Smart city crowd dispersal system, method and medium based on internet of things large model

Abstract

The application provides a smart city crowd dispersal system, method and medium based on an Internet of Things large model, the system comprising an emergency supervision management platform, the emergency supervision management platform being configured to: based on an emergency supervision perception control platform, acquire regional monitoring data through a monitoring device deployed in a monitoring area; determine a regional congestion risk based on the regional monitoring data; in response to the regional congestion risk meeting a dispersal condition: determine emergency dispersal parameters based on the regional congestion risk, the emergency dispersal parameters comprising passage control parameters and passage guidance parameters; based on the emergency dispersal parameters, transmit an emergency control signal to an emergency dispersal device deployed in the monitoring area through an emergency supervision sensing network platform, to control the opening interval of a passage gate based on the passage control parameters, and control the display content of an electronic sign based on the passage guidance parameters, the display content comprising at least one of a display color, a dispersal direction and a dispersal route.

Description

TECHNICAL FIELD

[0001] The present specification relates to the field of urban crowd evacuation, and in particular, to a smart city crowd evacuation system, method and medium based on an Internet of Things large model. BACKGROUND

[0002] In order to accurately determine the crowd characteristics corresponding to different public places and different times, and then determine the actual congestion risk, and further give a proper evacuation plan, it is necessary to provide a smart city crowd evacuation system based on an Internet of Things large model, which can determine the actual regional congestion risk through regional monitoring data obtained by a monitoring device deployed in a monitoring area, and send an emergency control signal to an emergency evacuation device deployed in the monitoring area to control the emergency evacuation device to perform personnel evacuation. SUMMARY

[0003] One or more embodiments of the present specification provide a smart city crowd evacuation system based on an Internet of Things large model, the system comprising an emergency supervision and management platform, the emergency supervision and management platform being configured to execute a smart city crowd evacuation method based on an Internet of Things large model.

[0004] One or more embodiments of the present specification provide a smart city crowd evacuation method based on an Internet of Things large model, the method being executed by an emergency supervision and management platform of a smart city crowd evacuation system based on an Internet of Things large model, the method comprising: obtaining regional monitoring data; determining a regional congestion risk based on the regional monitoring data; in response to the regional congestion risk meeting an evacuation condition: determining an emergency evacuation parameter based on the regional congestion risk, the emergency evacuation parameter comprising a passage control parameter and a passage guidance parameter; based on the emergency evacuation parameter, sending an emergency control signal to an emergency evacuation device deployed in the monitoring area, to control the opening interval of a passage gate based on the passage control parameter, and to control the display content of an electronic sign based on the passage guidance parameter, the display content comprising at least one of a display color, an evacuation direction and an evacuation route.

[0005] One or more embodiments of the present specification provide a smart city crowd evacuation device based on an Internet of Things large model, the device comprising at least one processor and at least one memory; the at least one memory is used to store computer instructions; the at least one processor is used to execute at least part of the computer instructions to realize the above-mentioned smart city crowd evacuation method based on an Internet of Things large model.

[0006] One or more embodiments of the present specification provide a computer readable storage medium, the storage medium stores computer instructions, when a computer reads the computer instructions in the storage medium, the computer executes the above-mentioned smart city crowd evacuation method based on an Internet of Things large model.

[0007] In some embodiments of the present specification, the actual area congestion risk can be accurately determined by the area monitoring data obtained by the monitoring device deployed in the monitoring area, and real-time and accurate risk perception and early warning can be realized. At the same time, based on the actual area congestion risk, the emergency evacuation parameters are determined, and the corresponding emergency control signals are transmitted to the emergency evacuation devices deployed in the monitoring area, so as to control the emergency evacuation devices to perform personnel evacuation, which can reduce the accident rate, improve the evacuation efficiency, and significantly improve the public safety benefit. BRIEF DESCRIPTION OF DRAWINGS

[0008] The present specification will be further described in the manner of exemplary embodiments, which will be described in detail through the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same numbers represent the same structures, wherein:

[0009] Figure 1 is an exemplary structural diagram of the smart city crowd evacuation system based on the Internet of Things large model according to some embodiments of the present specification;

[0010] Figure 2 is an exemplary flowchart of the smart city crowd evacuation method based on the Internet of Things large model according to some embodiments of the present specification;

[0011] Figure 3 is a scene schematic diagram for determining the area congestion risk according to some embodiments of the present specification;

[0012] Figure 4 is an exemplary schematic diagram for determining the emergency evacuation parameters according to some embodiments of the present specification. DETAILED DESCRIPTION

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some examples or embodiments of the present specification, and for those skilled in the art, the present specification can be applied to other similar scenarios without creative labor. Unless it is obvious from the language environment or otherwise stated, the same reference numbers in the drawings represent the same structure or operation.

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

[0015] As indicated in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of expressly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0016] Flowcharts are used in this specification to illustrate the operations performed by the system according to embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0017] Figure 1 This is an exemplary structural diagram of a smart city crowd management system based on an Internet of Things (IoT) big data model, as shown in some embodiments of this specification.

[0018] In some embodiments, such as Figure 1 As shown, the smart city crowd management system 100 based on the Internet of Things big data model (hereinafter referred to as system 100) may include 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 perception and control platform 150.

[0019] The Emergency Supervision User Platform 110 refers to the platform used by higher-level departments to comprehensively coordinate emergency supervision.

[0020] In some embodiments, the emergency monitoring user platform includes a third-party terminal.

[0021] A third-party terminal refers to an external terminal device or system software. For example, a third-party terminal can be one or any combination of mobile devices, computers, or other devices with input and / or output functions provided by other organizations.

[0022] The Emergency Monitoring Service Platform 120 refers to an interactive service platform for receiving and transmitting data.

[0023] In some embodiments, the emergency monitoring service platform 120 interacts upward with the emergency monitoring user platform 110 and downward with the emergency monitoring management platform 130.

[0024] In some embodiments, the emergency monitoring service platform 120 may be configured with a single server or a group of servers, a gateway, and a router, wherein the server group may be centralized or distributed.

[0025] The emergency supervision management platform 130 refers to a comprehensive platform for processing and managing emergency supervision data. The emergency supervision management platform includes a processor, a data center, and multiple emergency sub-platforms.

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

[0027] The data center can be used to manage the collected emergency supervision data.

[0028] In some embodiments, the data center is configured with a memory.

[0029] The memory can be used to store emergency supervision data and / or instructions. The memory can include one or more storage components, each of which can be a separate device or part of other devices. For example, the memory can include random access memory (RAM), read-only memory (ROM), and the like or any combination thereof.

[0030] The emergency sub-platform refers to a sub-platform for supervising emergency supervision data.

[0031] In some embodiments, the emergency supervision management platform 130 is configured as an emergency supervision perception control platform, acquires regional monitoring data through a monitoring device deployed in a monitoring area, determines a regional congestion risk based on the regional monitoring data, and in response to the regional congestion risk meeting a relief condition, determines an emergency relief parameter based on the regional congestion risk, the emergency relief parameter including a passage control parameter and a passage guidance parameter, and based on the emergency relief parameter, sends an emergency control signal to an emergency relief device deployed in the monitoring area through an emergency supervision sensor network platform, to control the opening interval of a channel gate based on the passage control parameter, and control the display content of an electronic sign based on the passage guidance parameter, the display content including at least one of display color, relief direction and relief route.

[0032] The emergency supervision sensor network platform 140 refers to a management platform for transmitting emergency supervision related sensor data or information.

[0033] In some embodiments, the emergency supervision sensor network platform 140 interacts with the data center in the emergency supervision management platform 130 upwardly and interacts with the emergency supervision perception control platform downwardly.

[0034] The emergency supervision sensing network platform 140 includes a plurality of sensing sub-platforms. In some embodiments, each sensing sub-platform can collect sensing data of an area and upload to a corresponding emergency sub-platform.

[0035] In some embodiments, the emergency supervision sensing network platform 140 includes a communication transmission network and a routing device. The communication transmission network can realize the functions of sensing communication of perception information and sensing communication of control information. The routing device is a hardware device for realizing sensing communication of information.

[0036] The emergency supervision perception control platform 150 refers to a platform for collecting emergency supervision data and implementing execution instructions.

[0037] In some embodiments, the emergency supervision perception control platform is configured with a sensor, a memory, and an emergency guidance device.

[0038] The sensor is a device for receiving and converting various monitoring information. In some embodiments, the sensor includes a camera and an infrared counter. The camera can be used to obtain monitoring image data, and the infrared counter can be installed at the entrance and exit of a channel to obtain monitoring count data. For more information about monitoring image data and monitoring count data, please refer to Figure 2 and related descriptions thereof.

[0039] The emergency guidance device is a device that provides support for emergency situations. In some embodiments, the emergency guidance device includes a gate, an electronic sign, an elevator or escalator, a broadcasting device, etc.

[0040] For more detailed description of the smart city crowd dispersal system based on the Internet of Things large model, please refer to the related description of Figures 2 to 4 .

[0041] In some embodiments of the present specification, the smart city crowd dispersal system based on the Internet of Things large model can form an information running closed loop between various functional platforms, coordinate and run regularly, and accurately determine the actual emergency control range through efficient and accurate determination, so as to improve the processing efficiency of emergency events.

[0042] Figure 2 is an exemplary flowchart of the smart city crowd dispersal method based on the Internet of Things large model according to some embodiments of the present specification. As Figure 2 shown, the flow 200 includes the following steps. In some embodiments, the flow 200 can be performed by the emergency supervision management platform.

[0043] Step 210, based on the emergency supervision perception control platform, obtaining area monitoring data through the monitoring device deployed in the monitoring area.

[0044] In some embodiments, the application scenario of the present application can be a place with multiple entrances and exits, such as a subway station or a large sports stadium.

[0045] In some embodiments, a place includes multiple monitoring areas, and the monitoring areas are connected to each other, such as being connected by a passageway, an entrance and exit, or being directly connected.

[0046] In some embodiments, the multiple monitoring areas can refer to multiple areas naturally formed by the corresponding building of the place. For example, waiting hall A and waiting hall B of a station.

[0047] In some embodiments, the multiple monitoring areas can also refer to multiple areas self-divided by the areas in the place. For example, the northeast corner, the southeast corner, the southwest corner, and the northwest corner of waiting hall A.

[0048] In some embodiments, a place can also correspond to one monitoring area, and different functional areas or different position areas in the monitoring area can correspond to different sub-areas in the monitoring area. The division method of the sub-area can be preset in advance, such as division based on unit space.

[0049] For ease of illustration, the following takes a place including multiple monitoring areas as an example.

[0050] The monitoring device refers to a device arranged in the monitoring area and performing a monitoring function. For example, a video analysis camera, an infrared / thermal imaging camera, an acoustic sensor, an intelligent gate, a face recognition device, an infrared counter, and the like.

[0051] The area monitoring data refers to the monitoring data of the entire monitoring area collected by the monitoring device.

[0052] In some embodiments, the area monitoring data can include monitoring image data, monitoring count data, and the like.

[0053] In some embodiments, the area monitoring data of the multiple monitoring areas constitutes the monitoring data of the entire place.

[0054] In some embodiments, the area monitoring data can be obtained by the monitoring device arranged in the monitoring area.

[0055] Step 220, determining a regional congestion risk based on the area monitoring data.

[0056] The regional congestion risk refers to a risk that, due to high personnel density, poor flow, or improper management, a safety accident, public order disorder, or a health hazard event may occur in the monitoring area. For example, a stampede risk and a failure risk of evacuation.

[0057] In some embodiments, the emergency supervision management platform can obtain a crowd flow feature based on the regional monitoring data, calculate a personnel density feature of the monitoring region based on the crowd flow feature and the area size of the region, and further determine the regional congestion risk.

[0058] The crowd flow feature refers to a feature related to crowd flow in the monitoring region. For example, the number of personnel, the crowd flow, the personnel movement mode, etc. The crowd flow features of multiple regions in the monitoring region can be calculated respectively.

[0059] In some embodiments, the emergency supervision management platform can obtain the crowd flow and the number of personnel using the monitoring count data, and then determine the crowd flow movement direction based on the monitoring image data using an image recognition algorithm or an image recognition model. The image recognition algorithm can include a Haar feature cascade algorithm, a support vector machine (SVM) algorithm, etc. The image recognition model can include YOLO, a Gaussian mixture model (GMM), etc.

[0060] The personnel density feature refers to a quantitative indicator and dynamic attribute of crowd distribution in the monitoring region, which is used to describe, evaluate and predict the regional congestion risk. For example, the personnel density in the region, the personnel density distribution, etc.

[0061] In some embodiments, the emergency supervision management platform can use a clustering algorithm to process the crowd flow feature and the area size to determine the personnel density distribution. For example, the personnel in the monitoring region can be clustered based on the personnel position coordinates through a clustering algorithm to obtain multiple clustering clusters, and each cluster contains the crowd coordinate range of multiple regions in the monitoring region (such as cluster 1 covering the A exit to the B gate region). The clustering algorithm can include a DBSCAN algorithm, etc.

[0062] In some embodiments, the personnel density distribution can include a personnel distribution cluster density and a personnel distribution cluster radius.

[0063] The personnel distribution cluster density refers to the ratio of the total number of personnel in the cluster to the cluster coverage area.

[0064] The personnel distribution cluster radius refers to the distance between the farthest two points in the cluster coverage area, which can reflect the degree of looseness of crowd distribution.

[0065] In some embodiments, the greater the personnel density feature of the monitoring region, the greater the regional congestion risk.

[0066] In some embodiments, in response to the number of clusters with a cluster density greater than a density threshold (for example, the number is greater than a number threshold), the emergency supervision management platform can generate a broadcast audio to prompt personnel not to gather in groups. The density threshold can be preset by a human being according to prior experience.

[0067] In some embodiments, the emergency supervision management platform can display the cluster density in the form of a heat map on the map interface, for example, red representing high risk and green representing low risk, to remind staff not to gather in crowds through broadcasting / interference.

[0068] In some embodiments, the emergency supervision management platform can also determine the region congestion risk based on the relationship that the greater the personnel density in the plurality of regions in the monitoring region, the more the number of clusters with a cluster density greater than the density threshold, and the greater the region congestion risk.

[0069] Step 230, in response to the region congestion risk meeting the dispersing condition: determining an emergency dispersing parameter based on the region congestion risk.

[0070] In some embodiments, the emergency dispersing parameter can include a passage control parameter and a passage guidance parameter.

[0071] The dispersing condition includes that the region congestion risk is higher than a preset risk threshold.

[0072] In some embodiments, the preset risk threshold can be preset by a human according to prior experience.

[0073] The passage control parameter refers to the control parameter of the passage-related device. For example, the opening interval of the passage gate of the entrance and exit.

[0074] The passage gate refers to the gate of the passage in the monitoring region. For example, the entrance and exit gate of the C exit of the subway station.

[0075] The opening interval refers to the duration that the passage gate in the monitoring region remains open.

[0076] The passage guidance parameter refers to the control parameter of the indication device (such as an electronic display board). For example, the display content of the electronic indication board.

[0077] The electronic indication board refers to a display board set in the monitoring region to provide indication information for the crowd. For example, an LED light board.

[0078] The display content can include at least one of a display color, a dispersing direction, and a dispersing route.

[0079] The display color refers to the color displayed by the electronic indication board. For example, red representing high emergency level, green representing low emergency level, and the like.

[0080] The dispersing direction refers to the direction to which the personnel are guided to go, for example, the direction of the destination of the dispersing route.

[0081] The dispersing route refers to the route guiding the personnel to disperse to the destination.

[0082] In some embodiments, the emergency supervision management platform can generate the evacuation route using a path planning algorithm. The path planning algorithm can include Dijkstra, algorithm, etc.

[0083] In some embodiments, the evacuation route can include multiple routes respectively leading to different low-risk areas (if there are multiple low-risk areas). The starting point of the evacuation route can be the area center of the current monitoring area. For the description of the low-risk area, please refer to the following.

[0084] For example, in the current shift subway, people are concentrated in the head area and the tail area of the subway car, while there are few people in the central area of the car. When the people in the head area and the tail area of the car get off the subway, an electronic indication can be generated to indicate the escalator leading to the central area of the car through the electronic indication board.

[0085] In some embodiments, the emergency supervision management platform can determine the emergency evacuation parameters based on the area congestion risk.

[0086] In some embodiments, the emergency supervision management platform can determine the access control parameters according to the area congestion risk of the monitoring area according to a preset table. For example, the greater the area congestion risk of the monitoring area, the smaller the opening interval time of the gate of the corresponding entrance of the monitoring area, and the larger the opening interval time of the gate of the exit, and at the same time, the emergency supervision management platform can display the area with small area congestion risk and the corresponding evacuation route on the electronic indication board.

[0087] In some embodiments, the preset table can be preset by humans according to prior experience.

[0088] In some embodiments, the emergency supervision management platform is further configured to determine the similar area of the monitoring area based on the area function data, the area layout feature, and the area object data, and determine the emergency evacuation parameters based on the similar area and the area congestion risk.

[0089] The area function data refers to information data describing the function of the area. The area function data can include the area type of the monitoring area and the related function of the monitoring area, etc.

[0090] In some embodiments, the area type of the monitoring area is different when the corresponding site type of the monitoring area is different. For example, when the site type is a subway station, the area type of the monitoring area can include a rest area, a transportation area, a personnel passage area, etc.

[0091] In some embodiments, the related function of the monitoring area can be determined based on the corresponding area type, such as the function of the monitoring area corresponding to the rest area, which can include providing a rest place, etc.

[0092] The regional layout feature refers to layout information describing a plurality of functional devices and equipment in the monitoring region. For example, the number and distribution of functional devices and equipment in the monitoring region. The functional devices and equipment can include seats, information screens, turnstiles, etc. The distribution can include distribution density, etc.

[0093] In some embodiments, the distribution of functional devices and equipment in the monitoring region can be calculated by planar coordinate.

[0094] The similar region of the monitoring region refers to a region that meets a preset similarity condition with the region of the monitoring region. The region similarity refers to an index for quantifying the matching degree of a plurality of monitoring regions in terms of function, layout, and risk features. The preset similarity condition can include that the region similarity is greater than a preset threshold.

[0095] In some embodiments, the emergency supervision and management platform can construct a regional feature vector based on the regional function data and the regional layout feature of each monitoring region, then use a clustering algorithm to cluster the regional feature vectors of all monitoring regions to obtain a plurality of clustering clusters, and then the monitoring regions in the same cluster are similar regions by default, i.e., the monitoring regions in the same cluster are similar regions.

[0096] In some embodiments, the clustering algorithm can include K-means, DBSCAN, etc.

[0097] In some embodiments, the emergency supervision and management platform can respectively regard the monitoring region with a congestion risk lower than a first risk threshold as a low-risk region, and regard the monitoring region with a congestion risk greater than a second risk threshold as a high-risk region. When determining the passage control parameter and the passage guidance parameter of the emergency evacuation parameter, the low-risk region in the similar region of the high-risk region is regarded as the end point of the evacuation route and displayed on the electronic sign, and the opening interval of the entrance and exit turnstiles on the evacuation route is controlled to be increased.

[0098] Based on the region similarity and the region congestion risk, adjusting the evacuation route can reduce the trial and error cost, and enhance the robustness and adaptability of the smart city crowd evacuation system based on the Internet of Things large model.

[0099] For more information on determining the emergency evacuation parameter, see Figure 4 and related content.

[0100] In some embodiments, the emergency evacuation parameter can also include a device setting parameter.

[0101] The device setting parameter refers to a parameter for controlling the associated transportation device. For example, the transportation speed of the associated transportation device.

[0102] In some embodiments, the emergency supervision management platform is further configured to control the transportation speed of the associated transportation device based on the device setting parameter.

[0103] The associated transportation device refers to a transportation device deployed in the monitoring area or needed to be used when entering or leaving the monitoring area. For example, the moving walkway in the airport.

[0104] The transportation speed refers to the speed of the associated transportation device for transportation. For example, the transportation speed of the moving walkway in the airport.

[0105] In some embodiments, the emergency supervision management platform can control the transportation speed of the associated transportation device based on the area congestion risk by querying the congestion risk-transportation speed table. For example, the higher the area congestion risk, the faster the transportation speed of the device in the corresponding monitoring area (provided that it does not exceed the upper limit of the safety speed).

[0106] In some embodiments, the congestion risk-transportation speed table can be preset by manual according to prior experience.

[0107] In some embodiments of the present specification, controlling the transportation speed of the associated transportation device based on the area congestion risk can adjust the running speed of the associated transportation device in real time, realize the active regulation of the crowd flow, and ensure the safety of personnel while improving the overall passing efficiency.

[0108] Step 240, based on the emergency relief parameter, through the emergency supervision sensor network platform, to the emergency relief device deployed in the monitoring area, the emergency control signal is transmitted, so as to control the opening interval of the passage gate based on the passing control parameter, and the display content of the electronic sign based on the passing guide parameter.

[0109] The emergency relief device refers to a device for performing emergency relief in the monitoring area. For example, the passage gate, the electronic sign, the transportation device, etc.

[0110] The emergency control signal refers to a signal for controlling the emergency relief device to perform emergency relief.

[0111] In some embodiments, the emergency supervision management platform can control the passage gate and the electronic sign based on the emergency control signal, and at the same time, the emergency supervision management platform can also send the corresponding relief prompt information to the user terminal based on the emergency supervision user platform.

[0112] In some embodiments of the present specification, the actual area congestion risk can be accurately determined by the area monitoring data obtained by the monitoring device deployed in the monitoring area, and real-time accurate risk perception and early warning can be realized. At the same time, based on the actual area congestion risk, the emergency evacuation parameters are determined, and the corresponding emergency control signals are transmitted to the emergency evacuation device deployed in the monitoring area, so as to control the emergency evacuation device to perform personnel evacuation, which can reduce the accident rate, improve the evacuation efficiency, and significantly improve the public safety benefit.

[0113] Figure 3 is an exemplary schematic diagram of the area congestion risk according to some embodiments of the present specification.

[0114] In some embodiments, the emergency supervision management platform 130 can determine the area tolerance 321 based on the area specification characteristics 311 and the obstacle distribution data 312, and determine the area congestion risk 330 based on the area tolerance 321 and the area monitoring data 322.

[0115] For more information about the area monitoring data 322 and the area congestion risk 330, please refer to Figure 2 and related content.

[0116] The area specification characteristics refer to parameters describing the size specifications of the monitoring area. In some embodiments, the area specification characteristics include the shape and area of the monitoring area. The area specification characteristics can be obtained and characterized by the plan view of the monitoring area.

[0117] In some embodiments, the area specification characteristics can be obtained by user input.

[0118] The obstacle distribution data refers to parameters describing the distribution of obstacles in the area. In some embodiments, the obstacle distribution data includes the size of multiple obstacles in the monitoring area and the position coordinates of the obstacles.

[0119] In some embodiments, the emergency supervision management platform can determine the obstacle distribution data based on the monitoring image data in the area monitoring data. For example, the emergency supervision management platform can identify the monitoring image data in the area monitoring data by image recognition algorithm or image recognition model, so as to obtain the obstacle distribution data. For more information about the image recognition algorithm or image recognition model, please refer to Figure 2 and related description.

[0120] The area tolerance refers to a parameter measuring the carrying capacity of a certain area to congestion risk. In some embodiments, the larger the area tolerance of a certain area, the more likely the area is to be congested. In some embodiments, when the number of people in the area is the same, the larger the area tolerance of the area, the more serious the congestion of the area.

[0121] The emergency supervision management platform can determine the regional tolerance based on the regional specification features and the obstacle distribution data. In some embodiments, the emergency supervision management platform can construct a tolerance feature vector based on the regional specification features, the obstacle distribution data, and the regional type, retrieve a vector database based on the tolerance feature vector, and determine the regional tolerance based on the regional tolerance. The regional type refers to the type of a certain region in the monitoring region, such as a waiting area or a security check area of a train station. The vector database contains multiple sets of reference tolerance feature vectors and corresponding reference regional tolerances. The vector database can be constructed based on historical data or experimental data.

[0122] For example, the emergency supervision management platform can take the regional specification features, the obstacle distribution data, and the regional type in the historical data (such as data extracted from historical data in existing subway stations, shopping malls, train stations, and other smart city construction cases) or experimental data as the reference tolerance feature vector, normalize the actual congestion situation (such as evacuation time, complaint times, and the like), the pedestrian density, and the change rate of the pedestrian density in the historical data / experimental data, and then sum them up after weighting to generate the corresponding regional tolerance. The weights of the weighting are preset.

[0123] The emergency supervision management platform can determine the regional congestion risk in multiple ways based on the regional tolerance and the regional monitoring data.

[0124] In some embodiments, the emergency supervision management platform can determine the regional congestion risk by querying a preset congestion risk table based on the regional tolerance and the regional monitoring data. The preset congestion risk table can be preset according to historical data or experience.

[0125] In some embodiments, the greater the number of personnel and the number of target clusters in the regional monitoring data corresponding to the monitoring region, the lower the regional tolerance, and the greater the regional congestion risk. The target cluster refers to a cluster with a cluster density greater than a density threshold, and the density threshold is set according to experience. For more information about the cluster density, see Figure 2 and the related description.

[0126] In some embodiments, the emergency supervision management platform can determine the regional personnel features based on the regional monitoring data, and determine the regional congestion risk based on the regional personnel features, the regional tolerance, and the regional monitoring data.

[0127] The regional personnel features are parameters used to describe the features of the people present in the region. In some embodiments, the regional personnel features include the age distribution of the personnel in the region, the number and location of special groups of people, and the number and location of people with luggage. The special groups of people include people with disabilities, pregnant women, and the like.

[0128] In some embodiments, the emergency supervision management platform can acquire regional personnel features based on regional monitoring data, by using image recognition algorithms or image recognition models. For more information about image recognition algorithms or image recognition models, please refer to Figure 2 and the related description.

[0129] The emergency supervision management platform can determine the regional congestion risk based on the regional personnel features, the regional tolerance, and the regional monitoring data. In some embodiments, the emergency supervision management platform can determine the first correction data according to the regional personnel features and the correction table, determine the initial regional congestion risk by querying the preset congestion risk table based on the regional tolerance and the regional monitoring data, and obtain the regional congestion risk according to regional congestion risk = first correction data x initial regional congestion risk, where the initial regional risk is the regional congestion risk before correction.

[0130] The first correction data includes a first correction amplitude. The first correction amplitude refers to the coefficient of the correction of the initial regional risk. The correction table contains the age distribution of the regional personnel, the proportion of special groups, and the corresponding correction amplitude. The correction table can be constructed according to historical data or experimental data. For example, the higher the proportion of elderly people in the age distribution of the regional personnel and the proportion of special groups, the larger the correction amplitude, and the larger the corrected regional congestion risk. In some embodiments, the correction amplitude > 1.

[0131] In some embodiments of the present specification, the regional congestion risk is appropriately corrected by considering the regional personnel features, so that the determined regional congestion risk is more in line with the actual situation and more accurate.

[0132] In some embodiments, the emergency supervision management platform can determine the estimated passenger flow data at the future time point based on the regional monitoring data, the regional specification features, and the external environment data by using the feature estimation model, determine the estimated risk data based on the estimated passenger flow data, and determine the updated regional congestion risk based on the estimated risk data and the regional tolerance.

[0133] The external environment data is data used to describe the external environment of the monitoring area at the current time point. In some embodiments, the external environment data can include the rainfall, temperature, and weather type of a certain area.

[0134] In some embodiments, the external environment data can be obtained through a third-party platform.

[0135] The estimated passenger flow data is the passenger flow feature of a certain area at the future time point. For more information about the passenger flow feature, please refer to Figure 2 and the related description.

[0136] In some embodiments, the emergency supervision management platform can determine the estimated crowd flow data at the future time point based on the regional monitoring data, the regional specification features, and the external environment data, through a feature estimation model.

[0137] The feature estimation model refers to a model for estimating the estimated crowd flow data at the future time point. The feature estimation model is a machine learning model. For example, the feature estimation model includes one or more of a combination of a deep neural network (DNN) model or other custom models.

[0138] The inputs of the feature estimation model include the regional monitoring data, the regional specification features, and the external environment data, and the output is the estimated crowd flow data at the future time point.

[0139] In some embodiments, the emergency supervision management platform can determine the estimated crowd flow data at the future time point based on the regional personnel features, the regional monitoring data, the regional specification features, and the external environment data, through a feature estimation model. For more information about the regional personnel features, please refer to the relevant description above.

[0140] In some embodiments of the present specification, the activity behaviors of different regional populations are different, and by considering the current regional personnel features, the estimated crowd flow at the future time point is more accurate.

[0141] In some embodiments, the feature estimation model can be obtained by training an initial feature estimation model with a plurality of first training samples with first labels. The first training sample can include sample regional monitoring data, sample regional specification features, and sample external environment data of a sample region at a first historical time point. The first label can include the actual crowd flow features of the sample region at a second historical time point under the first training sample. The first historical time point precedes the second historical time point. The sample region can include one or more sample monitoring regions.

[0142] In some embodiments, the first training sample and the first label can be obtained based on historical data.

[0143] In some embodiments, the emergency supervision management platform can input a plurality of first training samples with first labels into the initial feature estimation model, construct a loss function based on the first labels and the results of the initial feature estimation model, and update the parameters of the initial feature estimation model based on the loss function through gradient descent or other methods. When a preset condition is met, the model training is completed, and a trained feature estimation model is obtained. The preset condition can be that the loss function converges, the number of iterations reaches a threshold, etc.

[0144] The estimated risk data is data for describing the regional congestion risk of a region at a future time point.

[0145] In some embodiments, the emergency supervision management platform can determine the regional congestion risk at the future time point according to the people flow data at the future time point, and take the regional congestion risk at the future time point as the estimated risk data. For more information on how to determine the regional congestion risk based on the people flow data, please refer to step 220 of FIG. 2 and the related description thereof. Figure 2

[0146] In some embodiments, the emergency supervision management platform can determine the updated regional congestion risk based on the estimated risk data and the regional tolerance. For example, the emergency supervision management platform obtains a risk growth amplitude according to the difference between the estimated risk data and the current regional congestion risk, determines the regional congestion risk according to the regional personnel characteristics, the regional tolerance, and the regional monitoring data when the risk growth amplitude exceeds a risk threshold, determines a second correction data according to the risk growth amplitude, and determines the updated regional congestion risk according to the updated regional congestion risk = the second correction data x the regional congestion risk. The second correction data includes a second correction amplitude, which refers to the coefficient of the correction of the regional congestion risk. For more information on how to determine the regional congestion risk according to the regional personnel characteristics, the regional tolerance, and the regional monitoring data, please refer to the related description above.

[0147] wherein the risk growth amplitude and the correction data are positively correlated, and the risk threshold is empirically preset.

[0148] In some embodiments of the present specification, by considering the people flow data and the risk data at the future time point, the accuracy of regional congestion risk early warning is improved and the allocation of management resources is optimized.

[0149] In some embodiments of the present specification, by comprehensively analyzing the regional physical properties, the obstacle distribution, and the real-time monitoring data, the regional carrying capacity threshold and the risk level are dynamically quantified, the accurate prediction and graded early warning of people flow congestion risk are achieved, and the scientificity and risk prediction ability of public space safety management are effectively improved.

[0150] Figure 4 is an exemplary schematic diagram of determining the emergency evacuation parameter according to some embodiments of the present specification.

[0151] In some embodiments, the emergency supervision management platform is further configured to: obtain a candidate emergency parameter 410; determine the evacuation risk data 450 corresponding to the candidate emergency parameter 410 by the evacuation estimation model 440 based on the candidate emergency parameter 410, the regional congestion risk 420, and the regional specification characteristics 430; the evacuation estimation model 440 is a machine learning model; and determine the emergency evacuation parameter 460 based on the evacuation risk data 450.

[0152] The candidate emergency parameter refers to the candidate emergency evacuation parameter. ​

[0153] In some embodiments, the emergency supervision management platform can determine a parameter range of the emergency evacuation parameter of the monitoring area according to the regional congestion risk of the monitoring area, and randomly generate a candidate emergency parameter within the parameter range.

[0154] For example, different candidate emergency parameters can be exit gate opening intervals adjusted at different amplitudes, and different evacuation routes generated based on different evacuation directions. Wherein, the parameter range of the emergency evacuation parameter corresponding to different regional congestion risks is different, such as the greater the regional congestion risk, the smaller the opening interval time of the entrance gate, the larger the opening interval time of the exit gate, and the more the corresponding evacuation direction and / or evacuation route, and the evacuation destination is a monitoring area with less regional congestion risk (such as less than the regional congestion risk of the departure area) and higher similarity (such as higher than a preset threshold) to the departure area.

[0155] In some embodiments, the planning of the evacuation route can be determined based on the regional congestion risks of the monitoring areas of the entire site, such as the evacuation route can be a monitoring area with high regional congestion risk as the departure area, a monitoring area with low regional congestion risk as the destination, and the regional congestion risk of the monitoring area along the way is preferably not higher than the departure area, based on path planning algorithms such as Dijkstra, algorithm, etc., to plan the monitoring areas with high regional congestion risk.

[0156] The regional specification feature refers to a feature used to describe the physical space attribute of the monitoring area. For example, the size of the monitoring area.

[0157] The evacuation estimation model is a model used to determine the evacuation risk data corresponding to the candidate emergency parameter. In some embodiments, the evacuation estimation model is a machine learning model. For example, a deep neural network (DNN) model, etc.

[0158] The input of the evacuation estimation model can include the candidate emergency parameter, the current and historical regional congestion risk of the monitoring area, the regional specification feature, the current and historical regional monitoring data, the current and historical passenger flow feature, and the emergency device data. For more information about the regional congestion risk, the regional monitoring data, and the passenger flow feature, please refer to the above Figure 2 related content.

[0159] The emergency device data refers to data related to the emergency evacuation device, such as the type, number, distribution in the monitoring area, etc.

[0160] The output of the evacuation estimation model can include the evacuation risk data corresponding to the candidate emergency parameter.

[0161] The evacuation risk data refers to the regional congestion risk of the monitoring area at a future time point, assuming that the personnel in the monitoring area are evacuated using the candidate emergency parameter.

[0162] In some embodiments, the input of the evacuation estimation model further includes regional personnel features.

[0163] For more information about regional personnel features, please refer to the above Figure 3 .

[0164] By introducing regional personnel features, the evacuation estimation model can more accurately capture the dynamics and diversity of crowd behavior, thereby generating more scientific emergency evacuation parameters. The synergistic effect of such multi-dimensional input not only improves the prediction accuracy, but also enhances the adaptability of the system to complex scenarios, providing strong technical support for urban emergency management.

[0165] The training method of the evacuation estimation model is the same as that of the feature estimation model. For more information about the training method of the feature estimation model, please refer to the above Figure 3 .

[0166] In some embodiments, the second training sample and the second label can be obtained based on historical data.

[0167] In some embodiments, the second training sample includes a sample emergency parameter, a regional congestion risk of a sample area at a first time point, a regional congestion risk at a second time point, regional specification features of the sample area, regional monitoring data of the sample area at the first time point, regional monitoring data at the second time point, people flow features of the sample area at the first time point, people flow features at the second time point, and emergency device data of the sample area.

[0168] In some embodiments, the second training label is the actual regional congestion risk of the sample area at a third time point, which can be determined based on historical data, such as based on regional monitoring data of the sample area at the third time point. Wherein, the first time point, the second time point and the third time point are all historical time points, and the first time point is before the second time point, and the second time point is before the third time point.

[0169] In some embodiments, the emergency supervision and management platform can take the candidate emergency parameter corresponding to the evacuation risk data less than the second risk threshold as the emergency evacuation parameter.

[0170] In some embodiments, the emergency supervision and management platform can also take the candidate emergency parameter corresponding to the minimum evacuation risk data as the emergency evacuation parameter.

[0171] In some embodiments, the future time point can include a plurality of future time points, the emergency management platform can perform weighted calculation on the regional congestion risk of all future time points contained in the evacuation risk data, and take the candidate emergency parameter corresponding to the evacuation risk data with the minimum weighted value as the emergency evacuation parameter, wherein the closer the future time point is to the present, the greater the weight of the regional congestion risk thereof.

[0172] In some embodiments of the present specification, the emergency evacuation parameter is determined based on historical parameters by the evacuation estimation model, which can quickly locate high-value options from the historical parameters and improve decision-making efficiency. In addition, the use of the evacuation estimation model improves the accuracy of risk prediction and realizes precise risk prevention and control.

[0173] The above has described the basic concepts, and it is obvious that the above detailed disclosure is only used as an example and does not limit the present specification. Although it is not explicitly stated here, those skilled in the art can make various modifications, improvements and corrections to the present specification. Such modifications, improvements and corrections are suggested in the present specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of the present specification.

[0174] Meanwhile, specific words are used in the present specification to describe the embodiments of the present specification. As "one embodiment", "an embodiment", and / or "some embodiments" means a certain feature, structure or characteristic related to at least one embodiment of the present specification. Therefore, it should be emphasized and noted that the "an embodiment" or "one embodiment" or "one alternative embodiment" mentioned in different positions in the present specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present specification can be properly combined.

[0175] In addition, unless the claim explicitly states otherwise, the order of the processing elements and sequences described in the present specification, the use of numerals and letters, or the use of other names, is not intended to limit the order of the processes and methods of the present specification. Although some currently considered useful embodiments of the invention are discussed in the above disclosure through various examples, it should be understood that such details are only for the purpose of illustration, and the additional claims are not limited to the disclosed embodiments, on the contrary, the claims are intended to cover all modifications and equivalent combinations that meet the spirit and scope of the embodiments of the present specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on existing servers or mobile devices.

[0176] For simplicity and to facilitate understanding of one or more embodiments, a description of an embodiment sometimes refers to a plurality of features in a single embodiment, drawing, or description of an embodiment. However, this method of disclosure is not to be interpreted as meaning that the claimed embodiment requires more features than are explicitly recited in the claims. In fact, claims that do not specifically claim a combination of features are intended to cover the various possible combinations of features as would be understood by a person of ordinary skill in the art.

[0177] Some embodiments use numerical values to describe components, quantities of attributes. It should be understood that such numerical values used in the description of embodiments are, in some examples, modified by the adjectives "about," "approximately," or "substantially." Unless otherwise stated, "about," "approximately," or "substantially" indicate that the described numerical value allows for a variation of ±20%. Accordingly, numerical values used in the specification and claims of some embodiments are approximations that can vary depending on the desired characteristics of the individual embodiments. In some embodiments, numerical values used in the specification and claims are approximations that can vary depending on the desired characteristics of the individual embodiments. In some embodiments, numerical values should be considered in the context of the number of significant digits used in the number and the accepted bits of precision of the number. Although the numerical ranges and parameters setting forth the broadest scope of some embodiments of the specification are approximations, the numerical values set forth in the specific examples are reported as precisely as reasonably possible. The application is not limited to the specific numerical values set forth in the examples.

[0178] Each patent, patent application, patent publication, and other material cited in this specification is hereby incorporated by reference in its entirety. In the event of inconsistencies between the disclosure of this specification and the materials incorporated by reference, the disclosure of this specification shall prevail. In the event of inconsistencies between the disclosure of this specification and the claims, the claims shall prevail. In the event of inconsistencies between the disclosure of this specification and the materials incorporated by reference (whether attached hereto or subsequently added), the disclosure of this specification shall prevail. In the event of inconsistencies between the disclosure of this specification and the description, definitions, and / or terminology used in the materials incorporated by reference, the description, definitions, and / or terminology used in this specification shall prevail.

[0179] Finally, it should be understood that the embodiments described herein are merely exemplary of the principles of the embodiments described herein. Other variations having essentially the same structure and function but different values for components, and / or different arrangements of the components can also be utilized. Accordingly, the embodiments described herein are not to be considered as limited to the examples described herein.

Claims

1. A smart city crowd management system based on an IoT big data model, characterized by: The system includes an emergency monitoring and management platform, which is configured as follows: Based on the emergency monitoring and control platform, regional monitoring data is acquired through monitoring devices deployed in the monitoring area; Based on the regional monitoring data, the regional congestion risk is determined, including: determining the regional population characteristics based on the regional monitoring data; determining the regional tolerance based on the regional size characteristics and obstacle distribution data; determining the first corrected data by querying a correction table according to the regional population characteristics; determining the initial regional congestion risk by querying a preset congestion risk table based on the regional tolerance and the regional monitoring data; and determining the regional congestion risk by multiplying the first corrected data by the initial regional congestion risk, wherein the initial regional congestion risk is the regional congestion risk before correction; the regional population characteristics include the age distribution of the population in the region, the number and location of special groups, and the number and location of people carrying luggage, wherein the special groups include people with mobility impairments and pregnant women; In response to the congestion risk in the area meeting the dispersal conditions: Based on the area congestion risk, emergency evacuation parameters are determined, including: acquiring candidate emergency parameters; based on the candidate emergency parameters, the area congestion risk, the area's specifications, and the personnel characteristics, determining the evacuation risk data corresponding to the candidate emergency parameters using an evacuation prediction model; the evacuation risk data refers to the area congestion risk of the monitored area at a future time point assuming the candidate emergency parameters are used to evacuate personnel from the monitored area; the evacuation prediction model is a machine learning model; based on the evacuation risk data, the emergency evacuation parameters are determined; the emergency evacuation parameters include equipment setting parameters, traffic control parameters, and traffic guidance parameters, wherein the equipment setting parameters are used to control the transportation speed of associated transportation equipment; Based on the emergency evacuation parameters, an emergency control signal is transmitted to the emergency evacuation devices deployed in the monitoring area through the emergency monitoring sensor network platform. Based on the passage control parameters, the opening interval of the access gate is controlled, and based on the passage guidance parameters, the display content of the electronic signs is controlled. The display content includes at least one of display color, evacuation direction, and evacuation route.

2. The system according to claim 1, characterized in that, The emergency monitoring and management platform is further configured as follows: Based on the regional monitoring data, the regional specifications and characteristics, and the external environment data, the estimated pedestrian flow data for future time points is determined through a feature prediction model; the feature prediction model is a machine learning model. Based on the estimated pedestrian flow data, the estimated risk data is determined; Based on the estimated risk data and the regional tolerance, the updated regional congestion risk is determined.

3. The system according to claim 1, characterized in that, The emergency monitoring and management platform is further configured as follows: Based on regional functional data, regional layout characteristics, and regional object data, similar regions of the monitoring area are determined; The emergency evacuation parameters are determined based on the similar areas and the congestion risk in those areas.

4. A smart city crowd management method based on an IoT big data model, characterized by: The method is executed by an emergency monitoring and management platform for crowd control in smart cities based on an IoT big data model. The method includes: Based on the emergency monitoring and control platform, regional monitoring data is acquired through monitoring devices deployed in the monitoring area; Based on the regional monitoring data, the regional congestion risk is determined, including: determining the regional population characteristics based on the regional monitoring data; determining the regional tolerance based on the regional size characteristics and obstacle distribution data; determining the first corrected data by querying a correction table according to the regional population characteristics; determining the initial regional congestion risk by querying a preset congestion risk table based on the regional tolerance and the regional monitoring data; and determining the regional congestion risk by multiplying the first corrected data by the initial regional congestion risk, wherein the initial regional congestion risk is the regional congestion risk before correction; the regional population characteristics include the age distribution of the population in the region, the number and location of special groups, and the number and location of people carrying luggage, wherein the special groups include people with mobility impairments and pregnant women; In response to the congestion risk in the area meeting the dispersal conditions: Based on the area congestion risk, emergency evacuation parameters are determined, including: acquiring candidate emergency parameters; based on the candidate emergency parameters, the area congestion risk, the area's specifications, and the personnel characteristics, determining the evacuation risk data corresponding to the candidate emergency parameters using an evacuation prediction model; the evacuation risk data refers to the area congestion risk of the monitored area at a future time point assuming the candidate emergency parameters are used to evacuate personnel from the monitored area; the evacuation prediction model is a machine learning model; based on the evacuation risk data, the emergency evacuation parameters are determined; the emergency evacuation parameters include equipment setting parameters, traffic control parameters, and traffic guidance parameters, wherein the equipment setting parameters are used to control the transportation speed of associated transportation equipment; Based on the emergency evacuation parameters, an emergency control signal is transmitted to the emergency evacuation devices deployed in the monitoring area through the emergency monitoring sensor network platform. Based on the passage control parameters, the opening interval of the access gate is controlled, and based on the passage guidance parameters, the display content of the electronic signs is controlled. The display content includes at least one of display color, evacuation direction, and evacuation route.

5. The method according to claim 4, characterized in that, The method further includes: Based on the regional monitoring data, the regional specifications and characteristics, and the external environment data, the estimated pedestrian flow data for future time points is determined through a feature prediction model; the feature prediction model is a machine learning model. Based on the estimated pedestrian flow data, the estimated risk data is determined; Based on the estimated risk data and the regional tolerance, the updated regional congestion risk is determined.

6. The method according to claim 4, characterized in that, The determination of emergency evacuation parameters based on the area's congestion risk includes: Based on regional functional data, regional layout characteristics, and regional object data, similar regions of the monitoring area are determined; The emergency evacuation parameters are determined based on the similar areas and the congestion risk in those areas.

7. A smart city crowd management device based on an Internet of Things (IoT) big data model, characterized in that, The device includes at least one processor and at least one memory; The at least one memory is used to store computer instructions; The at least one processor is used to execute at least some of the computer instructions to implement the smart city crowd management method based on the Internet of Things big model as described in claim 4.

8. A computer-readable storage medium, characterized in that, The storage medium stores computer instructions. When the computer reads the computer instructions from the storage medium, the computer executes the smart city crowd management method based on the Internet of Things big model as described in claim 4.

Images