A high-speed emergency control management method and system

Abstract

The present invention provides a high-speed emergency deployment and management method and system, which relate to the technical field of highway management. The present invention directly obtains emergency task information from a task release center system and processes diversified data sources in real time, thereby achieving efficient task response. At the same time, the present invention utilizes a pre-built event association prediction model and a department association model for intelligent prediction and evaluation, which can accurately estimate the probability of an unexpected event and the probability of a backup department to be executed. On this basis, by calculating the weights of the backup execution departments and dividing the waiting order levels, the rational allocation of emergency resources is achieved, ensuring that key departments can respond quickly at critical moments. These measures jointly ensure the rapidity, accuracy and efficiency of emergency handling.

Description

Technical Field

[0001] The present invention relates to the technical field of highway management, and in particular to a highway emergency control management method and system. Background Art

[0002] In highway emergency management, response speed is a key factor in determining rescue effectiveness. However, traditional emergency management methods often rely on communication tools such as telephones and walkie-talkies to transmit information. This results in a long and complex information transmission chain, which is prone to information delays and distortion. Furthermore, the deployment of emergency resources often relies on manual coordination, making it difficult to quickly assemble and deploy resources in a short period of time.

[0003] Traditional emergency management approaches often lack scientific forecasting models and assessment methods, resulting in low forecast accuracy and difficulty in accurately determining the development trend and potential impact of emergency events. This introduces significant uncertainty into emergency decision-making, increasing the difficulty and risk of emergency management.

[0004] In highway emergency management, the rational allocation of resources is crucial for ensuring effective rescue operations. However, traditional emergency management approaches often rely on empirical judgment to allocate resources, lacking scientific methods and standards. This often leads to resource shortages or waste during emergencies, compromising rescue effectiveness.

[0005] Therefore, it is necessary to provide a high-speed emergency control management method and system to solve the above technical problems. Summary of the Invention

[0006] In order to solve the above technical problems, the present invention provides a high-speed emergency control management method and system for solving the problem that the traditional emergency management model often relies on manual coordination for the allocation of emergency resources, making it difficult to quickly assemble and deploy resources in a short period of time, and difficult to accurately judge the development trend and possible impact range of emergency events, resulting in difficulty and high risk in emergency management.

[0007] The present invention provides a high-speed emergency control management method, which includes the following steps:

[0008] S100, obtaining the current emergency task information and the corresponding execution plan from the task release center system, and extracting the key semantic information of the current emergency task information;

[0009] S200, acquiring and preprocessing diversified data in real time, wherein the diversified data sources include but are not limited to traffic monitoring data, environmental sensor data, vehicle GPS data, and social media data;

[0010] S300, based on the acquired current emergency task information, extracting data related to the current emergency task information from the pre-processed diversified data through parallel processing, and determining whether the current emergency task information is accurate;

[0011] S400: In response to determining that the current emergency task information is accurate, the probability of an unexpected event occurring and the probability of a backup department being executed are analyzed and estimated based on key semantic information of the current emergency task information using a pre-built event association prediction model and a department association model;

[0012] S500: Based on the estimated probability of the unexpected event occurring and the probability of the relevant departments being ready for execution, the weights of the backup execution departments are obtained by multiplication, and the reserve execution departments are classified into waiting levels;

[0013] S600, transmitting the emergency task information, execution target and the information on the standby level of the backup execution department to the corresponding execution department and the backup execution department;

[0014] S700. Each execution department receives the current emergency task information and the corresponding execution plan and executes it. The backup execution department waits for orders according to the waiting order level.

[0015] Preferably, the step S100 specifically includes the following steps:

[0016] S101. Establish a connection with the task release center system to obtain the current emergency task information and its corresponding execution plan in real time;

[0017] S102. Utilize semantic analysis technology to extract key semantic information from the acquired current emergency task information and execution plan, specifically including task type, location, time requirement, and urgency.

[0018] Preferably, the step S200 specifically includes the following steps:

[0019] S201, real-time collection of diverse data including traffic surveillance videos, environmental sensor, data, vehicle GPS positioning information, and social media;

[0020] S202: Clean, denoise, and unify the format of the collected diversified data to obtain pre-processed diversified data, and store it in a distributed database.

[0021] Preferably, the step S300 specifically includes the following steps:

[0022] S301, presetting multiple processing sub-cards, and using the multiple processing sub-cards to simultaneously scan pre-processed diversified data from different sources, extracting data information directly related to the current emergency task information, and obtaining relevant data;

[0023] S302: Compare the current emergency task information with the extracted relevant data to determine whether the description of the current emergency task information truly reflects the current situation;

[0024] S303: If it is determined that the description of the current emergency task information truly reflects the current situation, the task information is confirmed to be accurate; otherwise, the task information is marked as inaccurate.

[0025] Preferably, in step S400, the specific steps of constructing the event association prediction model are:

[0026] Collect historical emergency task data, including emergency task information, related event records, execution department records, and execution results, and clean them;

[0027] Extract features related to emergency tasks from the cleaned historical emergency task data, including event type, occurrence time, location, weather conditions, and traffic conditions;

[0028] Identify the mapping relationship between each feature and the corresponding accident through data statistical analysis and use it as a training set;

[0029] A classification algorithm model is adopted, and the mapping relationship between each feature and the corresponding accident is used as a training set to train the classification algorithm model to obtain an event association prediction model.

[0030] Preferably, in step S400, the specific steps of constructing the department association model are:

[0031] Collect historical emergency task data, including emergency task information, related event records, execution department records, and execution results, and clean them;

[0032] Extract the characteristics of department type, historical response time, resource allocation, and personnel experience from the cleaned historical emergency task data;

[0033] Use the correlation analysis algorithm to analyze the correlation between the extracted department type, historical response time, resource allocation, and personnel experience characteristics, and use the corresponding relationship between the analysis results and the characteristics as the training set

[0034] The association rule mining algorithm model is adopted to train the association rule mining algorithm model by using the corresponding relationship between the analysis results and the features as the training set to obtain the department association model.

[0035] Preferably, the specific steps of step S500 are:

[0036] S501: Outputs of the event correlation prediction model and the department correlation model are based on the probability values ​​of the unexpected event and the probability values ​​of the backup department to be executed;

[0037] S502: Multiply the estimated probability value of the unexpected event by the probability value of the relevant department to be executed, and calculate the weight of the backup execution department;

[0038] S503. Sort the weights of the backup execution departments according to the calculated weights, and divide the weight values ​​into different intervals, specifically, a first-level weight interval, a second-level weight interval, and a third-level weight interval;

[0039] S504: According to the result of dividing the weight values ​​into different intervals, corresponding waiting levels are set, specifically, level one waiting, level two waiting, and level three waiting.

[0040] Preferably, in step S700, the specific steps for the backup execution department to wait for orders according to the waiting order level are:

[0041] Each backup execution department receives a corresponding level of standby orders. Among them, a department that receives a level one standby order is a level one standby department, which keeps more than 70% of the personnel and equipment and tools in the department in a ready state; a department that receives a level two standby order is a level two standby department, which keeps more than 40% of the personnel and equipment and tools in the department in a ready state; a department that receives a level three standby order is a level three standby department, which keeps more than 20% of the personnel and equipment and tools in the department in a ready state.

[0042] A high-speed emergency control management system, comprising:

[0043] The management system includes:

[0044] The task acquisition module is used to obtain the current emergency task information and the corresponding execution plan from the task release center system, and extract the key semantic information in the current emergency task information and the execution plan;

[0045] A data acquisition module, which is used to acquire and pre-process diversified data in real time. The diversified data sources include but are not limited to traffic monitoring data, environmental sensor data, vehicle GPS data, and social media data;

[0046] The task judgment module is used to extract data related to the current emergency task information from the pre-processed diversified data through parallel processing based on the current emergency task information obtained, and judge whether the current emergency task information is accurate;

[0047] The prediction module is used to analyze and estimate the probability of an unexpected event occurring and the probability of a backup department being executed based on the key semantic information of the current emergency task information and the pre-built event association prediction model and department association model in response to the result that the current emergency task information is accurate;

[0048] The level classification module is used to obtain the weight of the backup execution department by multiplying the estimated probability of the accident and the probability of the relevant department to be executed, and classify the reserve execution department's waiting level;

[0049] An information transmission module is used to transmit emergency task information, execution targets, and information on the waiting level of backup execution departments to corresponding execution departments and backup execution departments;

[0050] The instruction receiving module is used for each execution department to receive the current emergency task information and the corresponding execution plan for execution, and the backup execution department is on standby according to the waiting order level.

[0051] Compared with related technologies, the high-speed emergency control management method and system provided by the present invention have the following beneficial effects:

[0052] The present invention achieves efficient task response by directly obtaining emergency task information from the task release center system and processing diversified data sources in real time. At the same time, it uses pre-built event association prediction models and department association models for intelligent prediction and evaluation, which can accurately estimate the probability of unexpected events and the probability of backup departments waiting for execution. On this basis, by calculating the weights of backup execution departments and dividing the waiting order levels, it achieves the rational allocation of emergency resources and ensures that key departments can respond quickly at critical moments. These measures jointly ensure the rapidity, accuracy and efficiency of emergency handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 This is a flow chart of a high-speed emergency control management method of the present invention;

[0054] Figure 2 This is a system block diagram of a high-speed emergency control and management system of the present invention. DETAILED DESCRIPTION

[0055] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0056] Example 1

[0057] like Figure 1 As shown, a high-speed emergency control management method includes the following steps:

[0058] S100, obtaining the current emergency task information and the corresponding execution plan from the task release center system, and extracting the key semantic information in the current emergency task information and the execution plan;

[0059] In the specific implementation process, step S100 specifically includes the following steps:

[0060] S101. Establish a connection with the task release center system to obtain the current emergency task information and its corresponding execution plan in real time;

[0061] Specifically, through the docking of API, or application programming interface, it is ensured that the two systems can exchange data in real time. During the interface docking process, the format, encryption method, and verification mechanism of data transmission are agreed upon to ensure the security and accuracy of data transmission. When the task release center system responds to the request or actively pushes it, it receives a data packet containing the current emergency task information and its corresponding execution plan. The data packet contains detailed information such as the task number, task description, location coordinates, time requirements, and degree of urgency.

[0062] S102. Using semantic analysis technology, extract key semantic information from the acquired current emergency task information and execution plan, specifically including task type, location, time requirement, and urgency;

[0063] Specifically, the received task information and execution plan text are first preprocessed, including removing irrelevant characters and word segmentation steps for subsequent processing. Then, the semantic analysis technology in natural language processing (NLP) is used to analyze the preprocessed text to obtain analysis results. According to the existing emergency management requirements standards, key semantic information is extracted from the analysis results. For high-speed tunnel emergency tasks, key semantic information includes but is not limited to task type (such as traffic accident handling), location (specific tunnel location and accident point), time requirements (such as immediate response), urgency, etc.

[0064] For example, through semantic analysis technology, the following key semantic information is successfully extracted from the task information and execution plan: the task type is "traffic accident handling", the location is "XX Expressway Tunnel K50+300", the time requirement is "immediate response", and the urgency is "high".

[0065] S200, acquiring and preprocessing diversified data in real time, wherein the diversified data sources include but are not limited to traffic monitoring data, environmental sensor data, vehicle GPS data, and social media data;

[0066] In the specific implementation process, step S200 specifically includes the following steps:

[0067] S201, real-time collection of diverse data including traffic surveillance videos, environmental sensor, data, vehicle GPS positioning information, and social media;

[0068] S202: Clean, remove noise, and unify the format of the collected diversified data to obtain pre-processed diversified data, and store it in a distributed database;

[0069] Specifically, the collected diversified data will be identified and invalid data will be deleted, such as duplicate data, null data, and obviously erroneous data (such as timestamp anomalies, geographic location outside the tunnel range, etc.). Then, the video data will be compressed and encoded to save storage space and speed up subsequent processing. The social media data will then be preprocessed, such as removing irrelevant tags and emoticons. After preprocessing, it will be stored in a distributed database.

[0070] S300, based on the acquired current emergency task information, extracting data related to the current emergency task information from the pre-processed diversified data through parallel processing, and determining whether the current emergency task information is accurate;

[0071] In the specific implementation process, step S300 specifically includes the following steps:

[0072] S301, presetting multiple processing sub-cards, and using the multiple processing sub-cards to simultaneously scan pre-processed diversified data from different sources, extracting data information directly related to the current emergency task information, and obtaining relevant data;

[0073] Specifically, according to the different data types and sources, multiple specialized processing sub-cards are designed. Each processing sub-card is responsible for scanning data of a specific type or source and extracting key information related to the current emergency task information. Then, using multi-core processors or distributed computing resources, multiple processing sub-cards are started at the same time for parallel processing, scanning pre-processed diversified data from different sources, and extracting data information directly related to the current emergency task information from the pre-processed data.

[0074] For example, the video processing sub-card can identify the type, number, and human activities of vehicles at the accident scene; the environmental data processing sub-card can monitor changes in environmental parameters such as smoke concentration and temperature; and the GPS processing sub-card can track the driving trajectory and speed changes of vehicles around the accident.

[0075] S302: Compare the current emergency task information with the extracted relevant data to determine whether the description of the current emergency task information truly reflects the current situation;

[0076] Specifically, the description in the current emergency task information is compared with the extracted relevant data one by one to determine whether the accident type, location, time, impact range, etc. are consistent with the information in the data report.

[0077] S303: If it is determined that the description of the current emergency task information truly reflects the current situation, the task information is confirmed to be accurate; otherwise, the task information is marked as inaccurate.

[0078] S400: In response to determining that the current emergency task information is accurate, the probability of an unexpected event occurring and the probability of a backup department being executed are analyzed and estimated based on key semantic information of the current emergency task information using a pre-built event association prediction model and a department association model;

[0079] In the specific implementation process, step S400 specifically includes the following steps:

[0080] S401, extracting event type, occurrence time, location, weather conditions, and traffic status characteristics from key semantic information of the current emergency task information;

[0081] S402: Input the extracted event type, occurrence time, location, weather conditions, and traffic status characteristics into an event correlation prediction model, and output a probability value of the accident occurrence.

[0082] S403. Extracting features of department type, historical response time, resource allocation, and personnel experience from key semantic information of the current emergency task information;

[0083] S403: Input the extracted department type, historical response time, resource allocation status, and personnel experience characteristics into the department association model, and output the probability value of the backup department to be executed.

[0084] S500: Based on the estimated probability of the unexpected event occurring and the probability of the relevant departments being ready for execution, the weights of the backup execution departments are obtained by multiplication, and the reserve execution departments are classified into waiting levels;

[0085] In the specific implementation process, step S500 specifically includes the following steps:

[0086] S501: Outputs of the event correlation prediction model and the department correlation model are based on the probability values ​​of the unexpected event and the probability values ​​of the backup department to be executed;

[0087] S502: Multiply the estimated probability value of the unexpected event by the probability value of the relevant department to be executed, and calculate the weight of the backup execution department;

[0088] Specifically, for each backup execution department, its weight = probability of an accident occurring × probability of the department to be executed. For example, if the current task is to handle a serious traffic accident occurring on a highway, the event association prediction model outputs a probability of an accident occurring of 80%, the department association model outputs a probability of the traffic police department to be executed of 90%, and a probability of the medical rescue department to be executed of 85%, then the weight of the traffic police department = 80% × 90% = 72%, and the weight of the medical rescue department = 80% × 85% = 68%.

[0089] S503. Sort the weights of the backup execution departments according to the calculated weights, and divide the weight values ​​into different intervals, specifically, a first-level weight interval, a second-level weight interval, and a third-level weight interval;

[0090] Specifically, based on the sorting results and the preset division criteria, this implementation uses percentage range as the division criteria, dividing weight values ​​above 70% into the first-level weight interval, weight values ​​between 50% and 70% into the second-level weight interval, and weight values ​​below 50% into the third-level weight interval.

[0091] S504: According to the result of dividing the weight values ​​into different intervals, corresponding waiting levels are set, specifically, level one waiting, level two waiting, and level three waiting.

[0092] Specifically, for departments in the first-level weight range, they are set to level one on standby, which means that these departments need to immediately prepare for emergency response; for departments in the second-level weight range, they are set to level two on standby, which means that these departments need to pay close attention and be ready to respond at any time; for departments in the third-level weight range, they are set to level three on standby, which means that these departments can maintain normal working status but also need to pay attention to emergency situations.

[0093] S700: Each execution department receives the current emergency task information and the corresponding execution plan and executes it. The backup execution department waits for orders according to the waiting order level.

[0094] In the specific implementation process, in step S700, the specific steps for the backup execution department to wait for orders according to the waiting order level are as follows:

[0095] Each backup execution department receives a corresponding level of standby orders. Among them, a department that receives a level one standby order is a level one standby department, which keeps more than 70% of the personnel and equipment and tools in the department in a ready state; a department that receives a level two standby order is a level two standby department, which keeps more than 40% of the personnel and equipment and tools in the department in a ready state; a department that receives a level three standby order is a level three standby department, which keeps more than 20% of the personnel and equipment and tools in the department in a ready state.

[0096] Example 2

[0097] like Figure 2 As shown, a high-speed emergency control management system applied to a high-speed emergency control management method specifically includes:

[0098] The task acquisition module is used to obtain the current emergency task information and the corresponding execution plan from the task release center system, and extract the key semantic information in the current emergency task information and the execution plan;

[0099] A data acquisition module, which is used to acquire and pre-process diversified data in real time. The diversified data sources include but are not limited to traffic monitoring data, environmental sensor data, vehicle GPS data, and social media data;

[0100] The task judgment module is used to extract data related to the current emergency task information from the pre-processed diversified data through parallel processing based on the current emergency task information obtained, and judge whether the current emergency task information is accurate;

[0101] The prediction module is used to analyze and estimate the probability of an unexpected event occurring and the probability of a backup department being executed based on the key semantic information of the current emergency task information and the pre-built event association prediction model and department association model in response to the result that the current emergency task information is accurate;

[0102] The level classification module is used to obtain the weight of the backup execution department by multiplying the estimated probability of the accident and the probability of the relevant department to be executed, and classify the reserve execution department's waiting level;

[0103] An information transmission module is used to transmit emergency task information, execution targets, and information on the waiting level of backup execution departments to corresponding execution departments and backup execution departments;

[0104] The instruction receiving module is used for each execution department to receive the current emergency task information and the corresponding execution plan for execution, and the backup execution department is on standby according to the waiting order level.

[0105] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0106] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0107] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

Claims

1. A high-speed emergency control management method, characterized in that: The management method comprises the following steps: S100, obtaining the current emergency task information and the corresponding execution plan from the task release center system, and extracting the key semantic information of the current emergency task information; S200, acquiring and preprocessing diversified data in real time, wherein the diversified data sources include but are not limited to traffic monitoring data, environmental sensor data, vehicle GPS data, and social media data; S300, based on the acquired current emergency task information, extracting data related to the current emergency task information from the pre-processed diversified data through parallel processing, and determining whether the current emergency task information is accurate; S400: In response to determining that the current emergency task information is accurate, the probability of an unexpected event occurring and the probability of a backup department being executed are analyzed and estimated based on key semantic information of the current emergency task information using a pre-built event association prediction model and a department association model; S500: Based on the estimated probability of the unexpected event occurring and the probability of the relevant departments being ready for execution, the weights of the backup execution departments are obtained by multiplication, and the reserve execution departments are classified into waiting levels; S600, transmitting the emergency task information, execution target and the information on the standby level of the backup execution department to the corresponding execution department and the backup execution department; S700: Each execution department receives the current emergency task information and the corresponding execution plan and executes it. The backup execution department stands by according to the waiting level. In step S400, the specific steps of constructing the event association prediction model are: Collect historical emergency task data, including emergency task information, related event records, execution department records, and execution results, and clean it. Extract features associated with the emergency tasks from the cleaned historical emergency task data, specifically including event type, occurrence time, location, weather conditions, and traffic conditions. Identify the mapping relationship between each feature and the corresponding accident through data statistical analysis and use this as a training set. Use a classification algorithm model to train the classification algorithm model using the mapping relationship between each feature and the corresponding accident as the training set to obtain an event association prediction model. In step S400, the specific steps of constructing the department association model are: Collect historical emergency task data, including emergency task information, related event records, execution department records and execution results, and clean them; extract department type, historical response time, resource allocation, and personnel experience characteristics from the cleaned historical emergency task data; use the correlation analysis algorithm to perform correlation analysis on the extracted department type, historical response time, resource allocation, and personnel experience characteristics, and use the corresponding relationship between the analysis results and the characteristics as a training set; use the association rule mining algorithm model, and use the corresponding relationship between the analysis results and the characteristics as a training set to train the association rule mining algorithm model to obtain a department association model.

2. A high-speed emergency control management method according to claim 1, characterized in that: The step S100 specifically includes the following steps: S101. Establish a connection with the task release center system to obtain the current emergency task information and its corresponding execution plan in real time; S102. Utilize semantic analysis technology to extract key semantic information from the acquired current emergency task information and execution plan, specifically including task type, location, time requirement, and urgency.

3. A high-speed emergency control management method according to claim 1, characterized in that: The step S200 specifically includes the following steps: S201, real-time collection of diverse data including traffic surveillance videos, environmental sensor, data, vehicle GPS positioning information, and social media; S202: Clean, denoise, and unify the format of the collected diversified data to obtain pre-processed diversified data, and store it in a distributed database.

4. A high-speed emergency control management method according to claim 1, characterized in that: The step S300 specifically includes the following steps: S301, presetting multiple processing sub-cards, and using the multiple processing sub-cards to simultaneously scan pre-processed diversified data from different sources, extracting data information directly related to the current emergency task information, and obtaining relevant data; S302: Compare the current emergency task information with the extracted relevant data to determine whether the description of the current emergency task information truly reflects the current situation; S303: If it is determined that the description of the current emergency task information truly reflects the current situation, the task information is confirmed to be accurate; otherwise, the task information is marked as inaccurate.

5. A high-speed emergency control management method according to claim 1, characterized in that: The specific steps of step S500 are: S501: Outputs of the event correlation prediction model and the department correlation model are based on the probability values ​​of the unexpected event and the probability values ​​of the backup department to be executed; S502: Multiply the estimated probability value of the unexpected event by the probability value of the relevant department to be executed, and calculate the weight of the backup execution department; S503. Sort the weights of the backup execution departments according to the calculated weights, and divide the weight values ​​into different intervals, specifically, a first-level weight interval, a second-level weight interval, and a third-level weight interval; S504: According to the result of dividing the weight values ​​into different intervals, corresponding waiting levels are set, specifically, level one waiting, level two waiting, and level three waiting.

6. A high-speed emergency control management method according to claim 1, characterized in that: In step S700, the specific steps for the backup execution department to stand by according to the waiting order level are as follows: Each backup execution department receives a corresponding level of standby orders. Among them, a department that receives a level one standby order is a level one standby department, which keeps more than 70% of the personnel and equipment and tools in the department in a ready state; a department that receives a level two standby order is a level two standby department, which keeps more than 40% of the personnel and equipment and tools in the department in a ready state; a department that receives a level three standby order is a level three standby department, which keeps more than 20% of the personnel and equipment and tools in the department in a ready state.

7. A high-speed emergency control management system, applied to a high-speed emergency control management method according to any one of claims 1 to 6, characterized in that: The management system includes: The task acquisition module is used to obtain the current emergency task information and the corresponding execution plan from the task release center system, and extract the key semantic information in the current emergency task information and the execution plan; A data acquisition module, which is used to acquire and pre-process diversified data in real time. The diversified data sources include but are not limited to traffic monitoring data, environmental sensor data, vehicle GPS data, and social media data; The task judgment module is used to extract data related to the current emergency task information from the pre-processed diversified data through parallel processing based on the current emergency task information obtained, and judge whether the current emergency task information is accurate; The prediction module is used to analyze and estimate the probability of an unexpected event occurring and the probability of a backup department being executed based on the key semantic information of the current emergency task information and the pre-built event association prediction model and department association model in response to the result that the current emergency task information is accurate; The level classification module is used to obtain the weight of the backup execution department by multiplying the estimated probability of the accident and the probability of the relevant department to be executed, and classify the reserve execution department's waiting level; An information transmission module is used to transmit emergency task information, execution targets, and information on the waiting level of backup execution departments to corresponding execution departments and backup execution departments; The command receiving module is used for each execution department to receive the current emergency task information and the corresponding execution plan for execution, and the backup execution department is on standby according to the waiting order level; The specific steps of constructing the event association prediction model are: Collect historical emergency task data, including emergency task information, related event records, execution department records, and execution results, and clean it. Extract features associated with the emergency tasks from the cleaned historical emergency task data, specifically including event type, occurrence time, location, weather conditions, and traffic conditions. Identify the mapping relationship between each feature and the corresponding accident through data statistical analysis and use this as a training set. Use a classification algorithm model to train the classification algorithm model using the mapping relationship between each feature and the corresponding accident as the training set to obtain an event association prediction model. The specific steps of constructing the department association model are: Collect historical emergency task data, including emergency task information, related event records, execution department records and execution results, and clean them; extract department type, historical response time, resource allocation, and personnel experience characteristics from the cleaned historical emergency task data; use the correlation analysis algorithm to perform correlation analysis on the extracted department type, historical response time, resource allocation, and personnel experience characteristics, and use the corresponding relationship between the analysis results and the characteristics as a training set; use the association rule mining algorithm model, and use the corresponding relationship between the analysis results and the characteristics as a training set to train the association rule mining algorithm model to obtain a department association model.

Images