Smart city hierarchical emergency supervision method, system and medium based on Internet of Things big model

Abstract

The present invention provides a smart city hierarchical emergency supervision method, system, and medium based on a large model of the Internet of Things. The method includes: obtaining regional information and emergency supervision data of a target management area corresponding to a lower-level management platform; based on the regional information, determining a first weight factor corresponding to each type of emergency supervision sub-data in the target management area; based on the first weight factor, determining the degree of processing of each type of emergency supervision sub-data in the lower-level management platform, and determining the risk level of the target management area; based on the processing degree of each type of emergency supervision sub-data, controlling the lower-level management platform to process the emergency supervision data; based on the risk level, determining patrol parameters of patrol equipment in the target management area; based on the patrol parameters, controlling the patrol equipment to patrol at a patrol frequency on the patrol path. This method can accurately and effectively improve the response speed to urgent and important emergency events.

Description

Technical Field

[0001] The present invention relates to the technical field of smart city emergency supervision, and in particular to a smart city hierarchical emergency supervision method, system and medium based on an Internet of Things large model. Background Art

[0002] With the development of smart cities, urban emergency management also needs to be gradually improved. However, faced with a large amount of emergency supervision data from different sources, how to determine the emergency processing priority of emergency supervision data and adjust the processing level of emergency supervision data accordingly are issues that need to be addressed.

[0003] Therefore, a smart city hierarchical emergency supervision method, system and medium based on the Internet of Things big model are provided, which can accurately and effectively improve the response speed to urgent and important emergency events. Summary of the Invention

[0004] One or more embodiments of the present invention provide a hierarchical emergency supervision method for smart cities based on a large model of the Internet of Things. The method is implemented through a hierarchical emergency supervision system for smart cities based on a large model of the Internet of Things. The system includes: an emergency supervision user platform, an emergency supervision service platform, an emergency supervision management platform, an emergency supervision sensor network platform and an emergency supervision object platform, wherein the emergency supervision management platform includes a lower-level management platform and an upper-level management platform, wherein each of the lower-level management platforms corresponds to one or more target management areas; the emergency supervision object platform includes patrol equipment. The method is executed based on the upper-level management platform, and the method includes: obtaining regional information and emergency supervision data of the target management area corresponding to the lower-level management platform, the regional information including at least one of environmental information, production information and life information, and the emergency supervision data including at least one emergency supervision sub-data, and one emergency supervision sub-data corresponding to one risk type; based on the regional information, determining a first weight factor corresponding to each emergency supervision sub-data in the at least one emergency supervision sub-data in the target management area; the first weight factor represents the importance of the corresponding emergency supervision sub-data in the target management area; based on the first weight factor, determining the processing degree of each emergency supervision sub-data in the lower-level management platform, and determining the risk level of the target management area; based on the processing degree of each emergency supervision sub-data, controlling the lower-level management platform to process the emergency supervision data; based on the risk level, determining patrol parameters of the patrol equipment in the target management area, the patrol parameters including patrol path and patrol frequency; based on the patrol parameters, controlling the patrol equipment to patrol on the patrol path at the patrol frequency.

[0005] One or more embodiments of the present invention provide a smart city hierarchical emergency supervision system based on a large model of the Internet of Things, the system including an emergency supervision user platform, an emergency supervision service platform, an emergency supervision management platform, an emergency supervision sensor network platform and an emergency supervision object platform; the emergency supervision user platform includes a user terminal, the emergency supervision service platform includes a communication terminal, the emergency supervision management platform includes a subordinate management platform and an upper management platform, wherein each of the subordinate management platforms corresponds to one or more target management areas; the emergency supervision object platform includes patrol equipment, and the upper management platform is configured to execute the above-mentioned smart city hierarchical emergency supervision method based on the large model of the Internet of Things.

[0006] One or more embodiments of the present invention provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the above-mentioned smart city hierarchical emergency supervision method based on the Internet of Things big model.

[0007] Beneficial effects: The technical solution of the present application can, based on the type of emergency supervision data and in combination with the regional information of the target management area, more comprehensively determine the degree of impact of different types of risks within the target management area by combining various factors, and further determine the importance of different types of emergency supervision data, so that the lower-level management platform can process the less important emergency supervision sub-data in detail, while the more important emergency supervision sub-data can be simply processed or directly uploaded to the upper-level management platform for processing. This can save the computing resources of the lower-level management platform and enable the upper-level management platform to coordinate the risk levels of various management areas, so as to more reasonably arrange security monitoring patrols and avoid the occurrence of actual risks. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0009] Figure 1 2. It is a schematic diagram of the platform structure of a smart city hierarchical emergency supervision system based on an Internet of Things large model according to some embodiments of the present invention;

[0010] Figure 2 is an exemplary flow chart of a hierarchical emergency supervision method for a smart city based on an Internet of Things large model according to some embodiments of the present invention;

[0011] Figure 3 is an exemplary schematic diagram of determining a processing degree according to some embodiments of the present invention;

[0012] Figure 4is an exemplary flow chart of patrol control according to some embodiments of the present invention. DETAILED DESCRIPTION

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

[0014] Figure 1 It is a platform structure diagram of a smart city hierarchical emergency supervision system based on an Internet of Things large model according to some embodiments of the present invention.

[0015] In some embodiments, as Figure 1 As shown, the smart city hierarchical emergency supervision system 100 based on the Internet of Things big model includes an emergency supervision user platform 110, an emergency supervision service platform 120, an emergency supervision management platform 130, an emergency supervision sensor network platform 140 and an emergency supervision object platform 150.

[0016] The emergency supervision user platform refers to the platform for superior departments to comprehensively coordinate emergency supervision.

[0017] In some embodiments, the emergency supervision user platform includes a user terminal.

[0018] A user terminal refers to an external terminal device or system software. For example, a user terminal can be a mobile device, a computer, or any combination thereof, of other devices with input and / or output functions.

[0019] The emergency supervision service platform refers to an interactive service platform that receives and transmits emergency supervision data.

[0020] In some embodiments, the emergency supervision service platform interacts with the emergency supervision user platform upward and with the emergency supervision management platform downward.

[0021] In some embodiments, the emergency supervision service platform includes a communication terminal.

[0022] A communication terminal refers to a device or software that enables real-time information exchange. For example, a communication terminal can be a wireless phone, a video monitor, a multimedia computer, etc.

[0023] The emergency supervision management platform refers to a comprehensive platform for processing and managing emergency supervision data.

[0024] In some embodiments, the emergency supervision management platform includes multiple lower-level management platforms and an upper-level management platform 131 .

[0025] The subordinate management platform refers to the platform for storing and processing regional information and emergency supervision data.

[0026] In some embodiments, each lower-level management platform may correspond to one or more target management areas.

[0027] The target management area refers to the corresponding management area of ​​the lower-level management platform that currently processes data / information.

[0028] The superior management platform refers to a comprehensive platform that coordinates the storage and processing of data / information uploaded by the subordinate management platform.

[0029] In some embodiments, the upper-level management platform can interact with multiple lower-level management platforms, such as lower-level management platform 1, lower-level management platform 2, ..., lower-level management platform n, which interact with the upper-level management platform respectively.

[0030] Emergency supervision sensor network platform refers to a platform that transmits emergency supervision related sensor data or information.

[0031] In some embodiments, the emergency supervision sensor network platform interacts upward with multiple subordinate management platforms in the emergency supervision management platform, and interacts downward with the emergency supervision object platform.

[0032] In some embodiments, the emergency monitoring sensor network platform includes communication devices such as routing gateways.

[0033] The emergency supervision object platform refers to the platform for collecting emergency supervision data and implementing execution instructions.

[0034] In some embodiments, the emergency supervision object platform includes patrol equipment.

[0035] Patrol equipment includes both manned and unmanned patrol equipment. Unmanned patrol equipment refers to unmanned patrol vehicles and drones that replace human patrols and perform routine tasks. Routine tasks include capturing images. For example, images can be taken to determine whether a fire or flood has occurred.

[0036] In some embodiments, routine items can be executed by a monitoring device configured on the unmanned patrol device. For example, the monitoring device can include a data acquisition device, a sensor, etc.

[0037] For more detailed information on the smart city hierarchical emergency supervision system based on the IoT big model and its implementation method of the smart city hierarchical emergency supervision method based on the IoT big model, please refer to Figures 2 to 4 Related description.

[0038] In some embodiments of the present invention, a smart city hierarchical emergency supervision system based on the Internet of Things big model can form an information operation closed loop between various functional platforms, operate in a coordinated and regular manner, and improve the processing efficiency of emergency scenarios by dynamically adjusting the processing level of emergency supervision data efficiently and accurately.

[0039] Figure 2 This is an exemplary flow chart of a hierarchical emergency supervision method for a smart city based on an Internet of Things model according to some embodiments of the present invention. Figure 2 As shown, the process 200 of the smart city hierarchical emergency supervision method based on the Internet of Things big model includes the following steps. In some embodiments, the process 200 of the smart city hierarchical emergency supervision method based on the Internet of Things big model can be executed by the upper-level management platform 131.

[0040] Step 210: Acquire the regional information and emergency supervision data of the target management area corresponding to the lower-level management platform.

[0041] For more information about the target management area, please refer to the present invention Figure 1 Related description.

[0042] The regional information refers to relevant information of the target management area. In some embodiments, the regional information includes at least one of environmental information, production information and life information.

[0043] Environmental information can reflect the sum of various data, information and conditions of the natural environment and ecosystem within the target management area.

[0044] In some embodiments, the environmental information includes the natural geographical conditions, climate characteristics, natural resource conditions, ecosystem types, and environmental quality within the target management area.

[0045] In some embodiments, production information includes industry-related information, agriculture-related information, service-related information, etc. For example, industry-related information may include information such as factory type, number of factories, and factory scale; agriculture-related information may include information such as type of crops planted and area of ​​crop planted; and service-related information may include information such as type of restaurants and number of tourism enterprises.

[0046] Life information refers to information related to the lives of residents in the management area.

[0047] In some embodiments, life information includes population information, residence information, consumption information, etc.

[0048] In some embodiments, the upper-level management platform may obtain the regional information within the management area in various ways, for example, through a third-party website, system, or platform.

[0049] In some embodiments, the upper-level management platform may also obtain the regional information from the database of the lower-level management platform via the network.

[0050] Emergency supervision data refers to data related to emergency prevention and control, such as water conservancy data and temperature data. Emergency supervision data includes at least one type of emergency supervision sub-data, and each type of emergency supervision sub-data corresponds to a risk type.

[0051] Risk type refers to the type of risk that may exist in the management area, such as flood risk, fire risk, high temperature risk, strong wind risk, production risk, etc.

[0052] Emergency supervision sub-data refers to sub-data of emergency supervision data divided according to risk type. For example, emergency supervision sub-data corresponding to flood risk and emergency supervision sub-data corresponding to fire risk.

[0053] In some embodiments, the emergency supervision data may include multiple emergency supervision sub-data.

[0054] The superior management platform can obtain emergency supervision data in a variety of ways, for example, obtaining emergency supervision data from the database of the subordinate management platform.

[0055] Step 220 : Determine, based on the regional information, a first weight factor corresponding to each type of emergency supervision sub-data in the at least one type of emergency supervision sub-data in the target management area.

[0056] The first weight factor represents the importance of the corresponding emergency supervision sub-data in the target management area.

[0057] In some embodiments, the first weight factor may be represented by a value between 0 and 1, where a larger value indicates a higher degree of importance.

[0058] In some embodiments, the upper-level management platform may determine the first weight factor through a first preset table.

[0059] The first preset table reflects the first weight factors corresponding to various types of environmental information, production information, life information, and emergency supervision data. The superior management platform can determine the first weight factor by querying the first preset table based on the types of environmental information, production information, life information, and emergency supervision data. For example, the type of emergency supervision data is fire risk, the environmental information shows that the forest coverage rate is 60%, the production information shows that there are multiple chemical plants in the management area, and the life information shows that the population density is relatively high. By querying the first preset table, it is determined that the first weight factor of the emergency supervision sub-data corresponding to the fire risk type is 0.9.

[0060] In some embodiments, the first preset table can be set by a technician based on experience or historical data.

[0061] In some embodiments, the upper management platform determines the first weight factor corresponding to each emergency supervision sub-data in at least one emergency supervision sub-data in the target management area based on regional information, including: determining the first weight factor corresponding to each emergency supervision sub-data in at least one emergency supervision sub-data in the target management area based on regional information of the target management area and regional information of associated management areas of the target management area.

[0062] The associated management area refers to an area within a preset range of the boundary distance from the target management area. In some embodiments, the preset range can be set by a technician based on experience and the surrounding terrain conditions of the target management area.

[0063] For example, the preset range may be 100 km.

[0064] In some embodiments, the associated management area also includes regional information and emergency supervision data. The regional information and emergency supervision data of the associated management area are similar to the regional information and emergency supervision data of the target management area. For specific instructions, refer to the relevant description of the regional information and emergency supervision data of the target management area.

[0065] In some embodiments, the upper-level management platform may construct a risk association map and a graph model to determine the first weight factor corresponding to each emergency supervision sub-data in the target management area.

[0066] A risk association map is a map used to reflect the impact relationship between various risk types in geographically adjacent management areas, and is composed of nodes and edges.

[0067] The nodes of the risk association map can be management areas, and the node characteristics can include environmental information, production information, and life information within the management area.

[0068] The edges of the risk association graph may include directed edges connecting geographically adjacent management areas. The direction of the directed edge indicates the direction of the risk impact between the management area and its adjacent management areas. If there is a risk impact between two adjacent management areas, there may be two directed edges. For example, if management area A and management area B are adjacent management areas, and the fire risks of management areas A and management area B are bidirectional, such as a risk accident such as a fire in management area A will spread to management area B, and a risk accident such as a fire in management area B will spread to management area A, then management area A and management area B will have two directed edges pointing in opposite directions.

[0069] The edge feature of each directed edge in the risk association graph may be the risk propagation degree of each risk type in its corresponding direction.

[0070] Risk propagation refers to the degree of influence of risk types between adjacent management areas. For example, if there is a flood risk in adjacent management area B of management area A, and multiple rivers flow from management area B to management area A, the flood risk of management area B will have a higher propagation degree on management area A.

[0071] In some embodiments, the risk propagation degrees in two directions between two nodes may be different. For example, in the above example, the risk propagation degree of flood risk in management area B to management area A is higher, but the risk propagation degree of flood risk in management area A to management area B is lower.

[0072] In some embodiments, the risk spread degree may be preset by a technician based on historical data.

[0073] In some embodiments, the first weight factor is further related to the risk propagation degree between the target management area and the associated management area, where the risk propagation degree includes at least one sub-propagation degree, and one sub-propagation degree corresponds to one risk type.

[0074] In some embodiments, the risk propagation degree is determined based on processing of propagation-related information and risk types by a risk propagation model, and the risk propagation model is a machine learning model.

[0075] The sub-propagation degree refers to the propagation degree of the risk propagation degree divided according to the risk type. For example, the sub-propagation degree can be the flood risk propagation degree or the fire risk propagation degree.

[0076] Diffusion-related information refers to factors related to the spread of risks from one management area to another.

[0077] In some embodiments, different risk types correspond to different propagation-related information. For example, for water risk, the propagation-related information may include the topography and river paths between adjacent management areas; for fire risk, the propagation-related information may include the wind direction and the distribution of combustibles (e.g., jungle, buildings, etc.) between adjacent management areas; and for power risk, the propagation-related information may include the distribution of power grids between adjacent management areas.

[0078] The risk propagation model is a model used to determine the degree of risk propagation. In some embodiments, the risk propagation model can be various machine learning models, such as a convolutional neural network (CNN) model.

[0079] In some embodiments, the input of the risk propagation model may include propagation-related information and risk types, and the output may be sub-propagation degrees corresponding to each input risk type. The sub-propagation degrees may include the sub-propagation degrees of the target management area to the associated management area, and the sub-propagation degrees of the associated management area to the target management area.

[0080] In some embodiments, the risk propagation model can be trained and acquired through various methods. For example, it can be acquired through training using multiple training samples with training labels. The training samples can include information related to sample propagation and the sample risk types corresponding to adjacent sample management areas. The training labels corresponding to the training samples are the sub-propagation degrees corresponding to the risk types corresponding to the adjacent sample management areas.

[0081] In some embodiments, the upper-level management platform can determine, based on historical data, the sample propagation-related information and sample risk types used in training, as well as the sample risk propagation degrees corresponding to the training samples. The upper-level management platform can determine, as the label corresponding to the training sample, the actual sub-propagation degree when a risk incident of the corresponding risk type actually occurred in an adjacent sample management area in the historical data.

[0082] In some embodiments, the actual sub-propagation degree can be determined based on the risk level and propagation direction of the risk incidents that actually occurred in adjacent sample management areas. For example, in historical data, if a magnitude 3 earthquake occurred in management area A, and a magnitude 2 earthquake affected the adjacent management area B, then the actual sub-propagation degree of the earthquake from management area A to management area B could be 2 / 3.

[0083] In some embodiments, the upper-level management platform can input sample propagation-related information and sample risk types into the initial risk propagation model, construct a loss function based on the sub-propagation degree output by the initial risk propagation model and the training labels, and update the initial risk propagation model based on the loss function. When the training end condition is met, the initial risk propagation model training is completed, resulting in a trained risk propagation model. The training end condition may be when the loss function converges or the number of iterations reaches a threshold, etc.

[0084] In some embodiments, the superior management platform may use the set of sub-propagation degrees corresponding to each risk type between the target management area and the associated management area as the risk propagation degree between the target management area and the associated management area, and determine the edge characteristics of the corresponding edges in the risk association map based on the risk propagation degree between the target management area and the associated management area, and then determine the first weight factor corresponding to each emergency supervision sub-data in the target management area based on the processing of the risk association map by the graph model.

[0085] The graph model refers to a model used to determine the first weight factor. In some embodiments, the graph model may be a graph neural network (GNN) model.

[0086] In some embodiments, the input of the graph model may include a risk association graph and risk types corresponding to the emergency supervision sub-data, and the output may be a first weight factor corresponding to each emergency supervision sub-data.

[0087] In some embodiments, the graph model can be acquired through various training methods. For example, it can be acquired by training multiple training samples with training labels. The training samples can include a sample risk association graph and a sample risk type corresponding to the sample emergency supervision sub-data. The training label corresponding to the training sample is the first weighting factor corresponding to the sample emergency supervision sub-data.

[0088] In some embodiments, the upper-level management platform can determine the sample risk types corresponding to the multiple sample risk association maps and sample emergency supervision sub-data used in training based on historical data, and determine the first weighting factors of the sample emergency supervision sub-data corresponding to the corresponding sample risk types based on the actual number of occurrences and risk levels of risk accidents of various risk types in each management area in the historical data. For example, the first weighting factor is positively correlated with the actual number of occurrences and risk level.

[0089] The training method of the graph model is similar to that of the risk propagation model. For details about the training method of the graph model, please refer to the relevant description of the training method of the risk propagation model mentioned above.

[0090] According to some embodiments of the present invention, based on the propagation-related information and the risk type, the risk propagation model is used to calculate and obtain the sub-propagation degree corresponding to each risk type, so that the first weight factor can be determined more accurately.

[0091] According to some embodiments of the present invention, determining the first weight factor corresponding to the risk type in combination with the associated management areas adjacent to the target management area can more comprehensively consider the risks brought to the target management area by the adjacent management areas, rather than just considering the risk factors of the target management area itself, thereby making the calculation of the first weight factor more accurate.

[0092] Step 230: Based on the first weight factor, determine the processing degree of each emergency supervision sub-data in the lower-level management platform, and determine the risk level of the target management area.

[0093] Different processing degrees represent different ways in which the subordinate management platform handles emergency supervision sub-data.

[0094] In some embodiments, different letters can be used to represent different levels of processing, for example, letters A, B, and C represent different levels of processing. For example, processing level A means that the emergency supervision sub-data is not processed and is directly uploaded to the upper-level management platform; processing level B means that the emergency supervision sub-data is pre-processed (for example, filtering the data); and processing level C means that the emergency supervision sub-data is processed in different levels (different levels correspond to different levels of processing details).

[0095] In some embodiments, the upper-level management platform may determine the processing degree based on the first preset relationship and the first weight factor.

[0096] The first preset relationship refers to the relationship between the first weight factor and the degree of processing. For example, the smaller the first weight factor, the less important the data is. In this case, the corresponding emergency supervision sub-data can be processed more carefully on the lower-level management platform, and the corresponding processing results can be transmitted to the upper-level management platform. Conversely, the larger the first weight factor, the more important the data is. The corresponding emergency supervision sub-data can be simply processed or not processed on the lower-level management platform, and uploaded to the upper-level management platform for more detailed processing.

[0097] In some embodiments, the first preset relationship may be set by a technician based on experience.

[0098] Risk level refers to the comprehensive degree to which the target management area is exposed to multiple risks. For example, the comprehensive degree to which the target management area may be exposed to the risks of drought, fire, and high temperature.

[0099] In some embodiments, the upper management platform can perform a weighted summation of the first weight factors of each emergency supervision sub-data in the target management area, and use the weighted summation value as the risk level of the target management area. The weight coefficient of each first weight factor can be preset.

[0100] For more information on how to determine the degree of treatment and risk, see Figure 3 Related description.

[0101] Step 240 : Based on the processing level of each emergency supervision sub-data, control the lower-level management platform to process the emergency supervision data.

[0102] In some embodiments, the upper management platform can feed back the calculated processing degree of each emergency supervision sub-data to the lower management platform, and the lower management platform performs corresponding processing on each emergency supervision sub-data according to the processing degree. The processing method can be referred to the relevant description of step 230.

[0103] Step 250: Determine patrol parameters of the patrol equipment in the target management area based on the risk level.

[0104] For more information on patrol equipment, see Figure 1 Related description.

[0105] Patrol parameters refer to the parameters used by patrol equipment when patrolling the target management area. Patrol parameters can include patrol routes and patrol frequencies.

[0106] The patrol path refers to the route that the patrol equipment takes when patrolling the target management area.

[0107] Patrol frequency refers to the number of times a patrol device patrols the target management area within a unit of time.

[0108] In some embodiments, the superior management platform may determine patrol parameters according to the second preset relationship.

[0109] The second preset relationship refers to the correspondence between the risk level and the patrol path and patrol frequency.

[0110] In some embodiments, the second preset relationship may be set by a technician based on experience.

[0111] In some embodiments, the superior management platform can determine patrol routes based on the level of risk. For example, if the risk level of the target management area is high, the patrol routes can be densely configured, for example, patrolling the main route and branch routes to reduce the probability of risk. If the risk level of the target management area is low, the patrol routes can be sparsely configured, for example, patrolling only the main route to reduce patrol consumption.

[0112] In some embodiments, the higher-level management platform can determine the patrol frequency based on the risk level. For example, if the risk level of the target management area is high, the patrol frequency of the patrol equipment can be increased, for example, to twice a day. If the risk level of the target management area is low, the patrol frequency of the patrol equipment can be reduced, for example, to once every three days or once a week.

[0113] Step 260: Based on the patrol parameters, control the patrol equipment to patrol at the patrol frequency on the patrol path.

[0114] In some embodiments, the upper-level management platform may feed back the patrol parameters to the lower-level management platform, and the lower-level management platform may set the patrol equipment according to the patrol parameters so that the patrol equipment patrols according to the patrol parameters.

[0115] In some embodiments, the superior management platform can directly control the patrol device through the network and automatically update the parameters of the patrol device so that the patrol device patrols according to the patrol parameters.

[0116] According to some embodiments of the present invention, based on the type of emergency supervision data (e.g., water risk, fire risk, etc.), and combined with the regional information of the target management area (e.g., environmental information, production information, and life information), the impact of different types of risks within the target management area can be confirmed more comprehensively by combining various factors. The importance of different types of emergency supervision data can be further confirmed, so that the lower-level management platform can process the less important emergency supervision sub-data in detail, while the more important emergency supervision sub-data can be simply processed or directly uploaded to the upper-level management platform for processing. This can save the computing resources of the lower-level management platform and enable the upper-level management platform to coordinate the risk levels of various management areas, so as to more reasonably arrange security monitoring patrols and avoid the occurrence of actual risks.

[0117] Figure 3 FIG. 1 is a schematic diagram of determining the degree of processing according to some embodiments of the present invention. Figure 3 As shown, determining the processing degree includes the following: In some embodiments, determining the processing degree may be performed by the upper-level management platform 131 .

[0118] In some embodiments, the upper-level management platform determines the degree of processing of each emergency supervision sub-data on the lower-level management platform based on the first weight factor 340, including: determining the degree of processing 350 of each emergency supervision sub-data on the lower-level management platform based on the first weight factor 340 and the second weight factor 330 of each emergency supervision sub-data; wherein, the second weight factor 330 of each emergency supervision sub-data represents the urgency of each emergency supervision sub-data, and the second weight factor 330 of each emergency supervision sub-data is determined based on the processing of the newly collected sub-data 310 corresponding to each emergency supervision sub-data by the weight model 320, and the weight model 320 is a machine learning model.

[0119] The second weight factor reflects the urgency of the corresponding emergency supervision sub-data.

[0120] The urgency of the emergency supervision sub-data refers to the urgency with which the emergency supervision sub-data needs to be processed as soon as possible or the urgency of the corresponding risk situation.

[0121] In some embodiments, the emergency supervision sensor network platform or the emergency supervision object platform may determine the second weight factor based on a weight model.

[0122] The weight model refers to a model used to determine the second weight factor. In some embodiments, the weight model may be a neural network (NN) model.

[0123] In some embodiments, the input of the weight model may include the newly collected sub-data corresponding to each type of emergency supervision sub-data, and the output may be a second weight factor corresponding to the corresponding emergency supervision sub-data.

[0124] Newly collected sub-data refers to data obtained through sampling based on newly collected data. Newly collected sub-data is similar to emergency supervision sub-data, and each newly collected sub-data corresponds to a risk type.

[0125] In some embodiments, the upper-level management platform can obtain new collected sub-data by using the newly collected emergency supervision sub-data under the risk type corresponding to each emergency supervision sub-data as the newly collected data corresponding to the corresponding emergency supervision sub-data, and then sampling the newly collected data. For more information on how to obtain the newly collected sub-data, please refer to the corresponding content below.

[0126] In some embodiments, the weight model can be acquired through various training methods. For example, it can be acquired by training multiple training samples with training labels. The training samples can include newly collected sub-data of the sample and the corresponding second weight factor of the sample. The training label corresponding to the training sample is the actual risk level of the sample.

[0127] In some embodiments, the upper-level management platform can determine the newly collected sub-data corresponding to multiple sample emergency supervision sub-data used for training based on historical data, and determine the labels corresponding to the training samples based on the severity of the actual risk accidents corresponding to the newly collected sub-data corresponding to the sample emergency supervision sub-data in the historical data. For example, the more serious the actual risk accident, the larger the label value.

[0128] The training method of the weight model is similar to that of the risk propagation model. For the training method of the weight model, please refer to the relevant description of the training method of the aforementioned risk propagation model.

[0129] In some embodiments, the upper-level management platform may determine the processing degree of the emergency supervision sub-data based on the second preset table.

[0130] The second preset table is a table reflecting the relationship between the first weight factor, the second weight factor, and the processing degree. The upper management platform can determine the processing degree of the corresponding emergency supervision sub-data by querying the second preset table based on the values ​​of the first weight factor and the second weight factor of the emergency supervision sub-data.

[0131] In some embodiments, the second preset table can be set by a technician based on experience.

[0132] In some embodiments, the newly collected sub-data is obtained by sampling the newly collected data corresponding to each type of emergency supervision sub-data based on the sampling parameters corresponding to each type of emergency supervision sub-data.

[0133] In some embodiments, the newly collected data includes multiple newly collected sub-data, and the new collected data corresponding to each emergency supervision sub-data has the same risk type as that corresponding to each emergency supervision sub-data.

[0134] In some embodiments, the sampling parameters corresponding to each emergency supervision sub-data are related to the historical occurrence characteristics of the target risk accident corresponding to each emergency supervision sub-data in the target management area and the associated management areas.

[0135] Newly collected data refers to the emergency supervision sub-data that was recently collected within the most recent preset time period and is of the same risk type as the corresponding emergency supervision sub-data. The most recent preset time period can be preset, such as the most recent 8 hours.

[0136] In some embodiments, the newly collected data may be obtained in a variety of ways, such as by patrol equipment or by monitoring equipment (eg, gas monitoring equipment, temperature monitoring equipment, etc.).

[0137] Sampling parameters refer to the parameters used when sampling the newly collected data corresponding to each emergency supervision sub-data.

[0138] In some embodiments, the sampling parameters include a sampling ratio, a sampling interval, and a sample size.

[0139] In some embodiments, the superior management platform may determine sampling parameters based on the target risk accident and target management area corresponding to each emergency supervision sub-data, and the historical occurrence characteristics of the associated management areas adjacent to the target management area.

[0140] Target risk accidents refer to actual accidents that have the same risk type as the emergency supervision sub-data.

[0141] Historical occurrence characteristics refer to characteristics related to the target risk accident, such as the number of target risk accidents that occur within a historical preset period of time, and the severity of each risk accident.

[0142] In some embodiments, target risk accidents and historical occurrence characteristics can be obtained from historical data.

[0143] In some embodiments, the upper-level management platform may determine the sampling parameters based on a third preset table.

[0144] The third preset table reflects the relationship between the target risk incidents and historical occurrence characteristics and the corresponding sampling parameters. The superior management platform can determine the sampling parameters by querying the third preset table based on the type, number of occurrences, and scale of the target risk incidents that actually occurred in the target management area and the associated management areas.

[0145] For example, the superior management platform can sum the number of target risk accidents in the target management area with the number of target risk accidents in the associated management areas to obtain a first sum value, and sum the level of target risk accidents in the target management area (e.g., earthquake magnitude, high wind level) with the level of target risk accidents in the associated management areas to obtain a second sum value. Based on the first and second sum values, the sampling parameters are determined by querying a third preset table.

[0146] For example, in the target management area and the associated management area, the more times a certain risk accident occurs and the larger the scale of the occurrence, the larger the sampling ratio in the sampling parameters of the newly collected data corresponding to the corresponding emergency supervision sub-data, the smaller the sampling interval, and the larger the sample size.

[0147] According to some embodiments of the present invention, based on actual historical occurrences of target risk incidents and their historical occurrence characteristics, it is possible to determine which risk types frequently occur in the target management area and associated management areas, as well as the scale of their occurrence, and thus determine which risk types have a higher probability of occurrence. When guiding the sampling of newly collected data, a higher probability of risk is prioritized for sampling, thereby improving the accuracy of the second weighting factor.

[0148] In some embodiments, the sampling parameter is further related to the sub-propagation degree from the associated management area to the target management area corresponding to the risk type to which the target risk incident belongs.

[0149] In some embodiments, the upper management platform may calculate the first sum using equation (1):

[0150] (1)

[0151] in, The total number of target risk accidents in the target management area and associated management areas (i.e. the first sum value); The number of target risk accidents occurring in the target management area; is the number of target risk accidents occurring in the i-th associated management area; For the i-th associated management area to the target management area, the corresponding target risk accident sub-propagation degree. For more information about sub-propagation degree, see Figure 2 Related description.

[0152] In some embodiments, the upper management platform may calculate the second sum using equation (2):

[0153] (2)

[0154] in, The total occurrence level of target risk accidents in the target management area and associated management areas (i.e., the second sum value); The level of target risk accidents in the target management area; is the level of target risk accident occurrence in the i-th associated management area; It is the sub-propagation degree corresponding to the corresponding target risk accident when the i-th associated management area is connected to the target management area.

[0155] According to some embodiments of the present invention, based on the sub-propagation degree from the associated management area to the target management area, the number of occurrences and the scale of occurrence of target risk accidents in the target management area and the associated management area are weighted and summed respectively. This can fully take into account the impact of the risk type of the associated management area on the target management area, making the calculation of the second weight factor more accurate, and thus obtaining a more accurate processing degree of the emergency management sub-data.

[0156] In some embodiments, the upper-level management platform determines the risk level of the target management area, including: determining the risk level of the target management area based on a first weighting factor and a second weighting factor of each emergency supervision sub-data.

[0157] In some embodiments, the upper management platform can determine the risk level of the target management area by using equation (3):

[0158] (3)

[0159] in, the risk level of the target management area; is the first weight factor of the emergency supervision sub-data of risk type i in the target management area; is the second weight factor of the emergency supervision sub-data of the i-th risk type.

[0160] According to some embodiments of the present invention, when determining the risk level of the entire area, not only the macro-level possibility of each risk occurring in the entire area is taken into consideration, but also the performance of the real-time supervision sub-data corresponding to various risk types is taken into consideration. Therefore, the determined risk level is more accurate and closer to the actual situation.

[0161] According to some embodiments of the present invention, when determining the processing level of the emergency supervision sub-data of the target management area and the risk level of the entire area, not only the importance of the emergency supervision sub-data corresponding to different risk types in the target management area is considered, but also the urgency of each emergency supervision sub-data is taken into account. This allows for more accurate and efficient processing of emergency supervision data and improves security prevention efficiency.

[0162] Figure 4 is an exemplary flow chart of patrol control according to some embodiments of the present invention.

[0163] In some embodiments, as Figure 4 As shown, the patrol control process 400 includes the following steps: In some embodiments, the patrol control process 400 can be executed by a superior management platform.

[0164] Step 410 : determining the collection parameters and warning parameters of the patrol equipment in the target management area based on the first weight factor of each emergency supervision sub-data and the risk level of the target management area.

[0165] For more information about each emergency supervision sub-data, first weight factor, target management area, risk level, and patrol equipment, see Figure 1 、 Figure 2 And related instructions.

[0166] Collection parameters refer to the data that patrol equipment needs to collect when performing monitoring tasks. For example, collection parameters may include key collection points and key collection frequencies.

[0167] Key data collection points are high-risk monitoring areas where patrol equipment needs to focus on collecting data. For example, if the first weighted risk is fire, key data collection points could be locations where fires are likely to occur, such as chemical plants.

[0168] In some embodiments, the key collection points can be determined in a variety of ways. For example, the key collection points can be manually preset based on points where corresponding risks have occurred in history.

[0169] Key collection frequency refers to the frequency of data collection by patrol equipment at key collection points within a period of time.

[0170] In some embodiments, the key collection frequency can be determined based on the first weight factor and the risk level. For example, the key collection frequency is proportional to the first weight factor of each emergency supervision sub-data and the risk level of the target management area.

[0171] Warning parameters refer to the type of data that patrol equipment uses to alert users after identifying a risk. For example, warning parameters may include the type of audio or video warnings.

[0172] The warning audio and video type refers to the audio and video type used to remind residents to prevent risks. The warning audio and video type can be determined based on the first weight factor of each emergency supervision sub-data and the risk level of the target management area.

[0173] Different emergency supervision sub-data corresponds to different risk types, and the upper-level management platform can determine the warning audio and video type based on the risk type corresponding to the emergency supervision sub-data with the largest first weight factor. For example, if the risk type corresponding to the emergency supervision sub-data with the largest first weight factor is fire, the warning audio and video type can be fire prevention audio and video.

[0174] Different risk levels correspond to different warning audio and video types. For example, the greater the risk level, the more warning audio and video types are applied.

[0175] Step 420: Based on the collection parameters, the patrol equipment is controlled to collect patrol information at key collection points and at a key collection frequency.

[0176] Patrol information refers to information collected by patrol equipment during patrols. For example, patrol information can include captured videos and images. Patrol information can be used as emergency supervision data.

[0177] Step 430: Based on the warning audio and video type, control the patrol equipment to play the warning audio and video during the patrol process.

[0178] In some embodiments, the superior management platform may control the patrol device to play the warning video or broadcast the warning sound based on the determined warning audio and video type of the patrol device.

[0179] In some embodiments, the superior management platform can determine whether a fire has occurred based on patrol information collected by patrol equipment; in response to a fire, obtain the fire area and fire characteristics; and control the drone to spray a fire extinguishing agent corresponding to the fire characteristics in the fire area.

[0180] In some embodiments, the upper-level management platform can confirm whether a fire has occurred through various methods. For example, it can process patrol information based on a preset algorithm to determine whether there is a fire risk. The preset algorithm can include image recognition.

[0181] The fire occurrence area refers to the area where the fire occurs.

[0182] In some embodiments, the upper-level management platform may determine the area where the fire occurred based on the source of the patrol information that identified the risk.

[0183] Fire characteristics may include black smoke but no clear fire source, solid materials (paper, wood) or oily substances as the fire source, etc.

[0184] Fire extinguishing agents are substances used to put out fires. Examples include water, a mixture of water and foam, dry powder, etc.

[0185] In some embodiments, the upper management platform can construct a preset table of fire characteristics and fire extinguishing agents based on historical experience, wherein the fire characteristics and fire extinguishing agents in the preset table correspond one to one.

[0186] In some embodiments of the present invention, by determining the fire occurrence area and fire characteristics and spraying the corresponding fire extinguishing agent, it is possible to accurately and quickly extinguish the fire and avoid risks.

[0187] In some embodiments of the present invention, by collecting parameters and warning parameters and controlling patrol equipment to play warning audio and video during patrol, residents can be effectively reminded to guard against the occurrence of high risks such as fire.

[0188] Some embodiments of the present invention further provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes any one of the methods described in the above embodiments.

[0189] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit the present invention. Although not explicitly described herein, those skilled in the art may make various modifications, improvements, and revisions to the present invention. Such modifications, improvements, and revisions are suggested in the present invention and remain within the spirit and scope of the exemplary embodiments of the present invention.

[0190] Finally, it should be understood that the embodiments described herein are intended only to illustrate the principles of the present invention. Other variations may also fall within the scope of the present invention. Therefore, by way of example and not limitation, alternative configurations of the embodiments of the present invention may be considered consistent with the teachings of the present invention. Accordingly, the embodiments of the present invention are not limited to the embodiments explicitly described and illustrated herein.

Claims

1. A hierarchical emergency supervision method for smart cities based on the Internet of Things large model, characterized by: This is achieved through a smart city hierarchical emergency supervision system based on the IoT big model; The system includes: an emergency supervision user platform, an emergency supervision service platform, an emergency supervision management platform, an emergency supervision sensor network platform, and an emergency supervision object platform; wherein the emergency supervision user platform includes a user terminal, the emergency supervision service platform includes a communication terminal, the emergency supervision management platform includes a lower-level management platform and an upper-level management platform, wherein each of the lower-level management platforms corresponds to one or more target management areas; and the emergency supervision object platform includes patrol equipment; The method is executed based on the upper-level management platform, and includes: Obtaining regional information and emergency supervision data of the target management area corresponding to the lower-level management platform, wherein the regional information includes at least one of environmental information, production information, and life information, and the emergency supervision data includes at least one emergency supervision sub-data, where each emergency supervision sub-data corresponds to one risk type; Based on the regional information, determining, through a first preset table, a first weighting factor corresponding to each type of the at least one type of emergency supervision sub-data in the target management area; the first weighting factor represents the importance of the corresponding emergency supervision sub-data in the target management area; the first preset table reflects the first weighting factors corresponding to the regional information and the type of emergency supervision data; Based on the first weighting factor, determining the degree of processing of each type of emergency supervision sub-data by the lower-level management platform through a first preset relationship; the first preset relationship refers to the relationship between the first weighting factor and the processing degree; different processing degrees represent different processing methods of the lower-level management platform for the emergency supervision sub-data; Performing weighted summation on the first weight factors of the emergency supervision sub-data in the target management area to determine the risk level of the target management area; controlling the lower-level management platform to process the emergency supervision data based on the processing degree of each type of emergency supervision sub-data; Based on the risk level, determining patrol parameters of the patrol device in the target management area, the patrol parameters including patrol path and patrol frequency; Based on the patrol parameters, the patrol device is controlled to patrol on the patrol path at the patrol frequency.

2. The method according to claim 1, characterized in that The determining of the first weight factor corresponding to each type of the at least one type of emergency supervision sub-data in the target management area includes: Based on the area information of the target management area and the area information of the associated management areas of the target management area, a first weight factor corresponding to each type of emergency supervision sub-data in the at least one emergency supervision sub-data in the target management area is determined.

3. The method according to claim 1, characterized in that Determining the processing degree of each emergency supervision sub-data on the lower-level management platform includes: determining, based on the first weight factor and the second weight factor of each type of emergency supervision sub-data, the degree of processing of each type of emergency supervision sub-data on the lower-level management platform; Among them, the second weight factor of each emergency supervision sub-data represents the urgency of each emergency supervision sub-data, and the second weight factor of each emergency supervision sub-data is determined based on the processing of the newly collected sub-data corresponding to each emergency supervision sub-data based on the weight model, and the weight model is a machine learning model.

4. The method according to claim 3, characterized in that Determining the risk level of the target management area includes: The risk level of the target management area is determined based on the first weighting factor and the second weighting factor of each emergency supervision sub-data.

5. The method according to claim 1, wherein The method further comprises: Determining, based on the first weight factor of each emergency supervision sub-data and the risk level of the target management area, collection parameters and warning parameters of the patrol equipment in the target management area, the collection parameters including key collection points and key collection frequencies, and the warning parameters including warning audio and video types; Based on the collection parameters, controlling the patrol equipment to collect patrol information at the key collection points and at the key collection frequency; Based on the warning audio and video type, the patrol device is controlled to play the warning audio and video during the patrol process.

6. A hierarchical emergency supervision system for smart cities based on the Internet of Things model, characterized by: The system includes: an emergency supervision user platform, an emergency supervision service platform, an emergency supervision management platform, an emergency supervision sensor network platform, and an emergency supervision object platform; wherein the emergency supervision user platform includes a user terminal, the emergency supervision service platform includes a communication terminal, the emergency supervision management platform includes a lower-level management platform and an upper-level management platform, wherein each of the lower-level management platforms corresponds to one or more target management areas; and the emergency supervision object platform includes patrol equipment; The upper management platform is configured as follows: Obtaining regional information and emergency supervision data of the target management area corresponding to the lower-level management platform, wherein the regional information includes at least one of environmental information, production information, and life information, and the emergency supervision data includes at least one emergency supervision sub-data, where each emergency supervision sub-data corresponds to one risk type; Based on the regional information, determining, through a first preset table, a first weighting factor corresponding to each type of the at least one type of emergency supervision sub-data in the target management area; the first weighting factor represents the importance of the corresponding emergency supervision sub-data in the target management area; the first preset table reflects the first weighting factors corresponding to the regional information and the type of emergency supervision data; Based on the first weighting factor, determining the degree of processing of each type of emergency supervision sub-data by the lower-level management platform through a first preset relationship; the first preset relationship refers to the relationship between the first weighting factor and the processing degree; different processing degrees represent different processing methods of the lower-level management platform for the emergency supervision sub-data; Performing weighted summation on the first weight factors of the emergency supervision sub-data in the target management area to determine the risk level of the target management area; controlling the lower-level management platform to process the emergency supervision data based on the processing degree of each type of emergency supervision sub-data; Based on the risk level, determining patrol parameters of the patrol device in the target management area, the patrol parameters including patrol path and patrol frequency; Based on the patrol parameters, the patrol device is controlled to patrol on the patrol path at the patrol frequency.

7. The system according to claim 6, characterized in that The upper management platform is further configured to: Based on the area information of the target management area and the area information of the associated management areas of the target management area, a first weight factor corresponding to each type of emergency supervision sub-data in the at least one emergency supervision sub-data in the target management area is determined.

8. The system according to claim 6, wherein: The upper management platform is further configured to: determining, based on the first weight factor and the second weight factor of each type of emergency supervision sub-data, the degree of processing of each type of emergency supervision sub-data on the lower-level management platform; Among them, the second weight factor of each emergency supervision sub-data represents the urgency of each emergency supervision sub-data, and the second weight factor of each emergency supervision sub-data is determined based on the processing of the newly collected sub-data corresponding to each emergency supervision sub-data based on the weight model, and the weight model is a machine learning model.

9. The system according to claim 8, characterized in that The upper management platform is further configured to: The risk level of the target management area is determined based on the first weighting factor and the second weighting factor of each emergency supervision sub-data.

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 hierarchical emergency supervision method based on the Internet of Things large model as described in claim 1.

Images