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

Abstract

The embodiments of this specification provide a smart city emergency management method, system, and medium based on an Internet of Things (IoT) macro model. The method comprises: responding to emergency management requests received from a sub-platform, determining a data retrieval order for the emergency management requests based on a first emergency level of the emergency management requests; and retrieving emergency management data corresponding to the emergency management requests from a database based on the data retrieval order. By integrating multiple data sources and implementing dynamic scheduling and decision support based on intelligent algorithms, this method improves the timeliness and effectiveness of emergency management, ensures efficient response to emergencies in various environments, and promotes the construction and development of smart cities.

Description

Technical Field

[0001] This specification relates to the field of smart cities, and in particular to a smart city emergency supervision method, system and medium based on the Internet of Things big model. Background Art

[0002] Traditional emergency management systems often suffer from low data collection efficiency, slow response times, and irrational resource scheduling, making them unable to meet the demands of modern cities for rapid and accurate emergency response. In particular, how to efficiently integrate multi-source data, dynamically adjust emergency resources, and implement intelligent decision support when facing emergencies has become a key issue that smart city emergency management systems urgently need to address.

[0003] Therefore, we propose a smart city emergency management system based on a large-scale IoT model to address the limitations of traditional management models, including their singularity and blind spots. This system will integrate multiple data sources and implement dynamic scheduling and decision support through intelligent algorithms, improving the timeliness and effectiveness of emergency management. This will ensure efficient response to emergencies in all environments and promote the construction and development of smart cities. Summary of the Invention

[0004] An embodiment of the present specification provides a smart city emergency supervision method based on an Internet of Things big model, which is executed by an emergency supervision management platform, and the method includes: in response to receiving an emergency management demand from a sub-platform, determining the data retrieval order of the emergency management demand according to the first emergency level of the emergency management demand; based on the data retrieval order, retrieving the emergency management data corresponding to the emergency management demand from the database, including: retrieving multiple emergency management data corresponding to the emergency management demand; according to the multiple emergency management data and the second emergency level of each of the multiple emergency management data, retrieving the preset processing model corresponding to each emergency management data from the data processing model library; processing each emergency management data based on the preset processing model corresponding to each emergency management data; sending the processed multiple emergency management data to the corresponding sub-platform; within a preset period: obtaining multiple second emergency levels of multiple emergency management data in multiple geographical areas; for multiple geographical areas for each geographical area: determining, according to the multiple second emergency levels, collection parameters for different emergency management data within the geographical area, the collection parameters including the patrol time and / or patrol frequency of the emergency vehicle for different emergency management data, and the shooting angle and / or shooting frequency of the camera installed on the emergency vehicle at the patrol point; generating a patrol instruction according to the collection parameters for different emergency management data within the geographical area, and sending it to the emergency supervision object platform to control the emergency vehicles located in the geographical area to patrol within the geographical area according to the patrol time and / or patrol frequency, and controlling the camera to shoot according to the shooting angle and / or the shooting frequency at the patrol point to collect corresponding emergency management data; when the emergency vehicle is patrolling, controlling the built-in terminal installed on the emergency vehicle to detect the image shot by the emergency vehicle at the patrol point; receiving the early warning instruction returned by the built-in terminal, and sending the early warning instruction to the display device for display.

[0005] An embodiment of this specification provides a smart city emergency supervision system based on the Internet of Things big model, the system including: an emergency supervision management platform, an emergency supervision sensor network platform and an emergency supervision object platform; the emergency supervision management platform is communicatively connected to the emergency supervision object platform through the emergency supervision sensor network platform; the emergency supervision management platform includes sub-platforms and a data center, the sub-platforms including at least one of an emergency prevention sub-platform, an emergency monitoring sub-platform, a risk prevention sub-platform and an emergency response sub-platform; the data center includes a database, a data processing model library and a computing unit; the emergency supervision management platform is configured to execute a smart city emergency supervision method based on the Internet of Things big model.

[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 a smart city emergency supervision method based on an Internet of Things big model.

[0007] Beneficial Effects: The IoT-based smart city emergency management method, system, and medium of this specification, by setting a first urgency level for emergency management needs, can process emergency management needs sequentially according to the first urgency level in situations of demand congestion, such as when multiple emergency management needs are awaiting processing, so that emergency management needs with higher urgency levels are prioritized. Furthermore, by determining corresponding collection parameters based on the second urgency level of multiple emergency management data within multiple geographic areas and generating patrol instructions, it is possible to ensure effective patrols for emergency vehicles in different geographic areas. 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:

[0009] Figure 1 is a schematic diagram of a system platform of a smart city emergency supervision system based on an Internet of Things large model according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of a smart city emergency supervision method based on an Internet of Things big model according to some embodiments of this specification;

[0011] Figure 3 is an exemplary flow chart for retrieving emergency management data corresponding to emergency management requirements from a database according to some embodiments of this specification;

[0012] Figure 4 is an exemplary flow chart for determining a first emergency level of emergency management needs according to some embodiments of this specification;

[0013] Figure 5 This is an exemplary flow chart of controlling sensors within a geographical area to upload data according to data upload features according to some embodiments of this specification. DETAILED DESCRIPTION

[0014] 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.

[0015] Figure 1 This is a system structure diagram of a smart city emergency supervision system based on the Internet of Things large model shown in some embodiments of this specification.

[0016] In some embodiments, as Figure 1 As shown, the smart city emergency supervision system 100 based on the Internet of Things big model may include an emergency supervision management platform 110 , an emergency supervision sensor network platform 120 , and an emergency supervision object platform 130 .

[0017] The emergency supervision and management platform 110 is a digital monitoring and management platform for monitoring global emergency events. Emergency events are sudden, destructive, and harmful events, such as natural disasters, accidents, public health incidents, and social security incidents.

[0018] In some embodiments, the emergency supervision and management platform 110 may be configured in a processor and / or server. The processor and / or server may process data and / or information obtained from other platforms. The processor and / or server may execute program instructions based on the data, information, and / or processing results to perform one or more functions described in this application.

[0019] The emergency supervision sensor network platform 120 is a platform for sensing and communicating smart city emergency supervision information. It is used to achieve bidirectional data communication and transmission between the emergency supervision management platform 110 and the emergency supervision object platform 130. For example, the emergency supervision sensor network platform may include communication equipment, servers, and various gateway devices.

[0020] The emergency supervision platform 130 is an information processing platform used to monitor the safety of various supervised objects involved in emergency management. These supervised objects may include chemical plants that manufacture flammable and explosive products, transportation hubs, public venues, and more. The platform can include a variety of monitoring, sensing, and interactive devices, such as cameras, fire alarms, hazardous gas leak detectors, and environmental monitoring sensors.

[0021] In some embodiments, the emergency supervision management platform 110 is communicatively connected to the emergency supervision object platform 130 via the emergency supervision sensor network platform 120 .

[0022] In some embodiments, the emergency supervision management platform 110 includes sub-platforms and a data center.

[0023] In some embodiments, the sub-platform includes at least one of an emergency prevention sub-platform, an emergency monitoring sub-platform, a risk prevention sub-platform, and an emergency response sub-platform.

[0024] The emergency prevention sub-platform refers to the management platform for emergency event assessment and prevention.

[0025] The emergency supervision sub-platform refers to a platform used to monitor, collect and analyze emergency event data.

[0026] The risk prevention sub-platform refers to a platform used to identify potential risks, assess risk levels and implement risk reduction strategies.

[0027] The emergency response sub-platform refers to a platform used to coordinate, dispatch and implement emergency plans after an emergency event occurs.

[0028] In some embodiments, the data center includes a database, a data processing model library, and a computing unit.

[0029] Databases are used to collect, store, and manage large amounts of data related to emergency management. Examples include MySQL, PostgreSQL, InfluxDB, and Prometheus.

[0030] The data processing model library refers to a collection of data processing models used for emergency management data processing.

[0031] A computing unit is a functional module used to perform arithmetic, logical, and other instruction operations. A computing unit may include, but is not limited to, a central processing unit (CPU).

[0032] In some embodiments, the smart city emergency supervision system based on the Internet of Things big model also includes an emergency supervision user platform and an emergency supervision service platform.

[0033] The emergency management user platform is an interactive platform for emergency management personnel and the public. In some embodiments, the emergency management user platform may include at least one human interaction device, such as a mobile phone or computer.

[0034] An emergency supervision service platform refers to a platform that provides emergency supervision services. In some embodiments, the emergency supervision service platform can be configured as a server, enabling data exchange with the emergency supervision user platform and the emergency supervision management platform. For example, upon discovering an emergency event, the public can use the emergency supervision user platform to report the event to the emergency supervision service platform. The emergency supervision service platform will then report the relevant event and its impact assessment to the emergency supervision management platform to facilitate response and decision-making by management departments.

[0035] Figure 2 This is an exemplary flow chart of a smart city emergency supervision method based on an Internet of Things 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 in an emergency supervision management platform.

[0036] In step 210, in response to receiving the emergency management request from the sub-platform, a data retrieval order of the emergency management request is determined according to the first emergency level of the emergency management request. In some embodiments, step 210 is performed by a data center.

[0037] An emergency management demand is an instruction sent by a sub-platform to retrieve one or more emergency management data. For example, an emergency management demand is an instruction sent by the emergency prevention sub-platform to retrieve emergency management data related to accident and disaster prevention.

[0038] The first emergency level is the importance level of the emergency management requirement. The first emergency level may include multiple levels. Different levels of the first emergency level correspond to different levels of importance of emergency management requirements.

[0039] In some embodiments, the first emergency level of the emergency management requirement may be preset by a technician or staff member.

[0040] In some embodiments, the first emergency level of the emergency management requirement can also be determined based on one or more second emergency levels of one or more emergency management data corresponding to the emergency management requirement. Figure 4 and its related contents.

[0041] The data retrieval order is the order in which one or more emergency management data corresponding to multiple emergency management requirements are retrieved.

[0042] In some embodiments, the data center sorts the emergency management requirements according to the first emergency levels, for example, by determining the order of emergency management requirements data retrieval according to the importance levels corresponding to the first emergency levels, from high to low.

[0043] Step 220: Based on the data retrieval ranking, retrieve the emergency management data corresponding to the emergency management requirements from the database. In some embodiments, step 220 is performed by a data center.

[0044] Emergency management data refers to various monitoring data required for emergency management. By way of example only, this data may include at least one of, or a combination of, ambient temperature, ambient humidity, wind speed, the presence of open flames, flammable / toxic gas concentrations, crowd size, the number of flammable and explosive items, and the duration of a gas outage.

[0045] During transmission, emergency management data will be electronically tagged. This electronic tag includes the data type and geographic region of the emergency management data. The electronic tag may also include the unique ID of the device collecting the data, such as a sensor or camera. Data types include text, images, video, and audio. The geographic region of the emergency management data is the geographic region where the device collecting the data is located. Geographic regions can include administrative regions or grid areas. Devices collecting emergency management data may include various sensors, cameras, and so on.

[0046] In some embodiments, the data center retrieves one or more emergency management data corresponding to the emergency management needs directly from the database based on the data retrieval sorting. In some embodiments, the data center can also process the retrieved emergency management data and send the processed emergency management data to the corresponding sub-platform. For details, see Figure 3 and its related contents.

[0047] Step 230: Acquire multiple second emergency levels of multiple emergency management data in multiple geographical areas within a previous preset period. In some embodiments, step 230 is performed by an emergency supervision management platform.

[0048] The second emergency level is the importance level of the emergency management data. Emergency management data with different second emergency levels correspond to different importance levels.

[0049] In some embodiments, the second emergency level of emergency management data can be pre-set by a technician. In some embodiments, the second emergency level of emergency management data can also be determined based on the frequency of emergency management data access within the last preset period, the data type of emergency management data, and the geographical area to which it belongs. Figure 4 and its related contents.

[0050] The preset period is a period for determining and executing the frequency of data collection. In some embodiments, the preset period is set by a technician or staff member based on experience. For example, the preset period can be set to one day, one week, or one month.

[0051] The geographical area is the geographical area where the collection equipment corresponding to the emergency management data is located. The geographical area can be an administrative area, etc.

[0052] In some embodiments, the second emergency level for the same type of emergency management data may be different for multiple geographic regions. For example, for emergency management data such as crowd size, the second emergency level for emergency management data in a city center area may be higher than the second emergency level for emergency management data in non-city center areas.

[0053] Step 240 : For each of the plurality of geographical regions, determine, based on the plurality of second emergency levels, collection parameters for different emergency management data within the geographical region. In some embodiments, step 240 is performed by an emergency supervision management platform.

[0054] The collection parameters include the patrol time and / or patrol frequency of emergency vehicles for different emergency management data, as well as the shooting angle and / or shooting frequency of the cameras installed on the emergency vehicles at the patrol points.

[0055] Emergency vehicles are vehicles used to collect emergency management data and / or handle emergencies. In some embodiments, emergency vehicles can include unmanned vehicles, manually driven vehicles, drones, etc. In some embodiments, emergency vehicles can include fire trucks, medical vehicles, emergency rescue vehicles, power supply vehicles, skid-mounted gas stations, etc.

[0056] Patrol times are the time or times at which emergency vehicles begin patrolling within a pre-set period, for example, patrols starting at 10:00 and 16:00 daily. Patrol frequency is the number of times an emergency vehicle patrols along a planned route within a pre-set period and the interval between patrols, for example, five patrols per day with a two-hour interval between each patrol.

[0057] Patrol points are locations where emergency vehicles need to collect data along their planned routes, for example, areas that require special attention.

[0058] The shooting angle includes the angle of the camera in the horizontal and vertical directions, the horizontal movement angle, the vertical movement angle, etc. The shooting frequency is the shooting frame rate, for example, it can be 25 frames per second.

[0059] In some embodiments, the collection parameters for different emergency management data within a geographic area can be determined based on the average second emergency level of the corresponding emergency management data within the previous preset period and a first preset table. The first preset table includes the collection parameters corresponding to each type of emergency management data at different average second emergency levels. The first preset table can be set by those skilled in the art based on experience.

[0060] Step 250: Generate patrol instructions based on the collection parameters of different emergency management data in the geographical area and send them to the emergency supervision object platform. In some embodiments, step 250 is performed by the emergency supervision management platform.

[0061] The patrol instructions are sent to the emergency supervision object platform to control the emergency vehicles located in the geographical area to patrol within the geographical area according to the patrol time and / or patrol frequency, and control the cameras at the patrol points to shoot according to the shooting angle and / or shooting frequency to collect the corresponding emergency management data.

[0062] The patrol instructions include patrol time and / or patrol frequency, shooting angle and / or shooting frequency. For example, the patrol instructions directly control the patrol vehicle and camera in the form of computer instructions.

[0063] Step 260: When the emergency vehicle is on patrol, the built-in terminal installed in the emergency vehicle is controlled to detect the images taken by the emergency vehicle at the patrol point. In some embodiments, step 260 is performed by the emergency supervision management platform.

[0064] The built-in terminal is a processor for image detection, such as an image processor or a central processor.

[0065] In some embodiments, after the image processor of the built-in terminal acquires the image data, it can output a detection result of whether the image is an accident image. If the output detection result is an accident image, the built-in terminal can determine that an accident has been detected.

[0066] In some embodiments, after the built-in terminal detects an accident, it generates an early warning instruction and sends it to the emergency supervision and management platform.

[0067] Step 270: Receive the warning instruction returned by the built-in terminal and send the warning instruction to the display device for display. In some embodiments, step 260 is performed by the emergency supervision management platform.

[0068] The early warning instructions include the type of accident, location and time of occurrence. Accident types may include the discovery of open fire points, crowd density exceeding a threshold, etc.

[0069] In some embodiments, the emergency supervision and management platform sends the received warning instructions to a display device for display. The display device includes a display device associated with the user, including one or any combination of a warning center display screen, a mobile terminal, a computer terminal, etc.

[0070] By setting a first urgency level for emergency management requests, in situations of demand congestion, such as when multiple emergency management requests are awaiting processing, emergency management requests can be processed sequentially according to their first urgency level, prioritizing those with higher urgency. Furthermore, by determining corresponding collection parameters based on the second urgency level of multiple emergency management data points within multiple geographic areas and generating patrol instructions, effective patrols for emergency vehicles in different geographic areas can be ensured.

[0071] Figure 3 This is an exemplary flow chart of retrieving emergency management data corresponding to emergency management requirements from a database according to some embodiments of this specification. Figure 3 As shown, the process 300 includes the following steps: In some embodiments, the process 300 may be performed by a data center.

[0072] Step 310: retrieve multiple emergency management data corresponding to the emergency management requirements from the database.

[0073] In some embodiments, the data center retrieves multiple emergency management data corresponding to the emergency management needs from the database according to the data retrieval order of the emergency management needs.

[0074] Step 320 : According to the plurality of emergency management data and the second emergency level of each of the plurality of emergency management data, retrieve a preset processing model corresponding to each emergency management data from a data processing model library.

[0075] The data processing model library is a model library that stores a plurality of preset processing models with different output precisions and parameter scales.

[0076] Output precision refers to the accuracy of the model's output results. For example, when emergency management data is based on population size, the output precision of the corresponding data processing model can range from retaining one decimal place to retaining two decimal places.

[0077] The parameter scale refers to the number of model input parameters and / or the accuracy of the input parameters themselves. When the emergency management data includes emergency management data in the form of images, the input parameters include the accuracy of the images themselves, such as the resolution of the images.

[0078] In some embodiments, the data center sorts the multiple emergency management data in descending order according to the second emergency level of each emergency management data, and then sequentially calls the preset processing model corresponding to each emergency management data according to the sorting.

[0079] In some embodiments, emergency management data belonging to different ranges of the second emergency level correspond to different preset processing models, and different preset processing models have different output accuracy and / or parameter scales.

[0080] In some embodiments, the higher the emergency level, the smaller the output accuracy and / or parameter scale of the preset processing model.

[0081] The data center may select a corresponding preset processing model according to the range of the second emergency level of the emergency management data.

[0082] The preset processing model is a model for processing emergency management data. The preset processing model can be a machine learning model, such as a neural network (NN) model. The input to the preset processing model is emergency management data, which can be text, images, etc. The output of the preset processing model is the information required for emergency management. For example, if the input emergency management data is an image of crowd size, the preset processing model processes the image and outputs a result related to crowd size.

[0083] In some embodiments, the data center may obtain multiple training samples, each of which includes emergency management data and corresponding labels. The labels are information required for emergency management, such as the size of a crowd. The emergency management data in the training samples may be derived from historical emergency management data, and the corresponding labels may be manually annotated information corresponding to the historical emergency management data.

[0084] In some embodiments, the data center can input the emergency management data in the training sample into the initial preset processing model to obtain the model prediction output corresponding to the training sample; according to the model prediction output and the label of the corresponding training sample, substitute it into the formula of a predefined loss function to calculate the value of the loss function; according to the value of the loss function, reversely update the model parameters in the preset processing model. This step can be performed using various methods. For example, it can be updated based on the gradient descent method; when the iteration end condition is met, the iteration is ended to obtain the trained preset processing model.

[0085] In some embodiments, the data center can incrementally train multiple preset processing models in the data processing model library based on emergency management data retrieved within a preset period. The training order of the multiple preset processing models is determined based on the multiple emergency management requirements corresponding to the multiple preset processing models within the preset period.

[0086] In some embodiments, the data center can extract multiple emergency management data retrieved within a preset period and their corresponding processed data. The processed data can be directly used as the label corresponding to the emergency management data, or the processed data can be manually corrected and used as the label corresponding to the emergency management data. The data center can use the multiple emergency management data and their corresponding labels as incremental training samples for training. The training process is similar to the model training process described above and will not be repeated here.

[0087] As an example, a preset processing model may process multiple emergency management data corresponding to multiple emergency management requirements within a preset period. These multiple emergency management requirements are the multiple emergency management requirements that the preset processing model handles within that preset period. For each preset processing model, the data center may determine the training order for the preset processing model based on the average first emergency level of the multiple emergency management requirements corresponding to the preset processing model. For example, the larger the average first emergency level, the higher the training priority of the corresponding preset processing model.

[0088] According to the needs of emergency supervision, the incremental training order of different preset processing models is determined, which can improve the data processing efficiency of the system while improving the output effect of the preset processing model.

[0089] Step 330: Process each emergency management data based on a preset processing model corresponding to each emergency management data.

[0090] For more information about the preset processing model, see step 320 .

[0091] Step 340: Send the processed emergency management data to the corresponding sub-platform.

[0092] In some embodiments, the data center sends the processed emergency management data to the sub-platform that issued the emergency management requirements corresponding to the emergency management data. The corresponding sub-platform can then make further preparations for the corresponding emergency management based on the received data, such as mobilizing a corresponding number of crowd evacuation devices based on the size of the accident crowd.

[0093] By processing the emergency management data according to the ranking of the second emergency levels of the multiple emergency management data, the emergency management data with a high emergency level can be processed first, the results can be obtained first, and the efficiency of emergency management can be improved.

[0094] Figure 4 FIG. 1 is an exemplary flow chart for determining the first emergency level of emergency management requirements according to some embodiments of this specification. Figure 4 As shown, the process 400 includes the following steps: In some embodiments, the process 400 may be performed by a data center.

[0095] Step 410 : Determine the frequency of emergency management data retrieval based on historical retrieval data corresponding to the emergency management data.

[0096] Historical retrieval data refers to the historical data retrieved from emergency management data over a period of time. This period can be, for example, a single month. This historical retrieval data includes the retrieval time and order of each retrieval.

[0097] The retrieval frequency is the number of times emergency management data has been retrieved in a unit of time. The unit of time can be a day or a week, etc.

[0098] In some embodiments, the historical retrieval times of each emergency management data can be determined based on the historical retrieval time of each emergency management data in the historical retrieval data, and then the historical retrieval times of each emergency management data per unit time can be determined as the retrieval frequency of the emergency management data.

[0099] Step 420 : Determine a second emergency level of the emergency management data based on the access frequency, the data type of the emergency management data, and the geographical area to which the data belongs.

[0100] In some embodiments, the data center can determine the second emergency level corresponding to each piece of emergency management data using a vector database. The vector database includes feature vectors and labels corresponding to the feature vectors. The feature vectors are constructed based on the frequency of access, data type, and geographic region of historical emergency management data retrieved over multiple periods of time. The labels corresponding to the feature vectors are the second emergency levels corresponding to the historical emergency management data.

[0101] The label corresponding to the feature vector can be determined in the following way: obtain the multiple actual retrieval orders of the historical emergency management data corresponding to the feature vector in its corresponding multiple historical retrievals, determine the average of the multiple actual retrieval orders, and use the average as the second emergency level of the emergency management data.

[0102] The data center can determine the vector to be matched corresponding to the current emergency management data based on the frequency of retrieval, the data type of the emergency management data, and the geographical area to which it belongs, and determine the feature vector in the vector database with the highest vector similarity to the vector to be matched as the target vector, and use the label of the target vector as the second emergency level corresponding to the current emergency management data.

[0103] In some embodiments, the data center may determine the second emergency level of the emergency management data through an emergency model based on the frequency of retrieval, data type, and geographical area of ​​the emergency management data.

[0104] In some embodiments, the emergency model is a machine learning model or a neural network (NN) model.

[0105] The emergency response model includes a correlation feature extraction layer and an emergency response prediction layer. The correlation feature extraction layer and the emergency response prediction layer can be trained separately or jointly.

[0106] The input of the correlation feature extraction layer includes each emergency management data, the data type of each emergency management data and the geographical area to which it belongs. The output of the correlation feature extraction layer includes the correlation features of each emergency management data.

[0107] The associated feature includes multiple associated data associated with the emergency management data. For example, when the associated data of emergency management data A are emergency management data B and emergency management data C, the associated feature of emergency management data A is emergency management data B and emergency management data C.

[0108] During separate training, the data feature extraction layer can be trained using the first training sample and the first label. The data center can obtain multiple historical emergency management data, along with their data types and geographic regions, from each of the multiple historical retrievals to construct multiple first training samples. The first label is the associated feature corresponding to the multiple historical emergency management data corresponding to the first training sample.

[0109] The data center can obtain several historical retrievals before and after the historical retrieval corresponding to the historical emergency management data in the first training sample. If some of the historical emergency management data are retrieved in the same historical retrieval, or the number of times they are retrieved in two adjacent historical retrievals is greater than the second preset threshold, then the historical emergency management data in this part of the historical emergency management data are mutually related data.

[0110] The input of the emergency level prediction layer includes the frequency of access, associated features, data type and geographical area of ​​each emergency management data. The output of the emergency level prediction layer includes the second emergency level of each emergency management data.

[0111] In separate training, the emergency level prediction layer can be obtained by training with the second training sample and the second label. The data center can obtain historical retrievals corresponding to emergency management in which multiple accident losses are less than a preset threshold, and construct multiple second training samples based on the retrieval frequency, associated features, data types and geographical areas of multiple historical emergency management data in each historical retrieval. In some embodiments, the data center or other related equipment can count the losses ultimately caused by historical accidents corresponding to the historical retrievals as the accident losses corresponding to the historical retrievals. The preset threshold is set according to demand. The second label is the second emergency level of the historical emergency management data in the second training sample. The data center can use the actual retrieval order of the historical emergency management data in the historical retrieval corresponding to the second training sample as the label corresponding to the second training sample.

[0112] The training process of separately training the associated feature extraction layer and the emergency level prediction layer is similar to the training process of the preset processing model in step 320, and will not be repeated here.

[0113] By introducing the frequency and correlation characteristics of emergency management data into the emergency model, the model can take into account future retrieval conditions when predicting the current input data, thereby improving the accuracy of model predictions.

[0114] Step 430 : determining a first emergency level of the emergency management requirement according to a plurality of second emergency levels of a plurality of emergency management data corresponding to the emergency management requirement.

[0115] In some embodiments, the data center may calculate a weighted sum of multiple second emergency levels of multiple emergency management data corresponding to the emergency management requirement and use the sum as the first emergency level of the emergency management requirement. The weighting coefficient of the second emergency level of each emergency management data is set based on experience.

[0116] In some embodiments, the data center determines the demand overlap rate of each emergency management data in the multiple emergency management data corresponding to the emergency management needs, and adjusts the multiple first emergency levels of the multiple emergency management needs according to the demand overlap rate.

[0117] The demand overlap rate is the overlap rate of emergency management data retrieved from multiple emergency management demands.

[0118] In some embodiments, the data center receives multiple emergency management demands within a time period. The length of the time period can be set according to demand. The multiple emergency management data in the multiple emergency management demands can be used as a batch of emergency management data. The data center can determine the demand overlap rate of the emergency management data retrieved in the batch. In some embodiments, for each emergency management data, the ratio of the number of emergency management demands that retrieved the emergency management data in the batch to the total number of emergency management demands retrieved in the batch is used as the demand overlap rate of the emergency management data.

[0119] In some embodiments, for each emergency management demand, the data center may calculate the average of the demand overlap rates of the corresponding multiple emergency management data, and multiply the first emergency level by the average to obtain the adjusted first emergency level of the emergency management demand.

[0120] When calculating the first emergency level of each emergency management demand, the demand overlap rate of the emergency management data corresponding to each demand is also considered, so that the emergency management data with a higher demand overlap rate can be retrieved first, thereby improving the overall response speed of this batch of demands.

[0121] The second emergency level of emergency management data can be determined based on the comprehensive data type and geographical area, and dangerous data or important data in important areas or high-risk areas can be given priority.

[0122] Figure 5This is an exemplary flow chart of controlling sensors in a geographical area to upload data according to data upload characteristics according to some embodiments of this specification. Figure 5 As shown, the process 500 includes the following steps. In some embodiments, the process 500 can be executed by an emergency supervision management platform.

[0123] Step 510: Determine a second emergency level of the emergency management data corresponding to the sensor.

[0124] In some embodiments, the emergency management data includes unique sensor ID information. The emergency supervision and management platform can determine the emergency management data corresponding to the sensor based on the unique sensor ID information included in the emergency management data, and then obtain the second emergency level of the emergency management data from the data center. For details on obtaining the second emergency level of the emergency management data, see step 230 and related content.

[0125] Step 520: Determine the data upload feature of the sensor according to the second emergency level of the emergency management data corresponding to the sensor.

[0126] The data upload characteristics include the data upload amount and / or the data upload frequency. In some embodiments, the acquisition parameters include the data upload characteristics of the sensors within the geographic area. For details on the acquisition parameters, see step 240 and related content.

[0127] The data upload amount is the amount of data that the sensor uploads each time. The data upload amount can be in bytes.

[0128] The data upload frequency is the number of times the sensor uploads data per unit time.

[0129] In some embodiments, the emergency supervision and management platform calculates the mean second emergency level for one or more emergency management data items corresponding to the sensor. Based on this mean, the platform determines the sensor's data upload volume and frequency using a third preset table. The third preset table includes the data upload volumes and frequencies corresponding to different emergency management data items whose mean second emergency levels fall within different second emergency level ranges. In some embodiments, the third preset table is pre-set by technical personnel based on experience.

[0130] In some embodiments, the data center may adjust the data upload characteristics of the sensor based on the average demand overlap rate of the emergency management data corresponding to the sensor during multiple data retrievals within a preset period.

[0131] The average demand overlap rate is the average of the demand overlap rates of multiple emergency management data. For details on the demand overlap rate, see step 430 and related content.

[0132] In some embodiments, when the average demand overlap rate of multiple emergency management data corresponding to a sensor exceeds a preset threshold, the data center may increase the data upload frequency and data upload volume of the sensor by a corresponding preset adjustment amount. The preset threshold and preset adjustment amount are set by technical personnel based on experience.

[0133] In some embodiments, the preset adjustment amount is related to the correlation characteristics of one or more emergency management data corresponding to the sensor. The more correlation data there is between one or more emergency management data and other emergency management data, the larger the preset adjustment amount. The more correlation relationships there are between one or more emergency management data and other emergency management data, the greater the impact of the sensor's collection accuracy, collection volume, and collection frequency on the overall emergency management. In this case, the preset adjustment amount needs to be appropriately increased to ensure that the sensor has sufficient collection accuracy and collection volume.

[0134] Adjusting the sensor data upload characteristics based on the average demand overlap rate of the emergency management data corresponding to the sensor can ensure that important sensors (i.e., sensors that have a greater impact on the entire emergency management) have sufficient collection frequency and volume, which is beneficial to the timeliness and accuracy of emergency management.

[0135] Step 530: Generate an upload instruction based on the data upload characteristics of the sensor and send it to the emergency supervision object platform.

[0136] The upload command is used to control sensors within a geographical area to upload data according to the data upload characteristics.

[0137] In some embodiments, after receiving the upload instruction, the emergency supervision object platform sends the upload instruction to the sensor, controls the sensor to upload the data to the emergency supervision object platform according to the data upload characteristics, and then sends it to the emergency supervision management platform, for example, the database therein.

[0138] By determining the amount of sensor data uploaded based on the second emergency level of emergency management data, important sensors (i.e., sensors that have a greater impact on the entire emergency management) can have sufficient collection frequency and volume, which is beneficial to the timeliness and accuracy of emergency management.

[0139] 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.

[0140] 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. A smart city emergency supervision method based on the Internet of Things large model, characterized by: The method is executed by the emergency supervision management platform, The method comprises: In response to receiving an emergency management demand from a sub-platform, determining a data retrieval order for the emergency management demand according to a first emergency level of the emergency management demand; Retrieving emergency management data corresponding to the emergency management requirements from a database based on the data retrieval sorting includes: Retrieving multiple emergency management data corresponding to the emergency management requirements; Retrieving, from a data processing model library, a preset processing model corresponding to each emergency management data according to the plurality of emergency management data and the second emergency level of each emergency management data, wherein the preset processing model is a machine learning model; Determining a frequency of retrieval of the emergency management data based on historical retrieval data corresponding to the emergency management data; determining a second emergency level of the emergency management data according to the retrieved frequency, the data type of the emergency management data, and the geographical area to which it belongs; determining the first emergency level of the emergency management requirement according to the plurality of second emergency levels of the plurality of emergency management data corresponding to the emergency management requirement; Processing each emergency management data based on the preset processing model corresponding to each emergency management data; Send the processed emergency management data to the corresponding sub-platform; Among them, within a preset period: Acquire multiple second emergency levels of multiple emergency management data in multiple geographical areas within a previous preset period; For each geographic region within multiple geographic regions: determining, based on the plurality of second emergency levels, collection parameters for different emergency management data within the geographical area; Generate patrol instructions based on the collection parameters of different emergency management data in the geographical area and send them to the emergency supervision object platform; when the emergency vehicle is on patrol, control the built-in terminal installed in the emergency vehicle to detect the images taken by the emergency vehicle at the patrol point; Receive the warning instruction returned by the built-in terminal, and send the warning instruction to the display device for display.

2. The method according to claim 1, wherein Determining the second emergency level of the emergency management data according to the retrieved frequency, the data type of the emergency management data, and the geographical area to which it belongs includes: The second emergency level of the emergency management data is determined based on the frequency of retrieval of the emergency management data, the data type and the geographical area to which it belongs through an emergency model, and the emergency model is a machine learning model.

3. The method according to claim 1, wherein The acquisition parameters further include data upload characteristics of sensors provided in the geographical area, wherein the data upload characteristics include data upload amount and / or data upload frequency; The method further comprises: During the preset period: determining the second emergency level of the emergency management data corresponding to the sensor; determining a data upload feature of the sensor according to the second emergency level of the emergency management data corresponding to the sensor; An upload instruction is generated according to the data upload characteristics of the sensor and sent to the emergency supervision object platform to control the sensors in the geographical area to upload data according to the data upload characteristics.

4. A smart city emergency supervision system based on an Internet of Things big model that applies the smart city emergency supervision method based on an Internet of Things big model as claimed in claim 1, characterized in that: The system includes: an emergency supervision management platform, an emergency supervision sensor network platform and an emergency supervision object platform; The emergency supervision management platform is communicatively connected to the emergency supervision object platform via the emergency supervision sensor network platform; The emergency supervision and management platform includes a sub-platform and a data center, wherein the sub-platform includes at least one of an emergency prevention sub-platform, an emergency monitoring sub-platform, a risk prevention sub-platform, and an emergency response sub-platform; The data center includes a database, a data processing model library and a computing unit; The data center is further configured to: Determining a frequency of retrieval of the emergency management data based on historical retrieval data corresponding to the emergency management data; determining a second emergency level of the emergency management data according to the retrieved frequency, the data type of the emergency management data, and the geographical area to which it belongs; determining the first emergency level of the emergency management requirement according to the plurality of second emergency levels of the plurality of emergency management data corresponding to the emergency management requirement; The emergency supervision management platform is configured to execute the smart city emergency supervision method based on the Internet of Things big model; Among them, within a preset period: Acquire multiple second emergency levels of multiple emergency management data in multiple geographical areas within a previous preset period; For each geographic region within multiple geographic regions: determining, based on the plurality of second emergency levels, collection parameters for different emergency management data within the geographical area; Generate patrol instructions based on the collection parameters of different emergency management data in the geographical area and send them to the emergency supervision object platform; when the emergency vehicle is on patrol, control the built-in terminal installed in the emergency vehicle to detect the images taken by the emergency vehicle at the patrol point; Receive the warning instruction returned by the built-in terminal, and send the warning instruction to the display device for display.

5. The system according to claim 4, wherein: The data center is further configured to: The second emergency level of the emergency management data is determined based on the frequency of retrieval of the emergency management data, the data type and the geographical area to which it belongs through an emergency model, and the emergency model is a machine learning model.

6. The system according to claim 4, wherein: The acquisition parameters further include data upload characteristics of sensors provided in the geographical area, wherein the data upload characteristics include data upload amount and / or data upload frequency; The emergency supervision management platform is further configured to: During the preset period: determining the second emergency level of the emergency management data corresponding to the sensor; determining a data upload feature of the sensor according to the second emergency level of the emergency management data corresponding to the sensor; An upload instruction is generated according to the data upload characteristics of the sensor and sent to the emergency supervision object platform to control the sensors in the geographical area to upload data according to the data upload characteristics.

7. 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 emergency supervision method based on the Internet of Things large model as described in any one of claims 1 to 3.

Images