Smart city crowd dredging system and method based on Internet of Things large model, and medium

Abstract

The invention provides a smart city crowd dispersion system and method based on an Internet of Things large model, and a medium, the system comprises an emergency supervision management platform, and the emergency supervision management platform is configured to obtain area monitoring data through a monitoring device deployed in a monitoring area based on an emergency supervision perception control platform; determining a regional congestion risk based on the regional monitoring data; responding to the condition that the regional congestion risk meets the dispersion condition: determining emergency dispersion parameters based on the regional congestion risk, the emergency dispersion parameters including a traffic control parameter and a traffic guide parameter; based on the emergency dredging parameters, an emergency control signal is transmitted to an emergency dredging device deployed in a monitoring area through an emergency supervision sensing network platform, so that the opening interval of a channel gate machine is controlled based on the passing control parameters, and the display content of an electronic indication board is controlled based on the passing guide parameters; the display content comprises at least one of a display color, a dredging direction and a dredging route.

Description

Technical Field

[0001] This specification relates to the field of urban crowd management, and in particular to a smart city crowd management system, method and medium based on an Internet of Things large model. Background Art

[0002] In order to accurately determine the crowd flow characteristics corresponding to different public places and at different times, and then determine the actual congestion risk and further provide appropriate crowd guidance plans, it is necessary to provide a smart city crowd guidance system based on the Internet of Things large model. It can obtain regional monitoring data through monitoring devices deployed in the monitoring area, determine the actual regional congestion risk, and send emergency control signals to the emergency guidance devices deployed in the monitoring area to control the emergency guidance devices to perform personnel guidance. Summary of the Invention

[0003] One or more embodiments of this specification provide a smart city crowd management system based on an Internet of Things big model, wherein the system includes an emergency supervision and management platform, which is configured to: execute a smart city crowd management method based on an Internet of Things big model.

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

[0005] One or more embodiments of this specification provide a smart city crowd management device based on a large model of the Internet of Things, 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 implement the above-mentioned smart city crowd management method based on the large model of the Internet of Things.

[0006] One or more embodiments of this specification provide a computer-readable storage medium that 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 the Internet of Things large model.

[0007] In some embodiments of this specification, regional monitoring data acquired by monitoring devices deployed in the monitoring area can accurately determine the actual regional congestion risk, enabling real-time and accurate risk perception and early warning. Furthermore, based on the actual regional congestion risk, emergency evacuation parameters are determined, and corresponding emergency control signals are transmitted to emergency evacuation devices deployed in the monitoring area to control the emergency guidance devices to perform personnel evacuation. This can reduce accident rates, improve evacuation efficiency, and significantly enhance public safety benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification 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: Figure 1 This is an exemplary structural diagram of a smart city crowd management system based on an Internet of Things (IoT) model according to some embodiments of this specification; Figure 2 This is an exemplary flow chart of a method for crowd management in a smart city based on an Internet of Things (IoT) model according to some embodiments of this specification; Figure 3 is a schematic diagram of a scenario for determining regional congestion risk according to some embodiments of this specification; Figure 4 This is an exemplary schematic diagram of determining emergency evacuation parameters according to some embodiments of this specification. DETAILED DESCRIPTION

[0009] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification 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.

[0010] 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.

[0011] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0012] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0013] Figure 1 This is an exemplary structural diagram of a smart city crowd management system based on an Internet of Things large model according to some embodiments of this specification.

[0014] In some embodiments, as Figure 1 As shown, a smart city crowd management system 100 based on the Internet of Things big 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 control platform 150.

[0015] The emergency supervision user platform 110 refers to the platform for comprehensive coordination of emergency supervision by higher-level departments.

[0016] In some embodiments, the emergency supervision user platform includes a third-party terminal.

[0017] 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.

[0018] The emergency supervision service platform 120 refers to an interactive service platform for receiving and transmitting data.

[0019] In some embodiments, the emergency supervision service platform 120 interacts with the emergency supervision user platform 110 upwards and interacts with the emergency supervision management platform 130 downwards.

[0020] In some embodiments, the emergency supervision service platform 120 may be configured with a single server or a server group, a gateway, and a router. The server group may be centralized or distributed.

[0021] The emergency supervision management platform 130 is 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.

[0022] 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.

[0023] The data center can be used to coordinate the management of the collected emergency supervision data.

[0024] In some embodiments, the data center is configured with storage.

[0025] 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.

[0026] The emergency sub-platform refers to the sub-platform for supervising emergency supervision data.

[0027] In some embodiments, the emergency supervision management platform 130 is configured to obtain regional monitoring data based on the emergency supervision perception control platform through monitoring devices deployed in the monitoring area; determine the regional congestion risk based on the regional monitoring data; in response to the regional congestion risk meeting the diversion conditions: determine emergency diversion parameters based on the regional congestion risk, and the emergency diversion parameters include traffic control parameters and traffic guidance parameters; based on the emergency diversion parameters, send an emergency control signal to the emergency diversion device deployed in the monitoring area through the emergency supervision sensor network platform to control the opening interval of the channel gate based on the traffic control parameters, and control the display content of the electronic sign based on the traffic guidance parameters, and the display content includes at least one of display color, diversion direction and diversion route.

[0028] The emergency supervision sensor network platform 140 refers to a management platform for transmitting sensor data or information related to emergency supervision.

[0029] In some embodiments, the emergency supervision sensor network platform 140 interacts upward with the data center in the emergency supervision management platform 130 and interacts downward with the emergency supervision perception control platform.

[0030] The emergency monitoring sensor network platform 140 includes multiple sensor sub-platforms. In some embodiments, each sensor sub-platform can collect sensor data of a region and upload it to the corresponding emergency sub-platform.

[0031] In some embodiments, the emergency monitoring sensor network platform 140 includes a communication transmission network and a routing device. The communication transmission network can implement the functions of sensing information and controlling information. The routing device is a hardware device that implements information sensing communication.

[0032] The emergency supervision perception control platform 150 refers to a platform for collecting emergency supervision data and implementing execution instructions.

[0033] In some embodiments, the emergency supervision perception control platform is configured with sensors, storage and emergency guidance devices.

[0034] Sensors are devices used to receive and convert various monitoring information. In some embodiments, sensors include cameras and infrared counters. The cameras can be used to obtain monitoring image data, and the infrared counters can be installed at the entrances and exits of the passages to obtain monitoring count data. For more information about monitoring image data and monitoring count data, please see Figure 2 and its related descriptions.

[0035] Emergency guidance devices are devices that provide support for emergency situations. In some embodiments, emergency guidance devices include gates, electronic signs, elevators or escalators, broadcasting devices, etc.

[0036] For more detailed information about the smart city crowd management system based on the IoT model, please refer to Figures 2 to 4 Related description.

[0037] In some embodiments of this specification, a smart city crowd management system based on a large IoT model can form an information operation closed loop between various functional platforms, operate in a coordinated and regular manner, and improve the efficiency of handling sudden emergency events by efficiently and accurately determining the actual emergency control scope.

[0038] Figure 2 This is an exemplary flow chart of a method for crowd management in a smart city based on a large IoT model according to some embodiments of this specification. 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.

[0039] Step 210: Based on the emergency supervision perception control platform, regional monitoring data is obtained through monitoring devices deployed in the monitoring area.

[0040] In some embodiments, the application scenario of this case may be places with multiple entrances and exits, including subway stations and large stadiums.

[0041] In some embodiments, a place includes multiple monitoring areas, and the monitoring areas are interconnected, such as through channels, entrances and exits, or directly connected.

[0042] In some embodiments, the multiple monitoring areas may refer to multiple areas naturally formed by buildings corresponding to the location, for example, waiting hall A and waiting hall B of a station.

[0043] In some embodiments, the multiple monitoring areas may also refer to multiple areas that are divided into areas within the venue, for example, the northeast corner, southeast corner, southwest corner, northwest corner, etc. of the waiting room A.

[0044] In some embodiments, a location may correspond to a monitoring area, and different functional areas or different location areas within the monitoring area may correspond to different sub-areas within the monitoring area. The sub-area division method may be preset in advance, such as based on unit space division.

[0045] For ease of explanation, the following example takes a place containing multiple monitoring areas.

[0046] Surveillance devices are devices installed within the monitoring area to perform surveillance functions. Examples include video analysis cameras, infrared / thermal imaging cameras, acoustic sensors, smart gates, facial recognition devices, infrared counters, etc.

[0047] Regional monitoring data refers to the monitoring data of the entire monitoring area collected by the monitoring device.

[0048] In some embodiments, the area monitoring data may include: monitoring image data, monitoring count data, etc.

[0049] In some embodiments, the regional monitoring data of multiple monitoring areas constitute the monitoring data of the entire site.

[0050] In some embodiments, regional monitoring data may be obtained through monitoring devices disposed within the monitoring area.

[0051] Step 220: Determine the regional congestion risk based on the regional monitoring data.

[0052] Regional congestion risk refers to the risk of safety accidents, public disorder, or health hazards occurring within a monitored area due to excessive population density, poor mobility, or improper management. Examples include stampede risks and evacuation failure risks.

[0053] In some embodiments, the emergency supervision and management platform can obtain crowd flow characteristics based on regional monitoring data, calculate the personnel density characteristics of the monitoring area based on the crowd flow characteristics and the size of the area, and then determine the regional congestion risk.

[0054] Crowd flow characteristics refer to characteristics related to the flow of people within a monitoring area. For example, the number of people, the volume of people, and the movement patterns of people. Crowd flow characteristics can be calculated separately for multiple areas within a monitoring area.

[0055] In some embodiments, the emergency supervision and management platform can use monitoring count data to obtain pedestrian flow and personnel numbers. Based on the monitoring image data, it can then use image recognition algorithms or models to determine the direction of pedestrian movement. Image recognition algorithms can include Haar feature cascade algorithms and support vector machines (SVMs). Image recognition models can include YOLO and Gaussian mixture models (GMMs).

[0056] Crowd density characteristics refer to the quantitative indicators and dynamic attributes of crowd distribution within a monitoring area, which are used to describe, assess, and predict regional congestion risks. For example, the density of people within the area and the distribution of people density.

[0057] In some embodiments, the emergency supervision and management platform can use clustering algorithms to process crowd flow characteristics and area size to determine population density distribution. For example, a clustering algorithm can be used to cluster people within the monitoring area based on their location coordinates, resulting in multiple clusters, each containing the coordinate ranges of people in multiple areas within the monitoring area (e.g., cluster 1 covers the area from Exit A to Gate B). Clustering algorithms can include the DBSCAN algorithm, among others.

[0058] In some embodiments, the personnel density distribution may include a personnel distribution cluster density and a personnel distribution cluster radius.

[0059] The density of a population distribution cluster refers to the ratio of the total number of people in the cluster to the area covered by the cluster.

[0060] The radius of a population distribution cluster refers to the distance between the farthest two points within the cluster coverage area, which can reflect the degree of looseness of population distribution.

[0061] In some embodiments, the greater the population density characteristic of the monitoring area, the greater the risk of congestion in the area.

[0062] In some embodiments, in response to a large number of clusters having a density greater than a density threshold (e.g., a number greater than a threshold), the emergency supervision management platform may generate a broadcast audio message to remind people not to gather in large groups. The density threshold may be manually preset based on prior experience.

[0063] In some embodiments, the emergency supervision management platform can display cluster density in the form of a heat map on a map interface, for example, red represents high risk and green represents low risk; this can be displayed to staff, who can broadcast / intervene to remind people not to gather in groups.

[0064] In some embodiments, the emergency supervision management platform may also determine the regional congestion risk based on the relationship that the greater the population density in multiple areas within the monitoring area and the greater the number of clusters with cluster density greater than the density threshold, the greater the regional congestion risk.

[0065] Step 230 , in response to the regional congestion risk meeting the evacuation condition: determining emergency evacuation parameters based on the regional congestion risk.

[0066] In some embodiments, emergency evacuation parameters may include traffic control parameters and traffic guidance parameters.

[0067] The conditions for diversion include the risk of regional congestion being higher than the preset risk threshold.

[0068] In some embodiments, the preset risk threshold may be preset manually based on prior experience.

[0069] Access control parameters refer to the control parameters of access-related equipment, such as the opening interval of the channel gate at the entrance and exit.

[0070] A channel gate is a gate that monitors the passages within the area being monitored, for example, the gate at Exit C of a subway station.

[0071] The opening interval refers to the length of time that the channel gate in the monitoring area remains open.

[0072] Traffic guidance parameters refer to the control parameters of the indicating device (such as an electronic sign), for example, the display content of the electronic sign.

[0073] Electronic signage refers to a display board installed within a monitoring area to provide information to the public, for example, an LED signage.

[0074] The display content may include at least one of a display color, a diversion direction, and a diversion route.

[0075] Display color refers to the color displayed on the electronic sign. For example, red represents high urgency, green represents low urgency, etc.

[0076] The diversion direction refers to the direction in which people are being guided, for example, the destination of the diversion route.

[0077] An evacuation route refers to the route that guides people to evacuate to their destination.

[0078] In some embodiments, the emergency supervision management platform can use a path planning algorithm to generate a diversion route. The path planning algorithm can include Dijkstra, Algorithms, etc.

[0079] In some embodiments, the evacuation route may include multiple routes leading to different low-risk areas (if multiple low-risk areas exist). The starting point of the evacuation route may be the center of the current monitoring area. For a description of low-risk areas, see below.

[0080] For example, in the current subway, people are concentrated in the front and rear areas of the subway car, while there are very few people in the central area of ​​the car. When people in the front and rear areas of the car walk out of the subway, they can generate electronic instructions and use electronic signs to direct them to the escalator in the center of the car.

[0081] In some embodiments, the emergency supervision and management platform can determine emergency evacuation parameters based on regional congestion risks.

[0082] In some embodiments, the emergency supervision and management platform can determine access control parameters based on a preset table and the risk of regional congestion in the monitored area. For example, as the risk of regional congestion in the monitored area increases, the emergency supervision and management platform can adjust the opening interval of gates at the corresponding entrances to the monitored area to be shorter, and the opening interval of gates at the corresponding exits to be longer. Furthermore, the emergency supervision and management platform can display areas with low regional congestion risks and their corresponding routes on electronic signs.

[0083] In some embodiments, the preset table may be preset manually based on prior experience.

[0084] In some embodiments, the emergency supervision management platform is further configured to: determine similar areas of the monitoring area based on regional function data, regional layout characteristics and regional object data; and determine emergency evacuation parameters based on similar areas and regional congestion risks.

[0085] Regional function data refers to information data describing regional functions. Regional function data may include the type of the monitoring area and the relevant functions of the monitoring area.

[0086] In some embodiments, when the monitoring area corresponds to different types of places, the area types of the monitoring area are different. For example, when the place type is a subway station, the area types of the monitoring area may include rest area, transportation area, personnel passage area, etc.

[0087] In some embodiments, the relevant functions of the monitoring area can be determined based on the corresponding area type. For example, the function of the monitoring area corresponding to the rest area can include providing a resting place, etc.

[0088] Area layout characteristics describe the layout of multiple functional devices and equipment within a monitoring area. For example, they include the number and distribution of functional devices and equipment within the monitoring area. Functional devices and equipment can include seats, information screens, gates, etc. Distribution can include density, etc.

[0089] In some embodiments, the distribution of functional devices and equipment within the monitoring area can be calculated using plane coordinates.

[0090] Similar areas within a monitoring area are areas whose regional similarity to the monitoring area meets preset similarity criteria. Regional similarity is a metric used to quantify the degree of matching between multiple monitoring areas in terms of function, layout, and risk characteristics. Preset similarity criteria may include regional similarity exceeding a preset threshold.

[0091] In some embodiments, the emergency supervision management platform can construct a regional feature vector based on the regional function data and regional layout characteristics of each monitoring area; then use a clustering algorithm to cluster the regional feature vectors of all monitoring areas to obtain multiple cluster clusters. The default regional similarity of the monitoring areas within the same cluster meets the preset similarity conditions, that is, the monitoring areas within the same cluster are similar areas to each other.

[0092] In some embodiments, the clustering algorithm may include K-means, DBSCAN, etc.

[0093] In some embodiments, the emergency supervision and management platform can designate monitoring areas with a congestion risk below a first risk threshold as low-risk areas, and monitoring areas with a congestion risk greater than a second risk threshold as high-risk areas. When determining the traffic control parameters and traffic guidance parameters for emergency diversion, the low-risk area within a similar area to the high-risk area is designated as the end point of the diversion route and displayed on an electronic sign. The opening interval of the entrance and exit gates along the diversion route is also increased.

[0094] Adjusting the crowd diversion routes based on regional similarity and regional congestion risk can reduce the cost of trial and error and enhance the robustness and adaptability of the smart city crowd diversion system based on the IoT big model.

[0095] For more information on determining emergency evacuation parameters, see Figure 4 and its related contents.

[0096] In some embodiments, emergency evacuation parameters may also include equipment setting parameters.

[0097] Equipment setting parameters refer to parameters related to controlling associated transport equipment, such as the transport speed of associated transport equipment.

[0098] In some embodiments, the emergency supervision management platform is further configured to: control the transportation speed of the associated transportation equipment based on equipment setting parameters.

[0099] Associated transportation equipment refers to transportation equipment deployed within the monitoring area or required for entering or exiting the monitoring area, for example, a moving walkway at an airport.

[0100] Transport speed refers to the speed at which the associated transport equipment is transporting goods. For example, the transport speed of a moving walkway at an airport.

[0101] In some embodiments, the emergency supervision and management platform can query the congestion risk-transportation speed table to control the transportation speed of associated transportation equipment based on regional congestion risk. For example, the higher the regional congestion risk, the faster the equipment transportation speed within the corresponding monitoring area (assuming it does not exceed the safety speed limit).

[0102] In some embodiments, the congestion risk-transportation speed table can be preset manually based on prior experience.

[0103] In some embodiments of this specification, the transport speed of associated transport equipment is controlled based on regional congestion risk, and the operating speed of associated transport equipment can be adjusted in real time to achieve active regulation of crowd flow, thereby ensuring personnel safety and improving overall traffic efficiency.

[0104] Step 240, based on the emergency evacuation parameters, an emergency control signal is transmitted to the emergency evacuation device deployed in the monitoring area through the emergency supervision sensor network platform to control the opening interval of the channel gate based on the passage control parameters, and to control the display content of the electronic sign based on the passage guidance parameters.

[0105] Emergency evacuation devices refer to devices that perform emergency evacuation within the monitoring area, such as access gates, electronic signs, and transportation equipment.

[0106] Emergency control signal refers to the signal that controls the emergency evacuation device to perform emergency evacuation.

[0107] In some embodiments, the emergency supervision management platform can control channel gates and electronic signs based on emergency control signals. At the same time, the emergency supervision management platform can also send corresponding guidance prompt information to the user terminal based on the emergency supervision user platform.

[0108] In some embodiments of this specification, regional monitoring data acquired by monitoring devices deployed in the monitoring area can accurately determine the actual regional congestion risk, enabling real-time and accurate risk perception and early warning. Furthermore, based on the actual regional congestion risk, emergency evacuation parameters are determined, and corresponding emergency control signals are transmitted to emergency evacuation devices deployed in the monitoring area to control the emergency guidance devices to perform personnel evacuation. This can reduce accident rates, improve evacuation efficiency, and significantly enhance public safety benefits.

[0109] Figure 3 is an exemplary schematic diagram of regional congestion risk according to some embodiments of this specification.

[0110] In some embodiments, the emergency supervision management platform 130 may determine the regional tolerance 321 based on the regional specification characteristics 311 and the obstacle distribution data 312 ; and determine the regional congestion risk 330 based on the regional tolerance 321 and the regional monitoring data 322 .

[0111] For more information on regional monitoring data 322 and regional congestion risk 330, please see Figure 2 and its related contents.

[0112] Regional specification characteristics refer to parameters that describe the size and specifications of the monitoring area. In some embodiments, regional specification characteristics include the shape and area of ​​the monitoring area. Regional specification characteristics can be obtained and characterized using a plan view of the monitoring area.

[0113] In some embodiments, the region specification features may be obtained through user input.

[0114] Obstacle distribution data refers to parameters describing the distribution of obstacles in an area. In some embodiments, the obstacle distribution data includes the sizes of multiple obstacles in the monitoring area and the location coordinates of the obstacles.

[0115] In some embodiments, the emergency supervision management platform can determine obstacle distribution data based on the monitoring image data in the regional monitoring data. For example, the emergency supervision management platform can use an image recognition algorithm or image recognition model to identify the monitoring image data in the regional monitoring data, thereby obtaining obstacle distribution data. For more information about image recognition algorithms or image recognition models, please refer to Figure 2 and its related descriptions.

[0116] Regional tolerance is a parameter that measures an area's ability to withstand the risk of congestion. In some embodiments, the greater the regional tolerance of an area, the more likely it is to be congested. In some embodiments, for areas with the same number of people, a greater regional tolerance indicates greater congestion.

[0117] The emergency supervision and management platform can determine the regional tolerance based on regional specification characteristics and obstacle distribution data. In some embodiments, the emergency supervision and management platform can construct a tolerance feature vector based on regional specification characteristics, obstacle distribution data, and regional type, and search the vector database based on the tolerance feature vector to determine the regional tolerance. Among them, the regional type refers to the type of a certain area in the monitoring area, such as the waiting area or security inspection area of ​​a railway station. The vector database contains multiple sets of reference tolerance feature vectors and their corresponding reference regional tolerances. The vector database can be constructed based on historical data or experimental data.

[0118] For example, the emergency supervision and management platform can use historical data (such as data extracted from existing smart city construction cases such as subway stations, shopping malls, and train stations) or experimental data on regional specifications, obstacle distribution data, and regional types as reference tolerance feature vectors. Based on the actual congestion situation (such as evacuation time and number of complaints), crowd density, and crowd density change rate in the historical / experimental data, the platform normalizes these data and then weights them to generate the corresponding regional tolerance. The weighted weights are preset.

[0119] The emergency supervision and management platform can determine regional congestion risks in a variety of ways based on regional tolerance and regional monitoring data.

[0120] In some embodiments, the emergency supervision and management platform can determine the regional congestion risk by querying a preset congestion risk table based on regional tolerance and regional monitoring data. The preset congestion risk table can be preset based on historical data or experience.

[0121] In some embodiments, the greater the population density and the number of target clusters in the regional monitoring data corresponding to the monitoring area, the lower the regional tolerance, and the greater the risk of regional congestion. Among them, the target cluster refers to the cluster whose cluster density is greater than the density threshold, and the density threshold is set based on experience. For more information about cluster density, please refer to Figure 2 and its related descriptions.

[0122] In some embodiments, the emergency supervision and management platform can determine regional personnel characteristics based on regional monitoring data; and determine regional congestion risks based on regional personnel characteristics, regional tolerance, and regional monitoring data.

[0123] Regional population characteristics are parameters used to describe the characteristics of people in an area. In some embodiments, regional population characteristics include the age distribution of people in the area, the number and location of special groups, and the number and location of people with luggage. Special groups include people with mobility impairments, pregnant women, and others.

[0124] In some embodiments, the emergency supervision and management platform can identify and obtain regional personnel characteristics based on regional monitoring data through image recognition algorithms or image recognition models. For more descriptions of image recognition algorithms or image recognition models, please refer to Figure 2 and its related descriptions.

[0125] The emergency supervision and management platform can determine regional congestion risk based on regional personnel characteristics, regional tolerance, and regional monitoring data. In some embodiments, the emergency supervision and management platform can query a correction table based on regional personnel characteristics to determine first correction data, and query a preset congestion risk table based on regional tolerance and regional monitoring data to determine an initial regional congestion risk. The regional congestion risk is calculated as follows: Regional congestion risk = first correction data × initial regional congestion risk, where the initial regional risk is the regional congestion risk before correction.

[0126] The first correction data includes a first correction amplitude. The first correction amplitude refers to the coefficient for correcting the initial regional risk. The correction table includes the age distribution of regional personnel, the proportion of special populations, and their corresponding correction amplitudes. The correction table can be constructed based on historical data or experimental data. For example, the higher the proportion of elderly people and the proportion of special populations in the age distribution of regional personnel, the greater the correction amplitude, and the greater the corrected regional congestion risk. In some embodiments, the correction amplitude is greater than 1.

[0127] In some embodiments of the present specification, the regional congestion risk is appropriately modified by considering the characteristics of the people in the area, so that the determined regional congestion risk is more in line with the actual situation and more accurate.

[0128] In some embodiments, the emergency supervision management platform can determine the estimated pedestrian flow data at a future time point based on regional monitoring data, regional specification characteristics, and external environment data through a feature prediction model; determine the estimated risk data based on the estimated pedestrian flow data; and determine the updated regional congestion risk based on the estimated risk data and regional tolerance.

[0129] 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 may include rainfall, temperature, weather type, etc. in a certain area.

[0130] In some embodiments, external environment data can be obtained through a third-party platform.

[0131] Estimated traffic flow data is the traffic flow characteristics of a certain area at a future time point. For more information about traffic flow characteristics, see Figure 2 and its related descriptions.

[0132] In some embodiments, the emergency supervision and management platform can determine the estimated pedestrian flow data at a future time point through a feature prediction model based on regional monitoring data, regional specification characteristics, and external environmental data.

[0133] A feature prediction model is a model used to estimate foot traffic data at future points in time. A feature prediction model is a machine learning model. For example, a feature prediction model may include a combination of one or more deep neural network (DNN) models or other custom models.

[0134] The input of the feature prediction model includes regional monitoring data, regional specification characteristics, and external environment data, and the output is the estimated pedestrian flow data at future time points.

[0135] In some embodiments, the emergency supervision and management platform can determine estimated pedestrian flow data at future points in time using a feature prediction model based on regional personnel characteristics, regional monitoring data, regional specification characteristics, and external environmental data. For more information on regional personnel characteristics, please refer to the relevant description above.

[0136] In some embodiments of this specification, the activities of people in different areas are different. By considering the characteristics of people in the current area, the estimated flow of people at a determined future time point can be made more accurate.

[0137] In some embodiments, a feature prediction model can be obtained by training an initial feature prediction model using multiple sets of first training samples with first labels. The first training samples may include sample area monitoring data, sample area specification features, and sample external environment data for the sample area at a first historical time point. The first label may include actual pedestrian flow characteristics of the sample area at a second historical time point under the first training sample. The first historical time point precedes the second historical time point. The sample area may include one or more sample monitoring areas.

[0138] In some embodiments, the first training sample and the first label may be obtained based on historical data.

[0139] In some embodiments, the emergency supervision management platform can input multiple first training samples with first labels into the initial feature prediction model, construct a loss function based on the first labels and the results of the initial feature prediction model, and iteratively update the parameters of the initial feature prediction model based on the loss function through gradient descent or other methods. When the preset conditions are met, the model training is completed and a trained feature prediction model is obtained. The preset conditions may include convergence of the loss function, the number of iterations reaching a threshold, etc.

[0140] Estimated risk data is data used to describe the regional congestion risk of a certain area at a future time point.

[0141] In some embodiments, the emergency supervision and management platform can determine the regional congestion risk at a future time point based on the pedestrian flow data at a future time point, and use the regional congestion risk at the future time point as the estimated risk data. For more information on how to determine regional congestion risk based on pedestrian flow data, please see Figure 2 Step 220 and its related description.

[0142] In some embodiments, the emergency supervision and management platform can determine the updated regional congestion risk based on the estimated risk data and regional tolerance. For example, the emergency supervision and management platform obtains the risk growth rate based on the difference between the estimated risk data and the current regional congestion risk. When the risk growth rate exceeds the risk threshold, the regional congestion risk is determined based on the regional personnel characteristics, regional tolerance, and regional monitoring data. The second correction data is determined based on the risk growth rate, and the updated regional congestion risk is determined according to the updated regional congestion risk = second correction data × regional congestion risk. The second correction data includes a second correction rate, which refers to the coefficient for correcting the regional congestion risk. For more information on how to determine the regional congestion risk based on regional personnel characteristics, regional tolerance, and regional monitoring data, please refer to the relevant description above.

[0143] Among them, the risk growth rate is positively correlated with the revised data, and the risk threshold is preset based on experience.

[0144] In some embodiments of this specification, by considering passenger flow data and risk data at future time points, the accuracy of regional congestion risk warning is improved and the allocation of management and control resources is optimized.

[0145] In some embodiments of this specification, by comprehensively analyzing the physical properties of the area, the distribution of obstacles and real-time monitoring data, the regional carrying capacity threshold and risk level are dynamically quantified, and accurate prediction and graded warning of crowd congestion risks are achieved, effectively improving the scientific nature and risk prediction capabilities of public space safety management.

[0146] Figure 4 This is an exemplary schematic diagram of determining emergency evacuation parameters according to some embodiments of this specification.

[0147] In some embodiments, the emergency supervision management platform is further configured to: obtain candidate emergency parameters 410; based on the candidate emergency parameters 410, regional congestion risk 420, and regional specification characteristics 430, determine the diversion risk data 450 corresponding to the candidate emergency parameters 410 through the diversion prediction model 440; the diversion prediction model 440 is a machine learning model; based on the diversion risk data 450, determine the emergency diversion parameters 460.

[0148] Candidate emergency parameters refer to candidate emergency evacuation parameters.

[0149] In some embodiments, the emergency supervision management platform may determine the parameter range of the emergency evacuation parameters of the monitoring area according to the regional congestion risk of the monitoring area, and randomly generate candidate emergency parameters within the parameter range.

[0150] For example, different candidate emergency parameters can be entrance and exit gate opening intervals adjusted at different amplitudes, and different evacuation routes generated based on different evacuation directions. The parameter ranges of emergency evacuation parameters corresponding to different regional congestion risks are different. For example, the greater the regional congestion risk, the shorter the corresponding entrance gate opening interval, the longer the exit gate opening interval, and the more corresponding evacuation directions and / or evacuation routes. The evacuation destination is a monitoring area with a smaller regional congestion risk (e.g., smaller than the regional congestion risk of the departure point) and a higher regional similarity with the departure point (e.g., the regional similarity is higher than a preset threshold).

[0151] In some embodiments, the planning of the evacuation route can be determined based on the comprehensive regional congestion risk of the monitoring area of ​​the entire site. For example, the evacuation route can be based on the monitoring area with high regional congestion risk as the starting point and the monitoring area with low regional congestion risk as the destination. The regional congestion risk of the monitoring area passed through is preferably not higher than that of the starting point. Based on Dijkstra, Algorithms and other path planning algorithms are used to comprehensively plan monitoring areas with high congestion risks in various areas.

[0152] Regional specification features are features used to describe the physical spatial attributes of the monitoring area, for example, the size of the monitoring area.

[0153] The diversion prediction model is a model used to determine diversion risk data corresponding to the candidate emergency parameters. In some embodiments, the diversion prediction model is a machine learning model, such as a deep neural network (DNN) model.

[0154] The inputs of the diversion prediction model may include candidate emergency parameters, current and historical regional congestion risks of the monitoring area, regional specification characteristics, current and historical regional monitoring data, current and historical pedestrian flow characteristics, and emergency device data. For more information on regional congestion risks, regional monitoring data, and pedestrian flow characteristics, please refer to the above Figure 2 Related content.

[0155] Emergency device data refers to data related to emergency evacuation devices, such as the type, quantity, and distribution of emergency evacuation devices in the monitoring area.

[0156] The output of the diversion prediction model may include diversion risk data corresponding to the candidate emergency parameters.

[0157] The evacuation risk data refers to the regional congestion risk of the monitoring area at a future time point, assuming that the candidate emergency parameters are used to evacuate people in the monitoring area.

[0158] In some embodiments, the input of the diversion prediction model also includes regional personnel characteristics.

[0159] For more information on regional personnel characteristics, please refer to the above Figure 3 Related content.

[0160] By incorporating regional demographic characteristics, the evacuation prediction model can more accurately capture the dynamics and diversity of crowd behavior, thereby generating more scientific emergency evacuation parameters. This synergistic effect of multi-dimensional input not only improves prediction accuracy but also enhances the system's adaptability to complex scenarios, providing strong technical support for urban emergency management.

[0161] The training method of the grooming prediction 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 Related content.

[0162] In some embodiments, the second training sample and the second label can be obtained based on historical data.

[0163] In some embodiments, the second training sample includes sample emergency parameters, regional congestion risk of the sample area at a first time point, regional congestion risk at a second time point, regional specification characteristics of the sample area, regional monitoring data of the sample area at a first time point, regional monitoring data at a second time point, pedestrian flow characteristics of the sample area at a first time point, pedestrian flow characteristics at a second time point, and emergency device data of the sample area.

[0164] 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 regional monitoring data of the sample area at the third time point. 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.

[0165] In some embodiments, the emergency supervision management platform may use candidate emergency parameters whose corresponding evacuation risk data is less than a second risk threshold as emergency evacuation parameters.

[0166] In some embodiments, the emergency supervision management platform may also use the candidate emergency parameter with the smallest corresponding evacuation risk data as the emergency evacuation parameter.

[0167] In some embodiments, the future time point may include multiple future time points. The emergency supervision management platform may perform weighted calculation on the regional congestion risks of all future time points contained in the diversion risk data, and take the candidate emergency parameter corresponding to the diversion risk data with the smallest weighted value as the emergency diversion parameter, where the closer the future time point is to the current time point, the greater the weight of its regional congestion risk.

[0168] In some embodiments of this specification, a pre-estimated emergency response model, based on historical parameters, can quickly identify high-value options from these historical parameters, improving decision-making efficiency. Furthermore, the use of a pre-estimated emergency response model improves the accuracy of risk prediction and enables precise risk prevention and control.

[0169] 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 this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0170] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0171] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this 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 an existing server or mobile device.

[0172] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0173] In some embodiments, numbers describing the quantity of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may vary according to the required features of the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0174] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This excludes any application history documents that are inconsistent with or conflicting with the content of this specification, as well as any documents (currently or subsequently appended to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification shall prevail.

[0175] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. The smart city crowd management system based on the IoT model is characterized by: The system includes an emergency supervision and management platform, which is configured to: Based on the emergency supervision perception control platform, regional monitoring data is obtained through monitoring devices deployed in the monitoring area; Determining regional congestion risk based on the regional monitoring data; In response to the congestion risk in the area meeting the diversion conditions: Determining emergency evacuation parameters based on the regional congestion risk, wherein the emergency evacuation parameters include traffic control parameters and traffic guidance parameters; Based on the emergency evacuation parameters, an emergency control signal is transmitted to the emergency evacuation device deployed in the monitoring area through the emergency supervision sensor network platform to control the opening interval of the channel gate based on the passage control parameters, and to control the display content of the electronic sign based on the passage guidance parameters, wherein the display content includes at least one of the display color, evacuation direction and evacuation route.

2. The system according to claim 1, wherein: The emergency supervision management platform is further configured to: Determine the regional tolerance based on regional specifications and obstacle distribution data; The congestion risk of the area is determined based on the area tolerance and the area monitoring data.

3. The system according to claim 1, wherein: The emergency supervision management platform is further configured to: Based on the regional monitoring data, the regional specification characteristics, and the external environment data, the estimated pedestrian flow data at a future time point is determined by a feature prediction model; the feature prediction model is a machine learning model; Determining estimated risk data based on the estimated pedestrian flow data; An updated regional congestion risk is determined based on the estimated risk data and the regional tolerance.

4. The system according to claim 1, wherein: The emergency supervision management platform is further configured to: Determining similar areas of the monitoring area based on the area function data, the area layout characteristics, and the area object data; The emergency evacuation parameters are determined based on the similar areas and the congestion risk of the areas.

5. The crowd management method for smart cities based on the IoT model is characterized by: The method is executed by an emergency supervision and management platform for crowd management in a smart city based on a large-scale model of the Internet of Things, and includes: Based on the emergency supervision perception control platform, regional monitoring data is obtained through monitoring devices deployed in the monitoring area; Determining regional congestion risk based on the regional monitoring data; In response to the congestion risk in the area meeting the diversion conditions: Determining emergency evacuation parameters based on the regional congestion risk, wherein the emergency evacuation parameters include traffic control parameters and traffic guidance parameters; Based on the emergency evacuation parameters, an emergency control signal is transmitted to the emergency evacuation device deployed in the monitoring area through the emergency supervision sensor network platform to control the opening interval of the channel gate based on the passage control parameters, and to control the display content of the electronic sign based on the passage guidance parameters, wherein the display content includes at least one of the display color, evacuation direction and evacuation route.

6. The method according to claim 5, wherein: Determining the regional congestion risk based on the regional monitoring data includes: Determine the regional tolerance based on regional specifications and obstacle distribution data; The congestion risk of the area is determined based on the area tolerance and the area monitoring data.

7. The method according to claim 6, wherein: The method further comprises: Based on the regional monitoring data, the regional specification characteristics, and the external environment data, the estimated pedestrian flow data at a future time point is determined by a feature prediction model; the feature prediction model is a machine learning model; Determining estimated risk data based on the estimated pedestrian flow data; An updated regional congestion risk is determined based on the estimated risk data and the regional tolerance.

8. The method according to claim 5, wherein: Determining emergency evacuation parameters based on the regional congestion risk includes: Determining similar areas of the monitoring area based on the area function data, the area layout characteristics, and the area object data; The emergency evacuation parameters are determined based on the similar areas and the congestion risk of the areas.

9. A smart city crowd management device based on the Internet of Things large model, characterized by: The apparatus comprises at least one processor and at least one memory; The at least one memory is for storing computer instructions; The at least one processor is used to execute at least part of the computer instructions to implement the smart city crowd evacuation method based on the Internet of Things large model as described in claim 5.

10. A computer-readable storage medium, characterized in that: The storage medium stores computer instructions. When the computer reads the computer instructions in the storage medium, the computer executes the smart city crowd guidance method based on the Internet of Things large model as described in claim 5.

Images