency management and control method.

[0007] Beneficial effects: The smart city integrated emergency control method, Internet of Things large model system and medium of the present invention improve the efficiency of handling emergencies by reasonably determining the emergency control scope that conforms to reality; by reasonably determining the driving route of emergency inspection vehicles, traffic control parameters that are conducive to the smooth driving and inspection of emergency inspection vehicles can be further set, thereby improving inspection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The present invention will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0009] Figure 1 2. It is a schematic diagram of the platform structure of the smart city integrated emergency management and control Internet of Things large model system according to some embodiments of the present invention;

[0010] Figure 2 is an exemplary flow chart of a smart city integrated emergency management and control method according to some embodiments of the present invention;

[0011] Figure 3 is an exemplary flow chart of generating a data group to be processed according to some embodiments of the present invention;

[0012] Figure 4 This is an exemplary schematic diagram of collecting and updating emergency management and control data according to some embodiments of the present invention. DETAILED DESCRIPTION

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of the present invention. Those skilled in the art can apply the present invention to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0014] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0015] Figure 1 1. It is a platform structure diagram of a large-scale model system of the Internet of Things for integrated emergency management and control in a smart city according to some embodiments of the present invention.

[0016] In some embodiments, as Figure 1 As shown, the smart city integrated emergency control IoT large 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.

[0017] The emergency supervision user platform refers to the management platform for comprehensive coordination of emergency supervision by superior departments.

[0018] In some embodiments, the emergency supervision user platform includes a third-party terminal.

[0019] A third-party terminal refers to an external terminal device or system software. For example, a third-party terminal can be any one or any combination of mobile devices, computers, or other devices with input and / or output functions provided by other organizations.

[0020] The emergency supervision service platform refers to an interactive service platform that receives and transmits data.

[0021] In some embodiments, the emergency supervision service platform interacts with the emergency supervision user platform upward and with the emergency supervision management platform downward.

[0022] In some embodiments, the emergency supervision service platform includes a communication terminal.

[0023] A communication terminal refers to a device or software that enables real-time information exchange. For example, a communication terminal can be a wireless phone, a video monitor, a multimedia computer, etc.

[0024] The emergency supervision management platform refers to a comprehensive platform for processing and managing emergency supervision data.

[0025] In some embodiments, the emergency supervision management platform includes a processor, a main data center 131 and multiple emergency sub-platforms. The multiple emergency sub-platforms each include a corresponding sub-data center. Figure 1 As shown, the emergency sub-platform 132-1 includes a sub-data center 133-1, the emergency sub-platform 132-2 includes a sub-data center 133-2, ..., and the emergency sub-platform 132-n includes a sub-data center 133-n.

[0026] The processor can be used to process acquired emergency regulatory data and other information. Based on this data, information, and / or processing results, the processor can execute program instructions to perform one or more functions described in this application. For example, the processor can include a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), or any combination thereof.

[0027] The central data center can be used to coordinate the management of the collected emergency supervision data.

[0028] In some embodiments, the overall data center is configured with a memory and a data processing model library.

[0029] Memory can be used to store emergency regulatory data and / or instructions. Memory can include one or more storage components, each of which can be a standalone device or part of another device. For example, memory can include random access memory (RAM), read-only memory (ROM), or any combination thereof.

[0030] The data processing model library can be used to store relevant computational models for the coordinated processing of data on the emergency supervision management platform. For example, computational models may include models for the coordinated classification of emergency supervision data and comprehensive analysis models for emergency supervision data. Classification models may include binary classification, decision trees, random forests, etc.

[0031] The emergency sub-platform refers to the sub-platform for supervising emergency supervision data.

[0032] The sub-data center can be used to store and process emergency supervision data allocated by the main data center.

[0033] In some embodiments, the sub-data center may include a sub-database and a sub-data processing model library, wherein the sub-database is used to store emergency supervision data, and the sub-data processing model library is used to store data processing models.

[0034] In some embodiments, the main data center 131 may interact with multiple sub-data centers.

[0035] The emergency supervision sensor network platform refers to a management platform that transmits emergency supervision related sensor data or information.

[0036] In some embodiments, the emergency supervision sensor network platform interacts upward with multiple sub-data centers in the emergency supervision management platform, and interacts downward with the emergency supervision object platform.

[0037] In some embodiments, the emergency monitoring sensor network platform includes a communication transmission network and a routing device, wherein the communication transmission network can realize the functions of sensing information sensing communication and controlling information sensing communication.

[0038] Routing devices are hardware devices that implement information sensing and communication.

[0039] The emergency supervision object platform refers to the platform for collecting emergency supervision data and implementing execution instructions.

[0040] In some embodiments, the emergency supervision object platform is configured with sensors and memory, wherein the memory can be used to store the monitored and collected information and data.

[0041] Sensors are devices used to receive and convert various monitoring information. For example, sensors can include temperature sensors, pressure sensors, ultrasonic sensors, etc.

[0042] In some embodiments, the emergency supervision object platform includes an emergency inspection vehicle and a communication device, and the emergency supervision object platform is configured to operate based on multiple emergency inspection vehicles and communication devices.

[0043] Emergency patrol vehicles are patrol vehicles used to prevent or respond to emergency situations. For example, emergency patrol vehicles can be driverless vehicles.

[0044] The communication device is a device used to realize data transmission between the emergency inspection vehicle and the emergency supervision sensor network platform. For example, the communication device can be a vehicle-mounted terminal.

[0045] In some embodiments, emergency inspection vehicles may be equipped with sensors, monitoring equipment, storage devices, and other devices.

[0046] For more detailed information about the IoT large-scale model system for integrated emergency control in smart cities and its implementation method for integrated emergency control in smart cities, please refer to Figures 2 to 4 Related description.

[0047] In some embodiments of the present invention, the smart city integrated emergency control Internet of Things large model system can form an information operation closed loop between various functional platforms, coordinate and operate regularly, and improve the efficiency of handling emergency events by efficiently and accurately determining the actual emergency control scope.

[0048] Figure 2 This is an exemplary flow chart of a smart city integrated emergency management method according to some embodiments of the present invention. Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 can be executed by an emergency supervision management platform.

[0049] Step 210 , a plurality of emergency management and control data are acquired through the communication transmission network of the emergency supervision sensor network platform configured in a plurality of geographical areas, and stored in the memory of the central data center.

[0050] A geographical region refers to a region obtained by dividing a national territory. In some embodiments, a geographical region can be divided in a variety of ways. For example, multiple geographical regions can be obtained based on administrative divisions.

[0051] In some embodiments, each geographical area is configured with a communication transmission network of at least one emergency supervision sensor network platform.

[0052] Emergency control data refers to data related to emergency control. For example, emergency control data includes combustible gas concentration, ambient temperature, ambient humidity, etc.

[0053] Emergency management and control refers to the response mechanism for dangerous problems such as major accidents and disasters (for example, gas leaks, fires and explosions, traffic accidents, etc.).

[0054] In some embodiments, the emergency supervision management platform can interact with the emergency supervision sensor network platform through a communication transmission network to obtain emergency control data collected by sensors configured in different geographical areas in the emergency supervision object platform, and store the emergency control data in the memory of the central data center.

[0055] Step 220 , retrieve the upload time, data type, and geographical area of ​​multiple emergency management and control data from the memory of the main data center to generate a data group to be processed.

[0056] The upload time of emergency control data refers to the time when the emergency control data is uploaded to the emergency supervision sensor network platform.

[0057] The data types of emergency management and control data include but are not limited to one or more of image data, sound data, text data, etc.

[0058] The geographical area to which the emergency control data belongs refers to the geographical area from which the emergency control data is collected.

[0059] A pending data group refers to a combination of multiple emergency control data. The emergency supervision management platform can generate pending data groups in a variety of ways.

[0060] In some embodiments, the emergency supervision and management platform can classify emergency management and control data based on preset rules to obtain multiple data groups to be processed. The preset rules can be system default rules or set in advance by the user. For example, the preset rules can include classifying emergency management and control data uploaded between 8 and 11 hours, belonging to region A, and having a text data type into one data group to be processed.

[0061] In other embodiments, the emergency supervision management platform can generate a data group to be processed through a data classification model. For more information about the data classification model, see Figure 3 And related instructions.

[0062] Step 230: According to the geographical scope of the geographical area involved in the data group to be processed, the emergency control range corresponding to the temporary control area is marked in the interactive terminal of the smart city GIS system, and the emergency control range corresponding to the temporary control area is displayed on the interface of the emergency control terminal.

[0063] A smart city Geographic Information System (GIS) is a technical system, supported by computer hardware and software, that collects, stores, manages, computes, analyzes, displays, and describes geographic distribution data on the entire or partial Earth's surface. The emergency supervision and management platform can exchange data with the smart city GIS system via an interactive terminal. In some embodiments, the interactive terminal includes a visual interface.

[0064] The emergency control scope refers to the area where emergency control is required.

[0065] In some embodiments, the emergency supervision and management platform can determine whether a major accident or disaster is imminent based on the pending data set. In response to the possibility of a major accident or disaster, the emergency supervision and management platform will determine the geographical area corresponding to the pending data set as a temporary control area and the area encompassed by the area as the emergency control area. In some embodiments, the emergency supervision and management platform can mark multiple emergency control areas with different colors and display the emergency control areas corresponding to the temporary control areas on the interface of the emergency control terminal.

[0066] Step 240: Generate a first driving route based on the emergency control streets within the emergency control range and the crowd size corresponding to the emergency control streets and send it to the emergency inspection vehicle to control the emergency inspection vehicle to execute the first driving route and conduct inspections.

[0067] Emergency control streets refer to streets within the emergency control area. The emergency supervision management platform can determine emergency control streets through the smart city GIS system.

[0068] The size of the crowd includes the flow of people and vehicles within the emergency control street. In some embodiments, the emergency supervision management platform can determine the size of the crowd based on image data in the to-be-processed data group corresponding to the emergency control range.

[0069] The first driving route is a route determined based on crowd size. In some embodiments, the emergency supervision management platform can select emergency control streets with crowd sizes larger than a preset size and connect these emergency control streets in a one-way manner, from near to far, based on the distance between the emergency control streets and the emergency inspection vehicle to obtain the first driving route.

[0070] Emergency inspection vehicles are vehicles used for inspections during emergency control. They can be unmanned. Inspections include, but are not limited to, one or more of the following: sounding an alarm to evacuate people, and collecting emergency control data through sensors.

[0071] Step 250: Update the signal light phase based on the driving requirements of the emergency inspection vehicle and the traffic flow conditions of the emergency control street.

[0072] Driving requirements refer to the requirements of emergency inspection vehicles during inspections. For example, driving requirements include the emergency control streets that the emergency inspection vehicle needs to pass through and the driving direction.

[0073] At intersections, traffic lights display different colors in a continuous time sequence. The colors of the lights change at different times, allowing for multiple signal phases. A signal phase can be specific to a single route. For example, if there are traffic lights at four intersections along a route, a signal phase might include the green light intervals between intersections 1 and 2, the green light intervals between intersections 2 and 3, and so on, when an emergency inspection vehicle is patrolling the route.

[0074] The green light interval time refers to the time interval between the end of the green light of the traffic light at the previous intersection and the start of the green light of the traffic light at the next intersection on the driving route.

[0075] The emergency supervision and management platform can update traffic light phases in a variety of ways. For example, based on the location information of emergency inspection vehicles, their driving needs, and the traffic volume of emergency-controlled streets, the platform can estimate the arrival time of emergency inspection vehicles at each intersection and update the traffic light phases based on the arrival time of emergency inspection vehicles, ensuring that the traffic lights at each intersection are green when the emergency inspection vehicles arrive.

[0076] In some embodiments, the emergency supervision management platform can generate an updated signal light phase based on the location information of the emergency inspection vehicle, the street information of the emergency control street, and the current signal light phase through a signal light phase model.

[0077] The signal light phase model is a model used to generate updated signal light phases. In some embodiments, the signal light phase model is a machine learning model, for example, a neural network (NN) model or other user-defined model.

[0078] The input of the traffic light phase model includes the location information and driving route of the emergency patrol vehicle, the street information of the emergency control street, and the candidate traffic light phases. The output of the traffic light phase model includes the number of times the emergency patrol vehicle encounters a red light on the driving route corresponding to the candidate traffic light phase.

[0079] The location information of the emergency inspection vehicle refers to the current location of the emergency inspection vehicle.

[0080] Street information refers to information related to emergency control streets. For example, street information includes the street layout, traffic light distribution, traffic flow, and current traffic light phase of the emergency control streets.

[0081] In some embodiments, the emergency supervision management platform can obtain the location information of the emergency inspection vehicle, street information of the emergency control street, and the current traffic light phase through a positioning system. Positioning systems include the Global Positioning System (GPS) and the Beidou Satellite Navigation System.

[0082] In some embodiments, the emergency supervision management platform may randomly generate multiple candidate signal light phases.

[0083] The emergency supervision and management platform can train a traffic light phase model based on multiple first training samples with first labels. The emergency supervision and management platform can input the first training samples into the initial traffic light phase model, construct a loss function based on the output of the initial traffic light phase model and the first label, iteratively update the parameters of the initial traffic light phase model based on the loss function, and terminate the iteration when an iteration termination condition is met, thereby obtaining a trained traffic light phase model. The iterative update method includes, but is not limited to, a gradient descent method, and the iteration termination condition can be when the loss function converges or the number of iterations reaches a threshold.

[0084] In some embodiments, the emergency supervision management platform can determine the historical location information and historical driving routes of emergency inspection vehicles, historical street information of emergency control streets, and historical traffic light phases during historical inspections as the first training sample, and the actual number of red lights encountered by emergency inspection vehicles during historical inspections as the first label corresponding to the first training sample.

[0085] In some embodiments, the emergency supervision management platform may determine the candidate signal light phase corresponding to the time when the emergency inspection vehicle encounters the least number of red lights as the updated signal light phase.

[0086] In some embodiments of the present invention, a signal light phase model is used to determine the number of times an emergency inspection vehicle encounters a red light under multiple candidate signal light phases, and the candidate signal light phase with the least number of red lights is determined as the updated signal light phase, which can reduce the waiting time for red lights and effectively improve inspection efficiency.

[0087] Step 260: Control the operation of traffic lights within the emergency control range based on the updated signal light phase, and control the signs of variable lanes within the emergency control range to update and indicate the driving direction.

[0088] In some embodiments, the emergency supervision management platform may set the current signal light phase to the updated signal light phase to control the operation of traffic lights within the emergency control range.

[0089] In some embodiments, the emergency supervision management platform can set the driving direction of the variable lanes entering the emergency control area to the opposite direction by controlling the signboard to reduce the traffic flow entering the emergency control area.

[0090] Some embodiments of the present invention improve the efficiency of handling emergencies by reasonably determining an emergency control range that conforms to reality; by reasonably determining the driving route of emergency inspection vehicles, traffic control parameters that are conducive to the smooth driving and inspection of emergency inspection vehicles can be further set to improve inspection efficiency.

[0091] Figure 3 FIG. 1 is an exemplary flow chart of generating a data set to be processed according to some embodiments of the present invention. Figure 3 As shown, the process 300 includes the following steps. In some embodiments, the process 300 can be executed by an emergency supervision management platform.

[0092] Step 310: retrieve a data classification model from a data processing model library based on the total data center.

[0093] A data classification model is a model used to classify emergency management data. For example, the data classification model is a binary classification model.

[0094] The input of the data classification model includes emergency control data, and the output of the data classification model includes the data group to be processed.

[0095] In some embodiments, the multiple emergency management and control data input into the data classification model are data that have undergone pre-processing and screening, and the pre-processing and screening are determined based on historical processing information corresponding to the multiple emergency management and control data.

[0096] Historical processing information refers to information related to the classification of emergency management and control data by the emergency supervision and management platform. Historical processing information can be obtained based on historical data.

[0097] In some embodiments, the emergency supervision management platform determines the frequency of dividing the emergency management data into different data groups to be processed based on historical processing information, and marks multiple emergency management data based on the frequency.

[0098] In some embodiments, pre-processing and screening can be performed by classifying emergency control data based on its tags, thereby determining the data group to be processed to which each tagged emergency control data belongs. For example, the emergency control data can be classified into the data group to be processed whose frequency value is the largest among its tagged frequencies and is greater than a preset frequency threshold. The preset frequency threshold can be set based on historical experience.

[0099] The data that has been pre-processed and filtered is the emergency control data that cannot be determined to belong to the data group to be processed based on the aforementioned marking process. For example, the historical processing information does not contain any historical grouping records or the marked frequency value does not exceed the preset frequency threshold.

[0100] Some embodiments of the present invention can improve data processing efficiency and reduce the data processing burden of the overall data center by pre-processing and screening emergency management and control data.

[0101] The emergency supervision management platform can train a data classification model based on the plurality of second training samples with the second label. The training process of the data classification model is the same as that of the traffic light phase model. For more details, see the relevant description in step 250.

[0102] The second training sample includes sample emergency control data, and the second label is a sample to-be-processed data group corresponding to the sample emergency control data. The second training sample and the second label can be determined based on historical processing information.

[0103] Step 320: Classify the multiple emergency management and control data based on the data classification model to generate a data group to be processed.

[0104] In some embodiments, the emergency supervision management platform may classify and process multiple emergency management and control data in the central data center based on a data classification model to generate a data group to be processed.

[0105] In other embodiments, a sub-data center is configured in the emergency sub-platform, and the emergency supervision management platform can classify and process multiple emergency management and control data in the sub-data center based on the sub-data classification model to generate a data group to be processed.

[0106] For more information about emergency control data and pending data groups, see Figure 2 And related instructions.

[0107] Step 330: Generate routing information based on the data group to be processed.

[0108] Routing information refers to information related to data transmission. For example, routing information includes the data group to be sent and processed and the corresponding sending and receiving ends.

[0109] In some embodiments, the emergency supervision and management platform can determine routing information based on actual needs. For example, the emergency supervision and management platform sets the central data platform as the sending end and the sub-data center of the emergency sub-platform corresponding to the geographic region of the data group to be processed as the receiving end. The geographic region corresponding to the data group to be processed refers to the geographic region to which the emergency management and control data in the data group to be processed belongs.

[0110] For more information about geographical regions, see Figure 2 And related instructions.

[0111] Step 340 : Based on the routing information, the routing device of the emergency monitoring sensor network platform is controlled to send the data group to be processed to the sub-data center of the emergency sub-platform in the corresponding geographical area.

[0112] In some embodiments, the emergency supervision management platform may control the routing device corresponding to the sending end based on the routing information to send the data group to be processed to the receiving end.

[0113] In some embodiments of the present invention, emergency management and control data are classified through a data classification model to obtain a data group to be processed, and the data group to be processed is sent based on actual needs, which can improve the transmission and processing efficiency of emergency management and control data.

[0114] In some embodiments, the emergency supervision management platform can also generate multiple association values ​​of emergency control data and emergency events based on the numerical range of multiple emergency control data within a preset time period, the geographical area to which they belong, the type of emergency event and the location of the emergency event; based on the association value, determine the data groups to be processed corresponding to different time periods; divide the emergency control range corresponding to the temporary control area according to the data groups to be processed and the geographical scope of the geographical area involved in the data groups to be processed; and, according to the temporary control area, control the interactive terminal of the smart city GIS system to display the electronic map corresponding to the temporary control area.

[0115] The numerical range of emergency control data refers to the fluctuation range of emergency control data within a preset time period. Different emergency control data corresponds to different numerical ranges. For example, if the minimum ambient temperature during the preset time period is 10°C and the maximum ambient temperature is 20°C, the corresponding numerical range of the ambient temperature is 10-20°C. The preset time period can be a system default or manually set by the user.

[0116] Emergency events are events that require emergency management and control. For example, emergency events can include major accidents and disasters (such as gas leaks, fires and explosions, and traffic accidents). Emergency events include major accidents and disasters that are currently occurring or are likely to occur. The location of an emergency event can be determined based on emergency management and control data.

[0117] The correlation value refers to the degree of correlation between emergency control data and emergency events. The larger the correlation value, the more closely the emergency control data relates to the emergency event. For example, the correlation between combustible gas concentration and gas leaks is greater than the correlation between ambient humidity and gas leaks. In some embodiments, the correlation value can be represented by a number between 0 and 1, with a larger value indicating a greater correlation value.

[0118] The emergency supervision management platform can determine the associated value in a variety of ways.

[0119] In some embodiments, the emergency supervision management platform can obtain historical emergency events of the same type as the current emergency event and located in the same geographical area based on historical data, and at the same time obtain the historical numerical range of emergency management data corresponding to the historical emergency events.

[0120] The emergency supervision and management platform determines the correlation value based on the degree of overlap between the numerical range of the emergency control data corresponding to the current emergency event and the historical numerical range. The greater the overlap, the greater the correlation value. When the historical numerical range contains the numerical range of the emergency control data corresponding to the current emergency event, the correlation value reaches its maximum value of 1.

[0121] In some embodiments, the emergency supervision management platform may determine the product of the above-mentioned correlation value and the type coefficient as the final correlation value. The type coefficient refers to a coefficient related to the type of the current emergency event, and the type coefficient may be a system default value.

[0122] In some embodiments, the emergency supervision management platform can generate correlation values ​​between multiple emergency management data and emergency events through an emergency correlation model based on the numerical range of multiple emergency management data within a preset time period, the geographical area to which they belong, the type of emergency event, and the location of the emergency event.

[0123] The emergency relevance model is a model used to determine the relevance value. In some embodiments, the emergency relevance model is a machine learning model, for example, a neural network (NN) model or other user-defined model.

[0124] The input of the emergency correlation model includes the numerical range of multiple emergency control data within a preset time period, the geographical area to which they belong, the type of emergency event, and the location of the emergency event. The output of the emergency correlation model includes the correlation values ​​between multiple emergency control data and emergency events.

[0125] In some embodiments, multiple emergency events may occur at the same time. In this case, the input of the emergency association model may include the types and locations of the multiple emergency events.

[0126] The emergency supervision management platform can train an emergency correlation model based on multiple third training samples with third labels. The training process of the emergency correlation model is the same as that of the traffic light phase model. For more details, please refer to the relevant description in step 250.

[0127] The third training sample includes the sample numerical range of emergency control data from historical data during emergency events, the geographic region to which the sample belongs, the type of the sample emergency event, and the location of the sample emergency event. The third label is the actual correlation value corresponding to the third training sample. Based on the third training sample, the emergency supervision and management platform can determine the third label corresponding to the third training sample using the aforementioned method for determining correlation values.

[0128] In some embodiments, the training data of the emergency association model includes multiple labeled training samples, and the labels are determined based on the data group to be processed corresponding to the multiple sample emergency control data included in the training samples. The emergency supervision management platform can obtain the event processing results corresponding to the training samples (i.e., the third training samples); estimate the association estimation value (i.e., the third label) corresponding to the training samples based on the event processing results; in response to the association estimation value being greater than the preset sample value, set the value of the label corresponding to the training sample to the preset label value, and the preset label value is greater than the preset threshold; based on the values ​​of multiple labels corresponding to multiple training samples, divide multiple training samples into multiple training sets; and train the emergency association model based on multiple training sets.

[0129] The event processing result refers to the result of processing the sample emergency event corresponding to the third training sample.

[0130] The estimated association value refers to an estimate of the association value. In some embodiments, the emergency supervision and management platform may obtain a historical numerical range of historical emergency management and control data for a period of time after the historical moment corresponding to the third training sample, determine the association value between the historical numerical range and the sample emergency event corresponding to the third training sample using the aforementioned method for determining the association value based on the degree of overlap, and determine the association value as the estimated association value.

[0131] In some embodiments, based on the historical event processing results in a large amount of historical data, it is possible to determine which emergency management and control data are valid data for the processing of emergency events through prior experience, and store the results in the emergency supervision and management platform. For example, when the emergency event is found to be a fire, the ambient temperature, traffic volume, and smoke concentration change significantly, and these emergency management and control data are determined to be valid data for the processing of the fire. If the emergency management and control data is valid data for the processing of the sample emergency event, the emergency supervision and management platform sets the value of the third label to the preset label value in response to the associated estimated value being greater than the preset sample value. The preset label value is greater than a preset threshold (for example, 0.75). If the emergency management and control data is not valid data for the processing of the sample emergency event, the value of the third label remains unchanged.

[0132] Historical emergency control data is effective data for the processing of sample emergency events, indicating that the actual correlation between historical emergency control data and sample emergency events is relatively high. When the estimated correlation value is greater than the preset sample value, the value of the third label is increased. The trained emergency correlation model can accurately predict the correlation value of subsequent emergency control data with higher correlation values.

[0133] In some embodiments, the emergency supervision management platform may divide the third training samples into two training sets. The first training set includes third training samples whose third labels have a preset label value, and the remaining third training samples belong to the second training set. The learning rate corresponding to the second training set is smaller than the learning rate corresponding to the first training set.

[0134] The emergency supervision and management platform can train an emergency correlation model based on the first training set and the second training set. The training process of the emergency correlation model is the same as that of the traffic light phase model. For more details, please refer to the relevant description in step 250.

[0135] In some embodiments of the present invention, taking into account that the association value may change over time, the third label is adjusted based on the association value in a subsequent event, and the third training samples corresponding to the adjusted and unadjusted third labels are divided into different training sets, and model training is performed based on different learning rates, so that the model parameters of the emergency association model are more accurate.

[0136] In some embodiments of the present invention, a trained emergency association model can be used to quickly determine the association value between a large amount of emergency management and control data and at least one emergency event, thereby improving data processing efficiency.

[0137] In some embodiments, the emergency supervision management platform can divide the emergency control data into multiple data groups to be processed based on the type of emergency event and the associated value interval (for example, 0.9-1, 0.8-0.9... correspond to an associated value interval respectively).

[0138] In some embodiments, the emergency supervision management platform may determine the emergency control scope based on the data group to be processed by the method described in step 230 .

[0139] In some embodiments, the emergency supervision and management platform can also determine the control time corresponding to each emergency control scope. For example, the control time is positively correlated with the amount of emergency control data in the pending data group. Furthermore, the control time is also related to the correlation value interval corresponding to the pending data group. The larger the correlation value interval, the longer the control time. The control time is also related to the severity of the emergency event. The more serious the emergency event, the longer the control time.

[0140] For more information on how to display the electronic map, see step 230 and related instructions.

[0141] In some embodiments of the present invention, by determining the correlation values ​​between different emergency management and control data and emergency events, more important emergency management and control data can be processed preferentially to ensure timeliness of data processing.

[0142] Figure 4 This is an exemplary schematic diagram of collecting and updating emergency management and control data according to some embodiments of the present invention.

[0143] In some embodiments, as Figure 4 As shown, the emergency supervision management platform adjusts the first driving route 421 and generates the second driving route 431 based on the correlation value 411 of multiple emergency control data and emergency events and the emergency control street 412; controls the emergency inspection vehicle to execute the second driving route 431 and conduct inspections to collect updated emergency control data.

[0144] In some embodiments, the multiple association values ​​411 of emergency management data and emergency events may include association value 1 of emergency management data and emergency events, association value 2 of emergency management data and emergency events, ..., association value n of emergency management data and emergency events.

[0145] In some embodiments, more descriptions of the association values ​​of emergency control streets, first driving routes, emergency inspection vehicles, and multiple emergency control data and emergency events can be found in Figure 2 、 Figure 3 and its related contents.

[0146] The second driving route refers to a driving route obtained by adjusting the first driving route based on the correlation value between emergency control data and emergency events and the emergency control streets.

[0147] In some embodiments, the second driving route may be determined by the following steps:

[0148] Step 1: Determine the emergency control scope corresponding to the geographical area to which the emergency control street belongs. For more information on the emergency control scope and its determination, please refer to Figure 2 and its related contents;

[0149] Step 2: Obtain the correlation values ​​between multiple emergency control data and emergency events. For more information about correlation values, see Figure 3 and its related contents;

[0150] Step 3: The emergency supervision management platform can take the emergency control streets corresponding to the emergency control data corresponding to the correlation values ​​as the emergency control streets corresponding to the correlation values, and sort the emergency control streets corresponding to the correlation values ​​from large to small according to the correlation values; the emergency supervision management platform can determine the correlation values ​​corresponding to the emergency control streets in different preset time periods; and then determine the increase in the correlation values ​​in the adjacent time periods of multiple preset time periods. For example, the correlation value of the previous time period is 0.2, and the correlation value of the current time period is 0.4, then the increase in the correlation value is 100%. The inspection frequency of the emergency control streets is positively correlated with the increase in the corresponding correlation value in the adjacent time periods of multiple preset time periods. For example, for every 30% increase in the increase in the correlation value in the adjacent time periods, the inspection frequency increases once;

[0151] Step 4: The emergency inspection vehicle generates an adjusted driving route, i.e., the second driving route, according to the ranking results of the emergency control streets;

[0152] Among them, it can be understood that when the emergency inspection vehicle goes to the emergency control street with a larger correlation value, it can complete the inspection of other emergency control streets with relatively smaller correlation values ​​along the way.

[0153] In some embodiments, updated emergency control data can be collected in a variety of ways. For example, emergency inspection vehicles and other processors can collect updated emergency control data during an inspection process based on the second driving route.

[0154] In some embodiments, the emergency supervision management platform adjusts the second driving route based on the updated emergency control data, combined with the associated value and the emergency control street, to generate a third driving route.

[0155] The third driving route is obtained by adjusting the second driving route based on the updated emergency control data.

[0156] In some embodiments, the third driving route may be determined by the following steps:

[0157] Step 1: Generate new associated values ​​based on the updated emergency control data. For more information on generating associated values ​​based on emergency control data, see Figure 3 and its related contents;

[0158] Step 2: Sort the emergency control streets corresponding to the new correlation values ​​from large to small;

[0159] Step 3: The emergency inspection vehicle generates an adjusted driving route, i.e., the third driving route, according to the new ranking results of the emergency control streets.

[0160] In some embodiments of the present invention, the association values ​​of different emergency control data are re-determined based on the updated emergency control data to update the priority of emergency control streets that should be inspected in real time, which can further improve the real-time inspection performance of emergency inspection vehicles.

[0161] In some embodiments of the present invention, the priority of emergency control streets to be inspected and the inspection frequency are updated in real time according to the size of the associated value, which can improve the inspection effect of emergency inspection vehicles and avoid the occurrence of untimely inspections.

[0162] Some embodiments of the present invention further provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes any one of the methods described in the above embodiments.

[0163] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit the present invention. Although not explicitly described herein, those skilled in the art may make various modifications, improvements, and revisions to the present invention. Such modifications, improvements, and revisions are suggested in the present invention and remain within the spirit and scope of the exemplary embodiments of the present invention.

[0164] Finally, it should be understood that the embodiments described herein are intended only to illustrate the principles of the present invention. Other variations may also fall within the scope of the present invention. Therefore, by way of example and not limitation, alternative configurations of the embodiments of the present invention may be considered consistent with the teachings of the present invention. Accordingly, the embodiments of the present invention are not limited to the embodiments explicitly described and illustrated herein.

Claims

1. A smart city integrated emergency management and control method, characterized in that: The method is executed based on the emergency supervision management platform and includes: Obtain multiple emergency control data; Retrieving the upload time, data type, and geographical area of ​​the multiple emergency management and control data, retrieving a data classification model from a data processing model library based on the central data center, and classifying and processing the multiple emergency management and control data based on the data classification model to generate a data group to be processed, wherein the data classification model is a binary classification model; According to the numerical range of the multiple emergency control data within a preset time period, the geographical area to which they belong, the type of emergency event and the location of the emergency event, an emergency correlation model is used to generate a correlation value, wherein the correlation value represents the degree of correlation between the emergency control data and the emergency event, and the emergency correlation model is a machine learning model; based on the correlation value, the data groups to be processed corresponding to different time periods are determined; according to the data groups to be processed and the geographical range of the geographical area to which the data groups to be processed belong, the emergency control range corresponding to the temporary control area is divided; In the interactive terminal of the smart city GIS system, the emergency control range is marked; generating a first driving route according to the emergency control streets within the emergency control range and the crowd size corresponding to the emergency control streets; According to the correlation value and the emergency control street, the first driving route is adjusted to generate a second driving route, including: determining the emergency control street corresponding to the correlation value; sorting the emergency control streets corresponding to the correlation value from large to small according to the correlation value; determining the correlation value corresponding to the emergency control street in different preset time periods; and then determining the increase rate of the correlation value in adjacent time periods of multiple preset time periods; setting the inspection frequency of the emergency control street to be positively correlated with the increase rate of the corresponding correlation value in adjacent time periods of multiple preset time periods; and adjusting the first driving route according to the sorting result of the emergency control streets corresponding to the correlation value; Controlling the emergency inspection vehicle to execute the second driving route and conduct inspections to collect updated emergency management and control data; Generate a new correlation value based on the updated emergency control data, adjust the second driving route based on the new correlation value and the corresponding emergency control street, generate a third driving route and send it to the emergency inspection vehicle; Update the signal light phase according to the driving requirements of the emergency inspection vehicle and the traffic flow of the emergency control street; The operation of the traffic lights within the emergency control range is controlled based on the updated signal light phase, and the signboards of the variable lanes within the emergency control range are controlled to update and indicate the driving direction.

2. The method according to claim 1, characterized in that The method further comprises: generating routing information based on the data group to be processed, Based on the routing information, the routing device of the emergency supervision sensor network platform is controlled to send the data group to be processed to the sub-data center of the emergency sub-platform in the corresponding geographical area.

3. The method according to claim 2, characterized in that The method further comprises: According to the temporary control area, the interactive terminal of the smart city GIS system is controlled to display an electronic map corresponding to the temporary control area.

4. A large-scale model system of the Internet of Things for integrated emergency management and control of smart cities, characterized by: The system includes an emergency supervision user platform, an emergency supervision service platform, an emergency supervision management platform, an emergency supervision sensor network platform and an emergency supervision object platform; Among them, the emergency supervision user platform includes a third-party terminal, the emergency supervision service platform includes a communication terminal, the emergency supervision management platform includes a processor, a main data center and an emergency sub-platform, and the main data center is configured with a memory and a data processing model library; the emergency supervision sensor network platform includes a communication transmission network and a routing device; the emergency supervision object platform is configured with sensors and memory, and the emergency supervision object platform is configured to operate based on emergency inspection vehicles and communication devices; The emergency supervision management platform is configured to execute the smart city integrated emergency management and control method as described in claim 1.

5. The system according to claim 4, wherein: The emergency supervision management platform is further configured to: generating routing information based on the data group to be processed; Based on the routing information, the routing device of the emergency supervision sensor network platform is controlled to send the data group to be processed to the sub-data center of the emergency sub-platform in the corresponding geographical area.

6. The system according to claim 5, wherein: The emergency supervision management platform is further configured to: According to the temporary control area, the interactive terminal of the smart city GIS system is controlled to display the electronic map corresponding to the temporary control area.

7. A computer-readable storage medium, characterized in that The storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the method according to any one of claims 1 to 3.

Images