A method and system for fractional emergency management in smart cities based on the Internet of Things large model

Abstract

The present invention provides a decentralized emergency management method and system for smart cities based on a large-scale Internet of Things model. The method is executed by the emergency supervision and management platform of the system and includes: determining at least one accident based on target data; determining data criticality based on target data, data anomaly characteristics, and data criticality; determining data emergency characteristics based on target data, data anomaly characteristics, and data criticality; determining at least one target sub-platform based on target data, data anomaly characteristics, and partitioning conditions; determining emergency parameters based on emergency type, emergency degree, and data emergency characteristics; determining operating parameters of rescue vehicles based on emergency degree, emergency parameters, and data emergency characteristics; and generating and sending dispatch instructions based on the emergency parameters and operating parameters to control rescue vehicles to drive to geographical areas for operation. The method and system can achieve accurate determination and dynamic allocation of emergency resources, improving the overall effectiveness of urban emergency management.

Description

Technical Field

[0001] This specification relates to the field of emergency monitoring, and in particular to a decentralized emergency management method and system for smart cities based on a large model of the Internet of Things. Background Art

[0002] In the development of smart cities, emergency management is a critical component in ensuring safe urban operations. However, current emergency management systems still have shortcomings in data processing and resource allocation. Firstly, data sources are diverse and complex, making it difficult to effectively integrate and share data across different departments, leading to severe information silos. Secondly, there is a lack of effective methods for analyzing the emergency characteristics of data, making it difficult to quickly determine its criticality and priority.

[0003] Therefore, we hope to provide a decentralized emergency management method and system for smart cities based on the Internet of Things big model, which can achieve accurate determination and dynamic allocation of data emergency characteristics, ensure the efficient use of emergency resources, and improve the overall effectiveness of urban emergency management. Summary of the Invention

[0004] One or more embodiments of the present specification provide a method for fractional emergency management in a smart city based on a large model of the Internet of Things, which is executed based on an emergency supervision management platform, including: obtaining multiple target data from an emergency supervision object platform based on a preset period through an emergency supervision sensor network platform; for each target data in the multiple target data: determining at least one accident corresponding to the target data based on the target data; determining the data criticality of the target data based on the target data, the data basic characteristics of the target data and the at least one accident; determining the data emergency characteristics of the target data based on the target data, the data abnormal characteristics of the target data and the data criticality; determining the target data, the data abnormal characteristics and the division conditions corresponding to the target data based on the target data, the data abnormal characteristics and the division conditions corresponding to the target data. at least one target sub-platform corresponding to the target data; obtaining the emergency type and emergency degree within the geographical area corresponding to the target data from the at least one target sub-platform; determining emergency parameters based on the emergency type, the emergency degree and the data emergency characteristics of the at least one target data within the geographical area; determining working parameters of a rescue vehicle based on the emergency degree, the emergency parameters and the data emergency characteristics of the at least one target data within the geographical area; generating a dispatch instruction based on the emergency parameters and the working parameters, and sending the dispatch instruction to the emergency supervision object platform; based on the emergency supervision object platform, controlling the rescue vehicle to drive to the geographical area, and controlling the rescue vehicle to work based on the emergency parameters and the working parameters.

[0005] One or more embodiments of the present specification provide a smart city centralized emergency management system based on a large model of the Internet of Things, including an emergency supervision management platform; the emergency supervision management platform is configured to: obtain multiple target data from the emergency supervision object platform based on a preset period through the emergency supervision sensor network platform; for each target data in the multiple target data: based on the target data, determine at least one accident corresponding to the target data; based on the target data, the data basic characteristics of the target data and the at least one accident, determine the data criticality of the target data; based on the target data, the data abnormal characteristics of the target data and the data criticality, determine the data emergency characteristics of the target data; based on the target data, the data abnormal characteristics and the corresponding accident of the target data ... Divide the conditions and determine at least one target sub-platform corresponding to the target data; obtain the emergency type and emergency degree in the geographical area corresponding to the target data from the at least one target sub-platform; determine the emergency parameters based on the emergency type, the emergency degree and the data emergency characteristics of the at least one target data in the geographical area; determine the working parameters of the rescue vehicle based on the emergency degree, the emergency parameters and the data emergency characteristics of the at least one target data in the geographical area; generate a dispatch instruction based on the emergency parameters and the working parameters, and send the dispatch instruction to the emergency supervision object platform; based on the emergency supervision object platform, control the rescue vehicle to drive to the geographical area, and control the rescue vehicle to work based on the emergency parameters and the working parameters.

[0006] The beneficial effects brought about by the above invention include but are not limited to: (1) by analyzing the target data and the basic data characteristics and data abnormality characteristics of the target data, different emergency parameters and dispatch instructions are determined, which is conducive to accurately responding to accidents, allocating rescue resources in a hierarchical and classified manner, improving emergency rescue efficiency, reducing the possibility of accidents, and reducing the losses caused by accidents; (2) for target data at different accident stages, by determining the division conditions, the target data corresponding to different accidents can be targeted and allocated to the appropriate target sub-platform, thereby improving the efficiency and accuracy of data processing; (3) based on the associated abnormal characteristics, the data abnormal characteristics of the target data and the data criticality, the data emergency characteristics are determined, which is conducive to improving the accuracy of data pairs, thereby improving the risk assessment effect and enhancing the accident warning capability. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] 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:

[0008] Figure 1This is an exemplary platform structure diagram of a decentralized emergency management system in a smart city based on an Internet of Things macro model according to some embodiments of this specification;

[0009] Figure 2 is an exemplary flow chart of a fractional emergency management method in a smart city based on an Internet of Things large model according to some embodiments of this specification;

[0010] Figure 3 is an exemplary flow chart of controlling the operation of a display device according to some embodiments of the present disclosure;

[0011] Figure 4 is a schematic diagram of an emergency prediction model according to some embodiments of this specification;

[0012] Figure 5 This is an exemplary schematic diagram of sending network data packets according to some embodiments of this specification. DETAILED DESCRIPTION

[0013] To more clearly illustrate the technical solutions of the present invention, the following briefly describes the drawings used in the description of the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art will be able to 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.

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

[0015] As used in this specification, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" are not intended to refer to the singular but may include the plural. Generally speaking, the terms "comprise" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

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

[0017] Figure 1This is an exemplary platform structure diagram of a decentralized emergency management system for a smart city based on the IoT model according to some embodiments of this specification. It should be noted that the following embodiments are only used to explain this specification and do not constitute a limitation of this specification.

[0018] In some embodiments, as Figure 1 As shown, the decentralized emergency management system 100 for a smart city based on the IoT model may include an emergency supervision user platform 110, an emergency supervision service platform 120, an emergency supervision management platform 130, an emergency supervision sensor network platform 140, and an emergency supervision object platform 150. The emergency supervision user platform 110, the emergency supervision service platform 120, the emergency supervision management platform 130, the emergency supervision sensor network platform 140, and the emergency supervision object platform 150 are sequentially communicatively connected.

[0019] The emergency supervision user platform 110 is a platform for interacting with supervision users, which may be the supervisory department at a higher level, local government departments, and the public.

[0020] The emergency supervision service platform 120 is a platform for receiving emergency feedback information from the emergency supervision management platform 130 and conveying user needs and control information. In some embodiments, the emergency supervision service platform 120 can exchange data with the emergency supervision user platform 110 and the emergency supervision platform 131 of the emergency supervision management platform 130.

[0021] The emergency supervision management platform 130 is a platform used to monitor and manage data related to the emergency management process. The emergency supervision management platform 130 can interact with the local regulatory department. The local regulatory department corresponds to the higher-level regulatory department corresponding to the emergency supervision user platform 110. For example, if the higher-level regulatory department is a provincial emergency regulatory department, the local regulatory department is the municipal emergency regulatory department.

[0022] In some embodiments, the emergency supervision management platform 130 may be configured to: obtain, through the emergency supervision sensor network platform 140, a plurality of target data from the emergency supervision object platform 150 based on a preset period; for each of the plurality of target data: determine, based on the target data, at least one accident corresponding to the target data; determine, based on the target data, the basic data characteristics of the target data, and the at least one accident, the data criticality of the target data; determine, based on the target data, the data anomaly characteristics of the target data, and the data criticality, the data emergency characteristics of the target data; determine, based on the target data, the data anomaly characteristics, and the partitioning conditions corresponding to the target data, at least one target sub-platform corresponding to the target data; obtain, from the at least one target sub-platform, the emergency type and emergency severity within the geographical area corresponding to the target data; determine, based on the emergency type and emergency severity within the geographical area, and the data emergency characteristics of at least one target data, emergency parameters; determine, based on the emergency severity within the geographical area, the emergency parameters, and the data emergency characteristics of at least one target data, operating parameters of a rescue vehicle; generate, based on the emergency parameters and operating parameters, a dispatch instruction, and send the dispatch instruction to the emergency supervision object platform 150; and, based on the emergency supervision object platform 150, control the rescue vehicle to drive to the geographical area and control the rescue vehicle to operate based on the emergency parameters and operating parameters. More information about the emergency supervision management platform 130 can be found in Figure 2-Figure 5 Related instructions.

[0023] In some embodiments, the emergency supervision management platform 130 may include an emergency supervision master platform 131 and multiple emergency supervision sub-platforms.

[0024] The emergency supervision central platform 131 is a central platform for managing multiple emergency supervision sub-platforms. In some embodiments, the emergency supervision central platform 131 includes an emergency supervision central data center 1311.

[0025] The Emergency Supervision Central Data Center 1311 is a platform for the coordinated management of all emergency supervision data, including target data, dispatch instructions, and other data generated during the emergency management process.

[0026] In some embodiments, the emergency supervision central data center 1311 may include a data coordination model library, a coordinated management database, and a computing unit. The data coordination model library refers to a library of computing models used to store and coordinate emergency supervision data. The data coordination model can perform coordinated classification and comprehensive analysis on received emergency supervision data. The coordinated management database can store data related to comprehensive analysis and management. The computing unit can be a processing device (e.g., a central processing unit, embedded processor, etc.).

[0027] The emergency supervision sub-platform refers to a platform used to process different data. In some embodiments, the emergency supervision sub-platform may include a prevention sub-platform, a monitoring sub-platform, a response sub-platform, a prevention sub-platform, etc. Among them, the prevention sub-platform is configured to process abnormal data to predict the occurrence of emergency accidents. The monitoring sub-platform is configured to process normal data to monitor abnormal situations in real time. The response sub-platform is configured to process abnormal data to determine the real-time status of emergency accidents. The prevention sub-platform is configured to process accident prevention measures data to prevent accidents from happening again.

[0028] In some embodiments, the emergency supervision sub-platform includes a sub-data center. The sub-data center is a platform for managing and storing data of the emergency supervision sub-platform. The sub-data center may include a sub-database and a sub-data processing model library.

[0029] In some embodiments, the sub-data center can exchange data with the emergency supervision main data center 1311.

[0030] In some embodiments, as Figure 1 As shown, the emergency supervision sub-platform may include emergency supervision sub-platform 133-1, emergency supervision sub-platform 133-2, ..., and emergency supervision sub-platform 133-n. The sub-data center may include sub-data center 132-1, sub-data center 132-2, ..., and sub-data center 132-n. Emergency supervision sub-platform 133-n corresponds to and exchanges data with sub-data center 132-n.

[0031] The emergency supervision sensor network platform 140 is a platform for performing sensor communication. In some embodiments, the emergency supervision sensor network platform 140 can be configured as a communication network or a gateway.

[0032] In some embodiments, the emergency supervision sensor network platform 140 may exchange data with the emergency supervision general platform 131 and the emergency supervision object platform 150 .

[0033] The emergency supervision object platform 150 is a platform for collecting data or executing instructions. In some embodiments, the emergency supervision object platform 150 may include monitoring equipment systems directly managed by the emergency supervision management platform 130 and monitoring equipment systems managed by lower-level supervision departments.

[0034] The monitoring equipment system includes a variety of data acquisition devices, such as pressure sensors, temperature sensors, flow meters, gas sensors, video surveillance, infrared sensors, etc.

[0035] For more information about the above platforms, please refer to Figure 2-Figure 5 and related instructions.

[0036] Through the decentralized emergency management system 100 of the smart city based on the Internet of Things big model, communication connections can be achieved between various functional platforms, an information operation closed loop can be formed between the various functional platforms, and they can be coordinated and operated regularly under the unified management of the emergency supervision management platform, realizing the informatization and intelligence of emergency supervision perception and control.

[0037] It should be noted that the above description of the decentralized emergency management system 100 for smart cities based on the IoT macromodel and its component platforms is for ease of description only and does not limit this specification to the exemplary embodiments described. It is understood that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the various platforms or construct subsystems that connect to other platforms without departing from these principles.

[0038] Figure 2 This is an exemplary flow chart of a fractional emergency management method for a smart city based on an IoT macro model, according to some embodiments of this specification. Process 200 is an exemplary process for a fractional emergency management method for a smart city based on an IoT macro model. In some embodiments, process 200 is executed by the emergency supervision management platform 130. Process 200 includes steps 201 through 210.

[0039] Step 201 : Acquire multiple target data from an emergency supervision object platform based on a preset period through an emergency supervision sensor network platform.

[0040] The preset period refers to the period during which the emergency supervision object platform 150 obtains target data.

[0041] In some embodiments, the preset period may be preset by a technician based on experience.

[0042] Target data is emergency management data related to the objects to be processed. For example, target data can include temperature, pressure, and other information. The objects to be processed can be gas systems, power systems, water resources systems, and traffic safety systems. For example, in the case of a gas system, target data can include at least one of gas temperature, gas pressure, gas flow rate, combustible or toxic gas concentration, the number of people around the pipeline, the number of flammable and explosive items, and the duration of a gas outage.

[0043] In some embodiments, the emergency supervision management platform 130 may obtain target data from a collection device of the emergency supervision object platform 150 through the emergency supervision sensor network platform 140 .

[0044] For each target data in the plurality of target data, steps 202 - 210 are executed until all target data are processed.

[0045] Step 202: Based on the target data, determine at least one accident corresponding to the target data.

[0046] Accidents may include leakage accidents, fire accidents, explosion accidents, poisoning accidents, equipment failure accidents, etc.

[0047] In some embodiments, the emergency supervision management platform 130 may search a first preset table based on the target data to determine at least one incident corresponding to the target data. The first preset table may include a correspondence between the target data and at least one incident. The first preset table may be constructed by technical personnel based on experience or historical data.

[0048] Step 203: Determine the data criticality of the target data based on the target data, the basic data characteristics of the target data, and at least one accident.

[0049] Data foundational features refer to the basic characteristics of the target data. For example, data foundational features may include the geographic region to which the target data belongs and the data type (such as text, image, etc.).

[0050] In some embodiments, the emergency supervision management platform 130 may determine the basic data features of the target data using a preset algorithm. For example, the preset algorithm may be a recognition algorithm.

[0051] Data criticality refers to the importance of the target data. The higher the data criticality, the more important the target data is.

[0052] In some embodiments, the emergency supervision and management platform 130 can search a second preset table based on the target data and at least one accident to obtain the development speed, degree of harm, importance of the target data type, and importance of the geographical region to which the target data belongs for each accident; and use the weighted sum of the development speed, degree of harm, importance of the data type, and importance of the geographical region as the data criticality, with the weights set based on experience. The second preset table can include the development speed and degree of harm of each accident corresponding to the target data, the importance of different data types, and the importance of different geographical regions. The second preset table can be obtained based on historical data statistics or preset by technical personnel based on needs.

[0053] Step 204 : determining the data emergency characteristics of the target data based on the target data, the data anomaly characteristics of the target data, and the data criticality.

[0054] Data anomaly features are features that indicate whether the target data is abnormal. For example, data anomaly features can include the current value of the target data, the trend of the target data value (such as an increase or decrease), etc.

[0055] In some embodiments, the emergency supervision management platform 130 can obtain target data at multiple time points within a preset period to form a target data sequence; obtain historical target data consisting of multiple historical time points and the next time point in the preset period in the historical data to form multiple historical change sequences, and cluster the multiple historical change sequences; in the cluster cluster to which the historical change sequence similar to the target data sequence belongs, the class with a relatively large proportion of change trends in subsequent data is used as the change trend of the target data. The historical change sequence reflects the change trend of the historical target data. For example, if the target data sequence is composed of target data at time points t1 to t4, then the historical change sequence is composed of historical target data at historical time points t1 to t5, and t5 is the next time point of t4. Similarity can be that the similarity between the target data sequence and the historical change sequence is greater than the similarity threshold, and the similarity is negatively correlated with the vector distance.

[0056] In some embodiments, the emergency supervision management platform 130 can determine data anomaly characteristics based on the changes in target data within a preset period. For details, see Figure 3 and its related descriptions.

[0057] The data emergency feature is a feature that reflects the importance of the target data. For example, the data emergency feature may include the importance of the target data and the changing trend of the importance.

[0058] In some embodiments, the emergency management platform 130 may use the weighted sum of the data criticality of the target data and the difference between the target data value and the normal range as the importance of the target data. The normal range is the range of the target data when no accidents occur.

[0059] In some embodiments, the emergency supervision management platform 130 may determine the changing trend of the importance based on the changing trend of the target data. For example, when the value of the target data is less than the normal range, the smaller the value of the target data, the greater the importance of the target data; when the value of the target data is greater than the normal range, the larger the value of the target data, the greater the importance of the target data.

[0060] In some embodiments, the emergency supervision management platform 130 can determine the data emergency characteristics of the target data based on at least one associated data of the target data, the data abnormality characteristics and the data criticality. For more information, please refer to Figure 3 and its related descriptions.

[0061] Step 205 : Determine at least one target sub-platform corresponding to the target data based on the target data, the data anomaly characteristics, and the division conditions corresponding to the target data.

[0062] The partitioning conditions refer to the conditions for partitioning target data into different target sub-platforms. The partitioning conditions may include the numerical range and change trend of the target data partitioned into each target sub-platform.

[0063] In some embodiments, the partitioning conditions may be pre-set by a technician based on experience.

[0064] In some embodiments, the emergency supervision management platform 130 can determine the division conditions corresponding to the target data based on the target data and the historical sensor data corresponding to the target data. Figure 5 and its related descriptions.

[0065] Target sub-platform refers to a platform that processes target data differently.

[0066] In some embodiments, the target sub-platform includes the platforms in the emergency supervision sub-platform (such as the prevention sub-platform, monitoring sub-platform, response sub-platform, prevention sub-platform, etc.). For more information, see Figure 1 and related descriptions.

[0067] In some embodiments, the emergency supervision management platform 130 can match the partitioning conditions based on the target data and data anomaly characteristics, determine the change trend of the target data and its numerical range in the partitioning conditions, and thus determine the target sub-platform to which the target data should be sent.

[0068] Step 206: Obtain the emergency type and emergency severity within the geographical area corresponding to the target data from at least one target sub-platform.

[0069] A geographical area refers to the geographical location information of the target data. Each geographical area includes at least one target data.

[0070] The emergency type refers to the type of work that needs to be performed in the geographical area to which the target data belongs, for example, monitoring and patrol, prevention, and / or rescue.

[0071] The emergency level refers to the urgency of the incident in the geographical area to which the target data belongs.

[0072] In some embodiments, the target sub-platform may analyze and process the received target data to determine the emergency type and emergency severity within the geographical area corresponding to the target data.

[0073] In some embodiments, the emergency supervision management platform 130 obtains the emergency type and emergency severity from the corresponding target sub-platform in the emergency supervision sub-platform.

[0074] Step 207: Determine emergency parameters based on the emergency type, emergency degree, and data emergency characteristics of at least one target data within the geographical area.

[0075] Emergency parameters refer to parameters related to emergency response within a geographic area. For example, emergency parameters may include the type of emergency vehicle required for the geographic area corresponding to the target data, the number of emergency vehicles, and the arrival time of emergency vehicles. Emergency vehicle types include emergency vehicles, communication vehicles, patrol vehicles, and power supply vehicles.

[0076] In some embodiments, the emergency supervision and management platform 130 can determine the type of rescue vehicle based on the emergency type. For example, if the emergency type is rescue, the rescue vehicle types include rescue vehicles, power supply vehicles, and communication vehicles. For another example, if the emergency type is prevention, the rescue vehicle types include rescue vehicles, power supply vehicles, communication vehicles, and patrol vehicles. For another example, if the emergency type is monitoring and patrol, the rescue vehicle types include patrol vehicles.

[0077] In some embodiments, the emergency supervision management platform 130 can determine the number of rescue vehicles based on the weighted sum of the emergency level in the geographical area and the average importance of at least one target data; in response to the weighted sum being greater than a first preset threshold, dispatch the maximum number of rescue vehicles to the geographical area; in response to the weighted sum being less than or equal to the first preset threshold, dispatch a standard number of rescue vehicles to the geographical area.

[0078] Among them, the first preset threshold, the maximum number, and the standard number can be preset by technicians based on experience.

[0079] Step 208: Determine the operating parameters of the rescue vehicle based on the emergency level, emergency parameters, and data emergency characteristics of at least one target data within the geographical area.

[0080] In some embodiments, operating parameters may include rescue parameters of the emergency vehicle, patrol parameters of the patrol vehicle, and / or power supply parameters of the power supply vehicle. Rescue parameters include the monitoring frequency of sensors on the emergency vehicle (e.g., temperature sensors, pressure sensors, gas concentration sensors, etc.) and operating parameters of ventilation equipment (e.g., ventilation time period, ventilation power, etc.). Patrol parameters include patrol frequency and / or patrol time of the patrol vehicle, and power supply parameters include the power generated by the power supply equipment.

[0081] In some embodiments, the emergency supervision and management platform 130 can determine the operating parameters of the rescue vehicle by searching a third preset table based on the emergency level, emergency parameters, and the data emergency characteristics of at least one target data. The third preset table includes the emergency level, emergency parameters, and the data emergency characteristics of the target data, and the corresponding operating parameters of the rescue vehicle. The third preset table can be pre-set by technical personnel based on historical data or needs.

[0082] Step 209: Generate a dispatch instruction based on the emergency parameters and the working parameters, and send the dispatch instruction to the emergency supervision object platform.

[0083] Dispatch instructions are instructions for dispatching emergency vehicles. Dispatch instructions may include control instructions for dispatching emergency vehicles to a geographical area and control instructions for controlling each dispatched emergency vehicle to operate according to operating parameters.

[0084] Step 210 : Based on the emergency supervision object platform, the rescue vehicle is controlled to drive to the geographical area, and the rescue vehicle is controlled to work based on the emergency parameters and working parameters.

[0085] In some embodiments, the emergency supervision object platform 150 can control the sensors installed on the rescue vehicle to monitor the environment around the rescue vehicle at a monitoring frequency; control the ventilation equipment installed on the rescue vehicle to exhaust air during the ventilation period at a ventilation power; control the power supply equipment installed on the power supply vehicle to supply power to the geographical area at a generated power; and control the patrol car to patrol within the geographical area at a patrol frequency and patrol time.

[0086] In some embodiments of the present specification, accidents are determined based on target data, and then the data criticality, data emergency characteristics, and corresponding target sub-platforms, geographical areas, emergency types, emergency levels, and emergency parameters of the target data are determined, and then the working parameters of the rescue vehicle are determined, and the operation of the rescue vehicle is controlled, which is conducive to accurately responding to accidents, grading and classifying the allocation of rescue resources, improving emergency rescue efficiency, reducing the possibility of accidents, and reducing the losses caused by accidents.

[0087] It should be noted that the above description of process 200 is for illustration and purpose only and does not limit the scope of application of this specification. Those skilled in the art may make various modifications and variations to process 200 under the guidance of this specification. However, such modifications and variations are still within the scope of this specification.

[0088] Figure 3 300 is an exemplary process for controlling the operation of a display device according to some embodiments of this specification. In some embodiments, process 300 may be executed by the emergency supervision management platform 130. Figure 3 As shown, the process 300 includes the following steps 310 to 330.

[0089] Step 310: Determine data anomaly characteristics of the target data based on changes in the target data within a preset period.

[0090] The change of the target data within the preset period can be represented by a change curve, wherein the abscissa of the change curve represents multiple time points within the preset period, and the ordinate represents the value of the target data corresponding to each time point.

[0091] In some embodiments, the emergency supervision management platform 130 can construct multiple coordinate points using multiple time points in a preset period as horizontal coordinates and the values ​​of the target data corresponding to the multiple time points as vertical coordinates; in response to the number of coordinate points being greater than or equal to a preset number threshold, the multiple coordinate points are sequentially connected to form a change curve. In response to the number of coordinate points being less than the preset number threshold, the emergency supervision management platform 130 can divide all coordinate points into different point sets according to a preset time range; for each point set, the emergency supervision sensor network platform 140 obtains additional target data for at least one time point within the time range corresponding to the point set from the emergency supervision object platform 150, constructs additional coordinate points based on the values ​​and time points of the additionally obtained target data, and fits the additional coordinate points to the original coordinate points to obtain a change curve.

[0092] In some embodiments, the preset time range and the preset number threshold can be pre-set by a technician based on needs or experience. In some embodiments, the preset number threshold is positively correlated with the geographic distribution breadth of the multiple target data. The geographic distribution breadth can be represented by the total number of geographic regions to which the multiple target data belong. The greater the geographic distribution breadth and the more complex the data patterns, the larger the preset data threshold.

[0093] In some embodiments, the emergency supervision management platform 130 may add the supplementary coordinate points to the point set, and perform fitting on each point set using a fitting model or fitting algorithm to obtain a change curve.

[0094] In some embodiments, the emergency supervision object platform 150 can use a data acquisition device to obtain additional target data for at least one time point within the time range corresponding to the point set. The time point corresponding to the additionally obtained target data is different from the original time point.

[0095] In some embodiments, for each target data, the emergency supervision management platform 130 may use the value of the target data corresponding to the current time point in the change curve of the target data and the first-order derivative of the change curve at the current time point as the data anomaly features of the target data.

[0096] In some embodiments, there is an association relationship between multiple target data. For each target data, the emergency supervision management platform 130 can also obtain at least one associated data of the target data and generate at least one associated data pair; based on the changes of at least one associated data pair within a preset period, determine at least one associated abnormal feature of at least one associated data pair; based on at least one associated abnormal feature, the data abnormal feature of the target data and the data criticality, determine the data emergency feature of the target data.

[0097] The existence of correlations between multiple target data indicates that they have a related impact on the same incident. For example, in the case of emergency monitoring of a gas system, in the event of a gas leak or gas blockage, gas temperature, gas flow rate, and other data are correlated with gas pressure.

[0098] Related data refers to data that is associated with the current target data.

[0099] In some embodiments, the emergency supervision management platform 130 may obtain associated data of the target data from the target sub-platform corresponding to the target data.

[0100] An associated data pair may include a pair of target data having an associated relationship.

[0101] In some embodiments, the emergency supervision management platform 130 may generate a plurality of associated data pairs based on the target data and the plurality of associated data of the target data.

[0102] In some embodiments, the associated data pair may further include associated accidents, and the emergency supervision management platform 130 may further generate at least one associated data pair based on the target data, at least one associated data of the target data, and at least one accident.

[0103] A correlated incident is an incident where the data in a correlated data pair have a common impact. For example, in emergency monitoring of a gas system, both gas pressure and gas temperature data have an impact on gas leaks and gas blockages. A correlated data pair consisting of gas pressure and gas temperature also includes gas leaks and gas blockages.

[0104] In some embodiments of the present specification, the associated data pairs also take into account specific associated accidents, so that the associated data pairs clearly reflect the association relationship between the target data, making the subsequent parameters determined based on the associated data pairs more accurate and reliable.

[0105] The abnormal correlation feature refers to a feature that indicates whether the associated data is in an abnormal state. For example, the abnormal correlation feature may include the value of the associated data or the change trend of the associated data.

[0106] The determination method of associated abnormal features is Figure 2 The method for determining abnormal data characteristics is the same as that in Figure 2 The relevant instructions will not be repeated here.

[0107] In some embodiments, the emergency supervision management platform 130 may determine the data emergency feature of the target data in a variety of ways based on at least one associated abnormality feature, the data abnormality feature of the target data, and the data criticality.

[0108] For example, the emergency supervision management platform 130 may use the weighted sum of the data criticality, the difference between the values ​​of multiple related data and the normal range, and the difference between the value of the target data and the normal range as the importance of the target data; based on the change trends of the multiple related data, update the change trend of the target data, and determine the change trend of the importance based on the change trend of the updated target data. For more information on how to determine the change trend of importance, please refer to Figure 2 and its related descriptions.

[0109] The emergency supervision management platform 130 can determine the change trend of the target data based on the change trends of the multiple related data through a fourth preset table. The fourth preset table includes a correspondence between the change trends of the related data and the change trends of the target data. The fourth preset table can be obtained by statistically analyzing historical data.

[0110] In some embodiments, the emergency supervision management platform 130 can determine the data emergency characteristics of the target data through the emergency prediction model. Figure 4 And related instructions.

[0111] In some embodiments of this specification, data emergency characteristics are determined based on associated abnormal characteristics, data abnormal characteristics of target data, and data criticality, which is conducive to improving the accuracy of data pairs, thereby improving risk assessment results and enhancing accident warning capabilities.

[0112] Step 320 : In response to the data anomaly characteristic satisfying a first preset condition, based on the target data and the data anomaly characteristic of the target data, determining display parameters of at least one display device within a preset area of ​​the target data.

[0113] The first preset condition includes a numerical range of the target data for sending the target data to the response sub-platform.

[0114] In some embodiments, the emergency supervision management platform 130 may use the division condition of the target data sent to the response sub-platform as the first preset condition.

[0115] The preset regional range refers to the geographical range within the geographical area to which the target data belongs.

[0116] In some embodiments, the preset area range may be pre-set by technicians based on experience.

[0117] A display device is a device used to display and alert abnormal situations. For example, a display device may include a warning light, a warning sign, etc. Multiple display devices may be set up in each geographical area.

[0118] Display parameters refer to the operating parameters of the display device. For example, display parameters may include the display frequency (such as the flashing frequency of a warning light) and display color of the display device.

[0119] In some embodiments, the emergency supervision management platform 130 can determine the display parameters of the display device by querying a fifth preset table based on the target data and data anomaly characteristics. The fifth preset table can include the target data, the data anomaly characteristics of the target data, and the corresponding display parameters (including display frequency and display color). The fifth preset table can be set by technical personnel based on historical data or experience.

[0120] Step 330: Generate an emergency risk avoidance instruction based on the display parameters, send the emergency risk avoidance instruction to the emergency supervision object platform, and control at least one display device to work according to the display parameters.

[0121] Emergency avoidance instructions are instructions for controlling the operation of a display device. In some embodiments, the emergency supervision management platform 130 can send the emergency avoidance instructions to the emergency supervision target platform 150 via the emergency supervision sensor network platform 140, thereby controlling the display device in the emergency supervision target platform 150 to operate according to the display parameters.

[0122] In some embodiments of the present specification, based on the changes in the target data within a preset period, the data anomaly characteristics of the target data are determined, and the display parameters of the target data are determined, and then an emergency avoidance instruction is generated, and the display device is sent and controlled to work, which is conducive to dynamically adjusting the display parameters, quickly generating and executing emergency avoidance instructions, improving emergency response efficiency, and improving the public's emergency avoidance capabilities.

[0123] It should be noted that the above description of process 300 is for illustration and purpose only and does not limit the scope of application of this specification. Those skilled in the art may make various modifications and changes to the process under the guidance of this specification. However, such modifications and changes are still within the scope of this specification.

[0124] In some embodiments, the emergency supervision management platform 130 may determine the data emergency feature of the target data through an emergency prediction model based on at least one associated abnormal feature, the target data, the data abnormal feature, and the data criticality.

[0125] The emergency prediction model refers to a model used to determine the data emergency characteristics of the target data. In some embodiments, the emergency prediction model can be a machine learning model, such as a deep neural network (DNN).

[0126] Figure 4 It is an exemplary schematic diagram of an emergency prediction model according to some embodiments of this specification.

[0127] In some embodiments, as Figure 4 As shown, the input of the emergency prediction model 420 may include at least one associated abnormality feature 411, target data 412, data abnormality feature 413 and data criticality 414, and the output may be a data emergency feature 430 of the target data.

[0128] In some embodiments, the emergency prediction model can be acquired by training a large number of training samples with training labels. A set of training samples may include multiple sample-associated abnormality features, sample target data, sample data abnormality features, and sample data criticality. The training labels corresponding to a set of training samples are the data emergency features of the sample target data.

[0129] Training samples can be determined based on historical data. Historical data includes historical correlation anomaly features, historical target data, historical data anomaly features, and historical data criticality. For each training sample, the emergency supervision management platform 130 can search the historical data to obtain multiple historical accidents at the historical time point of the sample target data corresponding to the training sample. The training labels are the weighted sum of the impact range and losses of the historical accidents (the weights can be preset based on experience), as well as the changing trend of the losses caused by the historical accidents in the next time period after the historical time point.

[0130] In some embodiments, the emergency supervision management platform 130 can perform multiple rounds of iterative training on the initial emergency prediction model based on multiple groups of training samples with training labels, and terminate the training when the iteration conditions are met to obtain a trained emergency prediction model. A round of iterative training includes: inputting a group of training samples with training labels into the initial emergency prediction model, determining the loss function value through the training labels and the output results of the initial emergency prediction model, and iteratively updating the parameters of the initial emergency prediction model based on the loss function value. The iteration method may include gradient descent method, etc. The iteration conditions may be that the loss function converges, the number of iterations reaches a preset number threshold, the loss function value is less than a preset function value threshold, etc.

[0131] In some embodiments of the present specification, the data emergency characteristics of the target data are determined by an emergency prediction model, and the influence of multiple factors (such as associated abnormal characteristics, target data, data abnormal characteristics, data criticality, etc.) on the data emergency characteristics is considered. This is conducive to utilizing the learning ability of the machine learning model to accurately predict the data emergency characteristics (including the importance of the target data and the changing trend of the importance), thereby improving the efficiency of emergency response.

[0132] Figure 5 This is an exemplary schematic diagram of sending network data packets according to some embodiments of this specification.

[0133] In some embodiments, as Figure 5As shown, the emergency supervision management platform 130 can obtain historical sensor data of sensors corresponding to target data, and the historical sensor data includes normal historical sensor data and abnormal historical sensor data; based on the historical sensor data and target data, determine the division conditions corresponding to the target data; based on the target data, the data anomaly characteristics of the target data and the division conditions, generate at least one network data packet and at least one network route; based on at least one network route, send at least one network data packet to at least one target sub-platform.

[0134] The sensor corresponding to the target data refers to the sensor used by the emergency supervision object platform 150 to obtain the target data.

[0135] Historical sensor data refers to target data acquired by the corresponding sensor at historical time points. Normal historical sensor data refers to relevant target data acquired before an accident. Abnormal historical sensor data refers to relevant target data acquired during an accident.

[0136] In some embodiments, the historical sensing data may include a preset amount of data acquired by the sensor during a historical accident occurrence period as the historical sensing data. The preset amount may be set as required.

[0137] In some embodiments, the emergency supervision object platform 150 can respectively count the upper and lower limits of multiple normal historical sensor data and multiple abnormal historical sensor data, and use the numerical range of the upper and lower limits of multiple normal historical sensor data as the numerical range of target data that needs to be sent to the monitoring sub-platform; use the intersection of the upper and lower limits of multiple normal historical sensor data and the upper and lower limits of multiple abnormal historical sensor data as the numerical range of target data that needs to be sent to the prevention sub-platform or the prevention sub-platform; use the numerical range of the upper and lower limits of multiple abnormal historical sensor data as the numerical range of target data that needs to be sent to the response sub-platform.

[0138] A network packet is the basic unit of network communication and includes a source address, a destination address, and the actual data to be transmitted (e.g., text, images, or video streams). Network routing refers to the process and path used to transmit a network packet from the emergency supervision target platform 150 to the target sub-platform.

[0139] In some embodiments, the emergency supervision object platform 150 can determine the target sub-platform to which the target data needs to be sent based on the target data, the data anomaly characteristics of the target data and the division conditions; based on the target sub-platform and the target data, generate a number of network data packets corresponding to the target sub-platform, and at least one network route for communicating with the target sub-platform.

[0140] In some embodiments of the present specification, determining the division conditions of target data based on historical sensor data can make the determined division conditions more accurate, so that the target data can be correctly allocated to the corresponding target sub-platform.

[0141] In some embodiments, the division condition also includes a division sub-condition of at least one accident corresponding to the target data. The emergency supervision object platform 150 can, for each of at least one accident: obtain the target data and at least one associated data corresponding to the accident; determine the division sub-condition corresponding to the accident based on the target data, the historical sensor data corresponding to the target data, and the associated historical sensor data corresponding to at least one associated data; determine at least one target sub-platform corresponding to the target data based on the data anomaly characteristics of the target data and the division sub-condition; generate at least one network data packet and at least one network route based on the target data, the data anomaly characteristics of the target data, and the corresponding at least one division sub-condition; and send at least one network data packet to at least one target sub-platform based on at least one network route.

[0142] How to obtain target data and related data refer to Figure 3 Related instructions.

[0143] The associated historical sensor data refers to target data collected by the sensor corresponding to the associated data at a historical point in time, including first sensor data and second sensor data. The first sensor data and second sensor data represent the target data collected by the sensor corresponding to the associated data at the time when an accident occurred and when no accident occurred, respectively.

[0144] In some embodiments, the emergency supervision object platform 150 can cluster the abnormal historical sensor data corresponding to a certain target data based on at least one accident corresponding to the target data. For each cluster obtained after clustering: obtain the first sensor data of multiple associated data corresponding to the abnormal historical sensor data in the cluster. If the collection period corresponding to the first sensor data is earlier than or partially earlier than the collection period corresponding to the abnormal historical sensor data, then add the first sensor data corresponding to the collection period earlier than the abnormal historical sensor data in the first sensor data to the abnormal historical sensor data and update it. For more information about abnormal historical sensor data, please refer to the previous article. Figure 5 Related instructions.

[0145] The division sub-condition refers to the division condition of the target data corresponding to different accidents. The division sub-condition may include the numerical range and change trend of the target data corresponding to different accidents divided into each target sub-platform.

[0146] In some embodiments, the emergency supervision object platform 150 can determine the sub-conditions for different accidents based on the upper and lower limits of historical normal sensor data and historical abnormal sensor data within each cluster. Figure 5 And related instructions.

[0147] In some embodiments, the emergency supervision management platform 130 can match the division sub-conditions based on the target data and data anomaly characteristics, determine the change trend of the target data and its numerical range in the division sub-conditions, and thus determine the target sub-platform to which the target data should be sent.

[0148] Methods for determining network data packets and network routes Figure 5 Similarly, see Figure 5 And related instructions.

[0149] In some embodiments of this specification, target data may be at different stages for different accidents. By dividing sub-conditions, the target data corresponding to different accidents can be specifically assigned to appropriate target sub-platforms. For some accidents, the target data has a lag. By considering the associated data and associated historical sensor data, the actual time period of the accident can be determined, thereby determining the target data's true value range at the time of the accident, and further determining the accurate sub-conditions for division.

[0150] In some embodiments, the emergency supervision management platform 130 can determine the abnormal duration distribution of the sensor based on historical sensor data; determine the accident stage of the target data based on historical sensor data and target data; determine the data upload parameters within the next preset period based on the target data, accident stage and abnormal duration distribution; generate sensor control instructions based on the data upload parameters, and send them to the emergency supervision object platform to control the sensor to work according to the data upload parameters.

[0151] For historical sensor data, see Figure 5 And related instructions.

[0152] The abnormal duration distribution includes the period during which the sensor continuously collects abnormal data (i.e., data when an accident occurs) and the corresponding abnormal data.

[0153] In some embodiments, the abnormal duration distribution can be obtained by statistically analyzing historical sensor data.

[0154] The accident stages include the initial stage, peak stage, calming stage and prevention stage.

[0155] In some embodiments, the emergency supervision management platform 130 can draw multiple candidate phase curves based on the abnormal historical sensor data corresponding to multiple accidents; perform weighted summation of the multiple candidate phase curves (the weights can be set based on experience) to determine the standard accident phase curve. The method of drawing the candidate phase curve is similar to that of the change curve, see Figure 3 And related instructions.

[0156] In some embodiments, the emergency supervision management platform 130 can determine the accident stage of the target data based on the value and change trend of the target data through the standard accident stage curve. If the value of the target data is within the value range corresponding to the first time period in the standard accident stage curve, the target data is in the peak stage of the accident. The first time period is a preset time period before and after the peak (set according to demand). If the value of the target data is within the value range corresponding to the second time period in the standard accident stage curve, the target data is in the initial stage of the accident or the accident calming stage. The second time period is a time period away from the peak, and the second time period can be a time period in the standard accident stage curve other than the first time period. If the value of the target data is not within the value range in the standard accident stage curve, the target data is in the accident prevention stage.

[0157] Data upload parameters include the upload frequency and upload volume of target data.

[0158] In some embodiments, the emergency supervision management platform 130 can determine data upload parameters for the next preset period by searching a sixth preset table based on the target data, accident stage, and abnormal duration distribution. The sixth preset table includes a correspondence between the target data, accident stage, and abnormal duration distribution and the data upload parameters. The sixth preset table can be preset by a technician.

[0159] The sensor control instruction is used to adjust the uploaded parameters of the sensor.

[0160] Considering the abnormal duration distribution and accident stage, adjusting the data upload parameters of the sensor in the next cycle can make the parameters collected and uploaded by the sensor more in line with actual needs, thereby improving the parameter collection efficiency of the sensor.

[0161] In some embodiments, a display element is provided on the rescue vehicle and / or the power supply vehicle. The emergency supervision management platform 130 can generate a display instruction based on the accident stage of the target data and send it to the emergency supervision object platform to control the display element to work based on the display instruction.

[0162] The display element is a component used to display the accident situation. The display element can be a warning light or the like.

[0163] Display instructions are instructions for controlling the operation of display components. Display instructions include the display frequency and display color of the display components.

[0164] In some embodiments, the emergency supervision and management platform 130 can determine different display modes for displaying the original document according to the accident stage using the seventh preset table and convert the different display modes into display instructions. Different display modes correspond to different display frequencies and / or display colors. The seventh preset table includes display modes corresponding to different accident stages. The seventh preset table can be configured as needed.

[0165] By setting up display elements to show different accident stages, timely and accurate warnings of accident occurrences can be provided, thereby facilitating timely investigation and handling of the accident.

[0166] 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.

[0167] This specification also uses specific terms to describe the embodiments of this specification. For example, "some embodiments" refers to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that mentioning "some embodiments" two or more times in different places in this specification does not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics in one or more embodiments of this specification may be appropriately combined.

[0168] Furthermore, the order of the processing elements and sequences, the use of alphanumeric characters, or other designations described in this specification are not intended to limit the order of the processes and laminar flow hoods described herein. While the system components described above can be implemented using hardware devices, they can also be implemented using software-only solutions, such as by installing the described system on an existing server or mobile device.

[0169] Similarly, it should be noted that in order to simplify the description disclosed in this specification and facilitate understanding of one or more embodiments of the invention, the foregoing description of the invention sometimes combines multiple features into a single embodiment, figure, or description thereof. In reality, the features of an embodiment may be less than all the features of a single embodiment disclosed above.

[0170] In some embodiments, the numerical parameters used in the specification are approximate values, which may vary depending on the desired characteristics of individual embodiments. In some embodiments, numerical parameters should take into account the specified significant digits and adopt a general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0171] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the present invention. Other variations are also possible within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the present invention 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 split emergency management method based on the Internet of Things large model, characterized by: Executed based on the emergency supervision management platform, including: Through the emergency supervision sensor network platform, multiple target data are obtained from the emergency supervision object platform based on a preset period. The target data include gas temperature, gas pressure, gas flow rate, combustible gas concentration or toxic gas concentration, the size of the crowd around the pipeline, the number of flammable and explosive items, and the duration of gas outage; For each target data in the plurality of target data: determining, based on the target data, at least one accident corresponding to the target data; Based on the target data, the data type and geographical area of ​​the target data, and the at least one accident, searching a second preset table to obtain the development speed, degree of harm, importance of the data type, and importance of the geographical area of ​​each of the at least one accident, and taking a weighted sum of the obtained values ​​as the data criticality of the target data; Acquire at least one associated data of the target data and generate at least one associated data pair; Determining at least one abnormal correlation feature of the at least one associated data pair based on a change in the at least one associated data pair within a preset period; Determining the data emergency feature of the target data by an emergency prediction model based on the at least one associated abnormal feature, the data abnormal feature of the target data, and the data criticality; the emergency prediction model is a machine learning model; Determining at least one target sub-platform corresponding to the target data based on the target data, the data anomaly characteristics, and a division condition corresponding to the target data; Acquiring, from the at least one target sub-platform, an emergency type and emergency severity within the geographical area corresponding to the target data; determining an emergency parameter based on the emergency type, the emergency degree, and the data emergency characteristics of the plurality of target data within the geographic area; determining operating parameters of a rescue vehicle based on the emergency level in the geographical area, the emergency parameters, and the data emergency characteristics of the plurality of target data; Generate a dispatch instruction based on the emergency parameters and the working parameters, and send the dispatch instruction to the emergency supervision object platform, Based on the emergency supervision object platform, the rescue vehicle is controlled to drive to the geographical area, and the rescue vehicle is controlled to work based on the emergency parameters and the working parameters.

2. The method according to claim 1, wherein The method further comprises: Determining the data anomaly feature of the target data based on changes in the target data within a preset period; In response to the data anomaly characteristic satisfying a first preset condition, determining, based on the target data and the data anomaly characteristic of the target data, a display parameter of at least one display device within a preset area of ​​the target data; An emergency risk avoidance instruction is generated based on the display parameters, and the emergency risk avoidance instruction is sent to the emergency supervision object platform, and the at least one display device is controlled to operate according to the display parameters.

3. The method according to claim 1, wherein The method further comprises: Acquiring historical sensor data of a sensor corresponding to the target data, wherein the historical sensor data includes normal historical sensor data and abnormal historical sensor data; Determining the division condition corresponding to the target data based on the historical sensor data and the target data; generating at least one network data packet and at least one network route based on the target data, the data anomaly characteristics of the target data, and the partitioning condition; Based on the at least one network route, the at least one network data packet is sent to the at least one target sub-platform.

4. The method according to claim 3, wherein The division condition further includes a division sub-condition of the at least one accident corresponding to the target data, and the method further includes: For each of the at least one incident: Acquire target data and at least one associated data corresponding to the accident; determining the division sub-condition corresponding to the accident based on the target data, the historical sensor data corresponding to the target data, and the associated historical sensor data corresponding to the at least one associated data corresponding to the accident; Determining the at least one target sub-platform corresponding to the target data based on the data anomaly feature of the target data and the division sub-condition; generating the at least one network data packet and the at least one network route based on the target data, the data anomaly feature of the target data, and the corresponding at least one partitioning sub-condition; Based on the at least one network route, the at least one network data packet is sent to the at least one target sub-platform.

5. A smart city centralized emergency management system based on the Internet of Things large model, characterized by: It includes the emergency supervision management platform, the emergency supervision sensor network platform and the emergency supervision object platform; The emergency supervision management platform is configured to: Acquiring multiple target data from the emergency supervision object platform based on a preset period through the emergency supervision sensor network platform, the target data including gas temperature, gas pressure, gas flow rate, combustible gas concentration or toxic gas concentration, the size of the crowd around the pipeline, the number of flammable and explosive items, and the duration of the gas outage; For each target data in the plurality of target data: determining, based on the target data, at least one accident corresponding to the target data; Based on the target data, the data type and geographical area of ​​the target data, and the at least one accident, searching a second preset table to obtain the development speed, degree of harm, importance of the data type, and importance of the geographical area of ​​each of the at least one accident, and taking a weighted sum of the obtained values ​​as the data criticality of the target data; Acquire at least one associated data of the target data and generate at least one associated data pair; Determining at least one associated abnormal feature of the at least one associated data pair based on changes in the at least one associated data pair within a preset period; Determining the data emergency feature of the target data by an emergency prediction model based on the at least one associated abnormal feature, the data abnormal feature of the target data, and the data criticality, wherein the emergency prediction model is a machine learning model; Determining at least one target sub-platform corresponding to the target data based on the target data, the data anomaly characteristics, and a division condition corresponding to the target data; Obtaining, from the at least one target sub-platform, an emergency type and emergency severity within the geographical area corresponding to the target data; determining an emergency parameter based on the emergency type, the emergency degree, and the data emergency characteristics of the plurality of target data within the geographic area; determining operating parameters of a rescue vehicle based on the emergency level in the geographical area, the emergency parameters, and the data emergency characteristics of the plurality of target data; Generate a dispatch instruction based on the emergency parameter and the working parameter, and send the dispatch instruction to the emergency supervision object platform; Based on the emergency supervision object platform, the rescue vehicle is controlled to drive to the geographical area, and the rescue vehicle is controlled to work based on the emergency parameters and the working parameters.

6. The system according to claim 5, wherein: The system also includes an emergency supervision user platform and an emergency supervision service platform. The emergency supervision user platform, the emergency supervision management platform, the emergency supervision service platform, the emergency supervision sensor network platform and the emergency supervision object platform are communicatively connected in sequence.

7. The system according to claim 5, wherein: The emergency supervision management platform is further configured to: Determining the data anomaly feature of the target data based on changes in the target data within a preset period; In response to the data anomaly characteristic satisfying a first preset condition, determining, based on the target data and the data anomaly characteristic of the target data, a display parameter of at least one display device within a preset area of ​​the target data; An emergency risk avoidance instruction is generated based on the display parameters, and the emergency risk avoidance instruction is sent to the emergency supervision object platform, and the at least one display device is controlled to operate according to the display parameters.

8. The system according to claim 5, wherein: The emergency supervision management platform is further configured to: Acquiring historical sensor data of a sensor corresponding to the target data, wherein the historical sensor data includes normal historical sensor data and abnormal historical sensor data; Determining the division condition corresponding to the target data based on the historical sensor data and the target data; generating at least one network data packet and at least one network route based on the target data, the data anomaly characteristics of the target data, and the partitioning condition; Based on the at least one network route, the at least one network data packet is sent to the at least one target sub-platform.

Images