Emergency command and dispatch method based on artificial intelligence

Abstract

The invention relates to the technical field of scheduling, in particular to an emergency command scheduling method based on artificial intelligence, and the method comprises the steps: obtaining the real-time operation data, emergency information and real-time scheduling demands of each train in a rail transit system; determining a first emergency response degree and a second emergency response degree; determining an emergency event; calculating the emergency scheduling matching degree of the executable emergency scheduling scheme; obtaining a scheduling distance of a rescue point corresponding to the executable emergency scheduling scheme; acquiring a nearest rescue point in front of the track advancing route of the emergency site; and determining an optimal emergency scheduling scheme based on the emergency type, the scheduling distance and the nearest rescue point. The emergency degree of the emergency can be quickly and accurately identified and evaluated, the optimal emergency scheduling scheme is intelligently matched according to the type and the place of the emergency in combination with the scheduling scheme library, and the response efficiency and the accuracy of the emergency command system are greatly improved.

Description

Technical Field

[0001] The present invention relates to the field of scheduling technology, and in particular to an emergency command and dispatch method based on artificial intelligence. Background Art

[0002] With the acceleration of the urbanization process, rail transit, as an efficient and environmentally friendly public transportation mode, has been widely used. However, during the operation of the rail transit system, various emergencies may occur, such as equipment failures, natural disasters, bad weather, public health emergencies, and human safety incidents. These emergencies not only pose a threat to the safety of passengers but also may lead to large-scale operation interruptions and affect the normal operation of the city. Therefore, how to effectively respond to these emergencies and ensure the safety and smoothness of the rail transit system has become an important issue to be solved urgently.

[0003] Traditional emergency command and dispatch methods ignore the characteristics of different emergencies, lack pertinence, and are prone to waste of resources and reduction of rescue effects.

[0004] The patent document with the publication number CN118134166A discloses a rail transit emergency command and automatic dispatch method, which includes: obtaining emergency request information, where the emergency request information includes the location of the rescue point to be rescued, the emergency level, and the rescue material information; obtaining the emergency personnel information of each emergency personnel and the material depot information of each material depot; the emergency personnel information includes the location and status of the emergency personnel; the material depot information includes the location of the material depot and the material storage information; inputting the emergency request information, the emergency personnel information, and the material depot information into a pre-constructed emergency command and dispatch model, and the emergency command and dispatch model solves an emergency dispatch plan that meets the preset control target according to the greedy algorithm. The emergency dispatch plan includes the emergency personnel information of the emergency personnel who need to participate in the emergency rescue in this dispatch, and the running routes of each emergency personnel.

[0005] Therefore, the following problems can be seen: In the prior art, there is a lack of pertinence to the implementation situation in emergency dispatch, resulting in poor dispatch efficiency and accuracy. Summary of the Invention

[0006] For this reason, the present invention provides an emergency command and dispatch method based on artificial intelligence to overcome the problems in the prior art that there is a lack of pertinence to the implementation situation in emergency dispatch, resulting in poor dispatch efficiency and accuracy, and to perform targeted dispatch according to emergencies.

[0007] To achieve the above object, the present invention provides an emergency command and dispatch method based on artificial intelligence, including:

[0008] Obtain the real-time operation data, emergency event information, and real-time scheduling requirements of each train in the rail transit system, where the emergency event information includes the type of emergency event and the location of the emergency;

[0009] Determine the first emergency response level according to the real-time operation data, and determine the second emergency response level according to the type of emergency event;

[0010] Determine the emergency event based on the first emergency response level and the second emergency response level;

[0011] Determine the executable emergency scheduling plan based on the emergency event information of the emergency event and the scheduling plan library, calculate the demand fit degree and demand relevance degree between the executable emergency scheduling plan and the real-time scheduling requirements, and calculate the emergency scheduling matching degree according to the demand fit degree and the demand relevance degree;

[0012] Obtain the scheduling distance of the rescue point corresponding to the executable emergency scheduling plan with an emergency matching degree greater than the standard matching degree in the location of the emergency;

[0013] Obtain the nearest rescue point in front of the track travel route at the location of the emergency;

[0014] Determine the best emergency scheduling plan based on the type of emergency event, scheduling distance, and nearest rescue point.

[0015] Further, determining the first emergency response level according to the real-time operation data includes:

[0016] Compare the real-time operation status with the preset abnormal operation data range to determine whether it conforms to a specific abnormal mode to obtain a determination result;

[0017] Determine the first emergency response level according to the determination result.

[0018] Further, comparing the real-time operation status with the preset abnormal operation data range to determine whether it conforms to a specific abnormal mode to obtain a determination result includes:

[0019] If the real-time operation data of the rail transit system is within the preset abnormal operation data, it is determined to conform to a specific abnormal mode;

[0020] If the real-time operation status of the rail transit system is not within the preset abnormal operation data, it is determined not to conform to a specific abnormal mode.

[0021] Further, determining the first emergency response level according to the determination result includes:

[0022] When the determination result indicates that the real-time operation status conforms to a specific abnormal pattern, determine that the first emergency response level is a strong response level.

[0023] Further, determining the second emergency response level according to the type of the emergency event includes:

[0024] Judge whether the type of the emergency event is in the emergency event library. If the type of the emergency event is in the emergency event library, then the second emergency response level is a strong response level.

[0025] Further, calculating the demand fit degree and the demand relevance degree between the executable emergency dispatching plan and the real-time dispatching demand includes:

[0026] Determine the demand relevance degree between the executable emergency dispatching plan and the real-time dispatching demand by comparing the processing object of the executable emergency dispatching plan with the real-time dispatching demand;

[0027] Obtain the processing time of the executable emergency dispatching plan and the real-time dispatching demand to determine the demand fit degree between the executable emergency dispatching plan and the real-time dispatching demand.

[0028] Further, calculating the emergency dispatching matching degree according to the demand fit degree and the demand relevance degree includes:

[0029] Assign corresponding fit degree weights and relevance degree weights to the demand fit degree and the demand relevance degree;

[0030] Perform weighted processing on the demand fit degree and the demand relevance degree according to the fit degree weights and the relevance degree weights to obtain a weighted fit degree and a weighted relevance degree;

[0031] Calculate the sum of the weighted fit degree and the weighted relevance degree to determine the emergency dispatching matching degree.

[0032] Further, obtaining the dispatching distance of the rescue point corresponding to the executable emergency dispatching plan with an emergency matching degree greater than the standard matching degree in the emergency location includes:

[0033] Compare the emergency matching degree with the standard matching degree to determine the best executable emergency dispatching plan;

[0034] Determine the rescue point where the best executable emergency dispatching plan can be carried out;

[0035] Determine the dispatching distance between the rescue point and the emergency location.

[0036] Further, comparing the emergency matching degree with the standard matching degree to determine the best executable emergency dispatching plan includes:

[0037] Obtain the comparison result between the emergency matching degree and the standard matching degree of the executable emergency dispatching plan;

[0038] Determine that the executable emergency dispatching plan with the comparison result that the emergency matching degree is greater than the standard matching degree is the best executable emergency dispatching plan.

[0039] Furthermore, determining the best emergency dispatching plan based on the type of emergency event, dispatching distance, and the nearest rescue point includes:

[0040] If the type of emergency event is abnormal internal personnel, the best emergency dispatching plan is for the train to continue moving forward, and emergency dispatching is carried out by the nearest rescue point;

[0041] If the type of emergency event is not abnormal internal personnel, the best emergency dispatching plan is for the train to stop, and emergency dispatching is carried out by the rescue point with the shortest dispatching distance.

[0042] Compared with the prior art, the beneficial effects of the present invention are as follows: By obtaining train operation data and emergency event information in real time, calculating the emergency response degree in multiple dimensions, the emergency degree of an emergency event can be quickly and accurately identified and evaluated. According to the type and location of the emergency event, combined with the dispatching plan library, the best emergency dispatching plan is intelligently matched, greatly improving the response efficiency and accuracy of the emergency command system. By calculating the matching degree between the emergency dispatching plan and the real-time dispatching requirements, it can be ensured that the selected plan has high feasibility and effectiveness, maximally meeting the actual requirements of current operations, and greatly improving the response efficiency and accuracy of the emergency command system.

[0043] Furthermore, by comparing the real-time operation data with the preset abnormal operation modes, abnormal situations that may occur in the rail transit system can be quickly and accurately detected, with high sensitivity and reliability, capable of timely discovering potential safety hazards, thereby ensuring the timeliness and accuracy, and also providing data support for continuous optimization.

[0044] Furthermore, by setting clear data ranges to judge abnormalities, the judgment logic is simplified, and the accuracy and efficiency of judgment are improved. The pattern matching method based on data ranges is very intuitive, facilitating system maintenance personnel to understand and adjust. Through simple range comparison, it can quickly judge whether the real-time operation state is abnormal, ensuring the efficiency and timeliness of system operation, and laying a foundation for subsequent emergency response.

[0045] Furthermore, by directly determining the real-time operation state that conforms to the abnormal mode as a strong response degree, the emergency response process can be quickly and accurately started, thereby minimizing potential risks and losses, improving the efficiency of emergency command and dispatching, and better ensuring the safe operation of the rail transit system.

[0046] Furthermore, classifying and responding to emergencies through the emergency event library ensures that the system can respond quickly and effectively to common emergencies. The predefined emergency response levels can help the system quickly determine the priorities of emergency handling, allocate resources reasonably, avoid resource waste, and improve the efficiency and accuracy of handling emergencies.

[0047] Furthermore, by determining the demand relevance and demand fit, the matching degree between the scheduling plan and the real-time demand can be effectively evaluated, improving the applicability and effectiveness of the scheduling plan.

[0048] Furthermore, by performing weighted calculations on the demand fit and demand relevance, the impacts of the two factors on the matching degree of the emergency scheduling plan can be comprehensively considered. By setting different weights, the focus of the matching degree can be flexibly adjusted, thus better adapting to different application scenarios. The matching degree after weighted processing can more accurately reflect the overall effect of the emergency scheduling plan, helping the system select a better emergency scheduling plan.

[0049] Furthermore, by comparing with the standard matching degree, the emergency scheduling plans that truly meet the requirements can be screened out, avoiding the interference of inefficient plans. By determining the rescue points where the plan can be executed, it can be ensured that emergency resources can arrive in a timely manner. By calculating the scheduling distance from the rescue points to the emergency locations, the efficiency of different rescue plans can be evaluated, providing a basis for selecting the optimal rescue plan later. By combining the emergency matching degree and the scheduling distance, the system can more comprehensively evaluate the effectiveness of the rescue plan, thus improving the efficiency and quality of emergency scheduling.

[0050] Furthermore, through simple and direct comparison, the emergency scheduling plans with high matching degrees can be quickly and effectively screened out. By setting a clear standard matching degree, the selection criteria for emergency plans can be controlled to ensure that the selected plans have high quality. This comparison method can improve the decision-making efficiency of scheduling and enable the best scheduling response to be made in the shortest time.

[0051] Furthermore, through the precise identification and differential processing of the types of emergencies, the intelligence and refinement of the emergency scheduling plan are realized. The dynamic scheduling strategy based on the event type not only improves the flexibility and pertinence of emergency response, but also can significantly shorten the emergency handling time, reduce secondary risks, and improve the efficiency of emergency scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a flowchart of the emergency command and scheduling method based on artificial intelligence according to an embodiment of the present invention;

[0053] Figure 2 is a flowchart of determining the first emergency response level according to an embodiment of the present invention;

[0054] Figure 3 Flow chart for calculating the emergency dispatch matching degree in the embodiments of the present invention;

[0055] Figure 4 Flow chart for obtaining the dispatch distance in the embodiments of the present invention. Detailed implementation manners

[0056] In order to make the objectives and advantages of the present invention clearer, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0057] The preferred implementation manners of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these implementation manners are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0058] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0059] In addition, it should also be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0060] Please refer to Figure 1 , as Figure 1 shown, which is the flow chart of the emergency command and dispatch method based on artificial intelligence in the embodiments of the present invention;

[0061] Specifically, the emergency command and dispatch method based on artificial intelligence in the embodiments of the present invention includes:

[0062] Obtaining the real-time operation data, emergency event information and real-time dispatch requirements of each train in the rail transit system, where the emergency event information includes the type of emergency event and the location of the emergency;

[0063] Determining the first emergency response level according to the real-time operation data and the second emergency response level according to the type of emergency event;

[0064] Determine the emergency incident based on the first emergency response level and the second emergency response level;

[0065] Based on the emergency incident information of the emergency incident and the dispatching plan library, determine the executable emergency dispatching plan, calculate the demand fit degree and demand relevance degree between the executable emergency dispatching plan and the real-time dispatching demand, and calculate the emergency dispatching matching degree according to the demand fit degree and the demand relevance degree;

[0066] Obtain the dispatching distance of the rescue point corresponding to the executable emergency dispatching plan with an emergency matching degree greater than the standard matching degree in the emergency location;

[0067] Obtain the nearest rescue point in front of the rail travel route of the emergency location;

[0068] Determine the best emergency dispatching plan based on the type of the incident, the dispatching distance and the nearest rescue point.

[0069] Specifically, the real-time operation data includes data such as the noise level inside the train, the train operation speed, the train operation track, the train operation stability, and the train temperature, which reflect the data that affects the train operation during the operation. The emergency incident information includes event information such as a fire inside the train, the train running off course, train passenger casualties, abnormal train driving, and train collisions. The emergency location is the specific location of the train when an emergency incident is detected. The real-time dispatching demand is the demand for train repair, personnel treatment, shift adjustment, train personnel replacement, etc. The types of emergency incidents are internal personnel abnormalities and train operation abnormalities.

[0070] Specifically, to perform this method, first, the operation data of each train is collected in real time through sensors and communication networks deployed in the rail transit system. The emergency event information is obtained through the alarm system, manual reporting, or intelligent monitoring system, including the event type and occurrence location. The real-time scheduling requirements are generated based on the operation plan and current emergencies. The operation data of the train is analyzed by artificial intelligence to determine the abnormal conditions of the data, and compared with the preset normal or abnormal data ranges to determine the first emergency response level. At the same time, the emergency event type is also analyzed. If the event type belongs to the event types defined in the pre-stored emergency event library, it is determined that the second emergency response level is a strong response level. Then, the first and second emergency response levels are combined and comprehensively determined as an emergency incident. Next, according to the information of the emergency incident, the scheduling plan library is retrieved to find a matching emergency scheduling plan, and the degree of fit and relevance between these plans and the current real-time scheduling requirements are calculated. The matching degree is calculated through the given weights. Finally, based on the geographical location information of the emergency location and the rescue point, the scheduling distance to the rescue point is calculated, and the nearest rescue point in front of the rail line is obtained to determine the best emergency scheduling plan.

[0071] Specifically, by obtaining the train operation data and emergency event information in real time and calculating the emergency response level in multiple dimensions, the urgency of the emergency incident can be quickly and accurately identified and evaluated. According to the emergency event type and location, combined with the scheduling plan library, the best emergency scheduling plan can be intelligently matched, greatly improving the response efficiency and accuracy of the emergency command system. By calculating the matching degree between the emergency scheduling plan and the real-time scheduling requirements, it can be ensured that the selected plan has high feasibility and effectiveness, maximally meeting the actual needs of the current operation, and greatly improving the response efficiency and accuracy of the emergency command system.

[0072] Please continue to refer to Figure 2 , such as Figure 2 shown, which is the flowchart for determining the first emergency response level in the embodiment of the present invention;

[0073] Specifically, determining the first emergency response level according to the real-time operation data includes:

[0074] Comparing the real-time operation status with the preset abnormal operation data range to determine whether it conforms to a specific abnormal pattern to obtain a determination result;

[0075] Determining the first emergency response level according to the determination result.

[0076] Specifically, by comparing the real-time operation data with the preset abnormal operation modes, abnormal situations that may occur in the rail transit system can be detected quickly and accurately, with high sensitivity and reliability. Potential safety hazards can be discovered in a timely manner, thus ensuring the timeliness and accuracy, and also providing data support for continuous optimization.

[0077] Specifically, comparing the real-time operation status with the preset abnormal operation data range to determine whether it conforms to a specific abnormal mode to obtain a determination result includes:

[0078] When the real-time operation data of the rail transit system is within the preset abnormal operation data, it is determined to conform to a specific abnormal mode;

[0079] When the real-time operation status of the rail transit system is not within the preset abnormal operation data, it is determined not to conform to a specific abnormal mode.

[0080] Specifically, a range-based abnormal data pattern library is established. In this library, each abnormal mode defines a range of one or more real-time operation data, such as the threshold range of train speed, the deviation range of train position, the warning value range of carriage temperature, etc. When making a comparison and judgment, each parameter in the real-time operation data will be compared with the corresponding abnormal mode data range respectively. If one or more parameters of the real-time operation data fall within the preset abnormal data range, it is determined that the real-time operation status conforms to a specific abnormal mode and is marked as an abnormal status that needs further processing. On the contrary, if all parameters of the real-time operation data do not exceed the preset normal range, the system determines that the real-time operation status does not conform to any abnormal mode and is marked as a normal status.

[0081] Specifically, by setting clear data ranges to judge abnormalities, the judgment logic is simplified, and the accuracy and efficiency of judgment are improved. The range-based pattern matching method is very intuitive, facilitating system maintenance personnel to understand and adjust. Through simple range comparison, it can quickly judge whether the real-time operation status is abnormal, ensuring the efficiency and timeliness of system operation and laying a foundation for subsequent emergency response.

[0082] Specifically, determining the first emergency response level according to the determination result includes:

[0083] When the determination result is that the real-time operation status conforms to a specific abnormal mode, it is determined that the first emergency response level is a strong response level.

[0084] Specifically, after comparing and judging the real-time operation data with the preset abnormal patterns, the first emergency response level will be set according to the judgment result. Specifically, if the judgment result of the previous step is that the real-time operation state conforms to a specific abnormal pattern, this step will directly set the first emergency response level to a strong response level, which indicates that the system recognizes that there may be relatively serious abnormal situations in the current rail transit system and immediate emergency measures need to be taken.

[0085] Specifically, by directly judging the real-time operation state that conforms to the abnormal pattern as a strong response level, the emergency response process can be started quickly and accurately, thereby minimizing potential risks and losses, improving the efficiency of emergency command and dispatch, and better ensuring the safe operation of the rail transit system.

[0086] Specifically, determining the second emergency response level according to the type of the emergency event includes:

[0087] Judging whether the type of the emergency event is in the emergency event library. If the type of the emergency event is in the emergency event library, the second emergency response level is a strong response level.

[0088] Specifically, the emergency event library contains various predefined types of emergency events, such as fires, explosions, casualties, equipment failures, sudden illnesses of passengers, etc. Each event type corresponds to a unique identifier and the corresponding emergency response level. Matching the type of the emergency event with the event types in the emergency event library. If the corresponding event type is matched, indicating that the emergency event is a predefined emergency event, the system will set the second emergency response level to a strong response level.

[0089] Specifically, classifying and responding to emergency events through the emergency event library ensures that the system can make quick and effective responses to common emergency events. The predefined emergency response levels can help the system quickly determine the priorities of emergency handling, reasonably allocate resources, avoid resource waste, and improve the efficiency and accuracy of handling emergency events.

[0090] Specifically, calculating the demand fit degree and demand relevance degree between the executable emergency dispatch plan and the real-time dispatch demand includes:

[0091] Determining the demand relevance degree between the executable emergency dispatch plan and the real-time dispatch demand by comparing the processing objects of the executable emergency dispatch plan with the real-time dispatch demand;

[0092] Obtaining the processing time of the executable emergency dispatch plan and the real-time dispatch demand to determine the demand fit degree between the executable emergency dispatch plan and the real-time dispatch demand.

[0093] Specifically, when calculating the relevance of the computing requirements, the requirement relevance is determined according to the text similarity rate corresponding between the executable emergency scheduling plan and the processing objects in the real-time scheduling requirements, and the requirement compliance is determined according to the processing time of the executable emergency scheduling plan and the longest time of the real-time scheduling requirements.

[0094] Specifically, by determining the requirement relevance and the requirement compliance, the matching degree between the scheduling plan and the real-time requirements can be effectively evaluated, and the applicability and effectiveness of the scheduling plan can be improved.

[0095] Please continue to refer to Figure 3 , such as Figure 3 shown, which is the flowchart for calculating the emergency scheduling matching degree in the embodiment of the present invention;

[0096] Specifically, calculating the emergency scheduling matching degree according to the requirement compliance and the requirement relevance includes:

[0097] Assigning corresponding compliance weights and relevance weights to the requirement compliance and the requirement relevance;

[0098] Performing weighted processing on the requirement compliance and the requirement relevance according to the compliance weights and the relevance weights to obtain a weighted compliance and a weighted relevance;

[0099] Calculating the sum of the weighted compliance and the weighted relevance to determine the emergency scheduling matching degree.

[0100] Specifically, weight values are set for the requirement compliance and the requirement relevance respectively, which are called the compliance weight and the relevance weight respectively. The settings of these two weight values can be adjusted according to the actual application scenario. In specific implementation, the compliance weight is set to 0.6, the relevance weight is set to 0.4, the requirement compliance is 0.8, and the requirement relevance is 0.7. Then, the calculated requirement compliance and requirement relevance are multiplied by the corresponding weight values respectively to obtain the weighted compliance and the weighted relevance. The weighted compliance is 0.8 * 0.6 = 0.48, and the weighted relevance is 0.7 * 0.4 = 0.28. Finally, the weighted compliance and the weighted relevance are added together to obtain the emergency scheduling matching degree. For example, 0.48 + 0.28 = 0.76. The obtained emergency scheduling matching degree will be used to select the best emergency scheduling plan in the follow-up.

[0101] Specifically, by performing weighted calculations on the requirement compliance and the requirement relevance, the impacts of the two factors on the matching degree of the emergency scheduling plan can be comprehensively considered. By setting different weights, the focus of the matching degree can be flexibly adjusted, so as to better adapt to different application scenarios. The matching degree after weighted processing can more accurately reflect the overall effect of the emergency scheduling plan, thereby helping the system select a better emergency scheduling plan.

[0102] Please continue to refer to Figure 4 , as Figure 4 shown, which is a flowchart for obtaining the scheduling distance in an embodiment of the present invention;

[0103] Specifically, obtaining the scheduling distance of the rescue point corresponding to the executable emergency scheduling plan with an emergency matching degree greater than the standard matching degree in the emergency location includes:

[0104] Comparing the emergency matching degree with the standard matching degree to determine the best executable emergency scheduling plan;

[0105] Determining the rescue point where the best executable emergency scheduling plan can be carried out;

[0106] Determining the scheduling distance between the rescue point and the emergency location.

[0107] Specifically, by comparing with the standard matching degree, the emergency scheduling plans that truly meet the requirements can be screened out, avoiding the interference of inefficient plans. By determining the rescue point where the plan can be executed, it can be ensured that emergency resources can arrive in time. By calculating the scheduling distance from the rescue point to the emergency location, the efficiency of different rescue plans can be evaluated, providing a basis for selecting the optimal rescue plan subsequently. By combining the emergency matching degree and the scheduling distance, the system can more comprehensively evaluate the effectiveness of the rescue plan, thereby improving the efficiency and quality of emergency scheduling.

[0108] Specifically, comparing the emergency matching degree with the standard matching degree to determine the best executable emergency scheduling plan includes:

[0109] Obtaining the comparison result between the emergency matching degree of the executable emergency scheduling plan and the standard matching degree;

[0110] Determining that the executable emergency scheduling plan with the comparison result that the emergency matching degree is greater than the standard matching degree is the best executable emergency scheduling plan.

[0111] In the specific implementation process, the standard matching degree is 0.8. The emergency matching degree of an executable emergency scheduling plan is 0.7, then the emergency matching degree of this plan is less than the standard matching degree. The emergency matching degree of another executable emergency scheduling plan is 0.9, then the comparison result is that the emergency matching degree of this plan is greater than the standard matching degree, and it is an executable emergency scheduling plan.

[0112] Specifically, through simple and direct comparison, the emergency scheduling plans with high matching degrees can be quickly and effectively screened out. By setting a clear standard matching degree, the selection criteria for emergency plans can be controlled to ensure that the selected plans have high quality. This comparison method can improve the decision-making efficiency of scheduling and can make the best scheduling response in the shortest time.

[0113] Specifically, determining the optimal emergency dispatch plan based on the type of the emergency event, the dispatch distance, and the nearest rescue point includes:

[0114] If the type of the emergency event is an internal personnel anomaly, the optimal emergency dispatch plan is for the train to continue moving forward, and emergency dispatch is carried out by the nearest rescue point.

[0115] If the type of the emergency event is not an internal personnel anomaly, the optimal emergency dispatch plan is for the train to stop, and emergency dispatch is carried out by the rescue point with the shortest dispatch distance.

[0116] Specifically, the optimal emergency dispatch plan is finally determined according to the type of the emergency event and the dispatch distance. If the type of the emergency event is determined to be an internal personnel anomaly, the optimal dispatch plan is for the train to continue moving forward, and emergency dispatch is carried out by the nearest rescue point ahead. If the type of the emergency event does not belong to internal personnel anomalies such as train speed failure, track failure, train fire, etc., the optimal dispatch plan is for the train to immediately stop running, and emergency dispatch is carried out by the rescue point with the shortest dispatch distance from the emergency location.

[0117] Specifically, through the accurate identification and differential processing of the type of the emergency event, the intelligence and refinement of the emergency dispatch plan are realized. The dynamic dispatch strategy based on the event type not only improves the flexibility and pertinence of the emergency response, but also can significantly shorten the emergency handling time, reduce secondary risks, and improve the efficiency of the emergency dispatch.

[0118] So far, the technical solution of the present invention has been described in combination with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

[0119] The above are only the preferred embodiments of the present invention and are not used to limit the present invention; for those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An emergency command and dispatch method based on artificial intelligence, characterized in that: include: Acquire real-time operation data, emergency information and real-time dispatching requirements of each train in the rail transit system, wherein the emergency information includes the type and location of the emergency; Determine a first emergency response level according to the real-time operation data, and determine a second emergency response level according to the type of emergency event; Determining an emergency event based on the first emergency response level and the second emergency response level; Determine an executable emergency dispatch plan based on the emergency event information of the emergency event and the dispatch plan library, calculate the demand fit and demand relevance between the executable emergency dispatch plan and the real-time dispatch demand, and calculate the emergency dispatch matching degree according to the demand fit and demand relevance; Obtaining the dispatch distance of the rescue point corresponding to the executable emergency dispatch plan in the emergency location where the emergency matching degree is greater than the standard matching degree; Obtain the nearest rescue point ahead of the track route of the emergency location; The best emergency dispatch plan is determined based on the type of emergency, dispatch distance and nearest rescue point.

2. The artificial intelligence-based emergency command and dispatch method according to claim 1, characterized in that: Determining the first emergency response level according to the real-time operation data includes: Comparing the real-time operation status with a preset abnormal operation data range to determine whether it conforms to a specific abnormal mode to obtain a determination result; The first emergency response level is determined according to the determination result.

3. The artificial intelligence-based emergency command and dispatch method according to claim 2 is characterized in that: Comparing the real-time operation status with a preset abnormal operation data range to determine whether it conforms to a specific abnormal mode to obtain a determination result includes: If the real-time operation data of the rail transit system is within the preset abnormal operation data, it is determined to be consistent with a specific abnormal mode; If the real-time operating status of the rail transit system is not within the preset abnormal operating data, it is determined that it does not conform to the specific abnormal mode.

4. The artificial intelligence-based emergency command and dispatch method according to claim 3 is characterized in that: Determining the first emergency response level according to the determination result includes: When the determination result is that the real-time operating status conforms to a specific abnormal mode, the first emergency response level is determined to be a strong response level.

5. The artificial intelligence-based emergency command and dispatch method according to claim 4 is characterized in that: Determining the second emergency response level according to the type of emergency event includes: It is determined whether the emergency event type is in the emergency event database. If the emergency event type is in the emergency event database, the second emergency response level is a strong response level.

6. The artificial intelligence-based emergency command and dispatch method according to claim 5 is characterized in that: Calculating the demand fit and demand relevance between the executable emergency dispatch plan and the real-time dispatch demand includes: Determining the demand correlation between the executable emergency dispatch solution and the real-time dispatch demand by comparing the processing object of the executable emergency dispatch solution with the real-time dispatch demand; The processing time of the executable emergency dispatch solution and the real-time dispatch requirement are obtained to determine the degree of compliance between the executable emergency dispatch solution and the real-time dispatch requirement.

7. The artificial intelligence-based emergency command and dispatch method according to claim 6, characterized in that: Calculating the emergency dispatch matching degree according to the demand fit and the demand relevance includes: Assigning corresponding fit weights and relevance weights to the demand fit and the demand relevance; The demand fit and the demand relevance are weighted according to the fit weight and the relevance weight to obtain a weighted fit and a weighted relevance; The sum of the weighted fit degree and the weighted relevance degree is calculated to determine the emergency dispatch matching degree.

8. The artificial intelligence-based emergency command and dispatch method according to claim 7, characterized in that: Obtaining the dispatch distance of the rescue point corresponding to the executable emergency dispatch plan in the emergency location where the emergency matching degree is greater than the standard matching degree includes: Comparing the emergency matching degree with the standard matching degree to determine the best executable emergency dispatch plan; Determine the rescue point where the best executable emergency dispatch plan can be implemented; Determine the dispatch distance between the rescue point and the emergency location.

9. The artificial intelligence-based emergency command and dispatch method according to claim 8, characterized in that: Comparing the emergency matching degree with the standard matching degree to determine the best executable emergency dispatch plan includes: Obtaining a comparison result between the emergency matching degree and the standard matching degree of the executable emergency dispatch plan; Determine that the executable emergency dispatch plan whose comparison result is that the emergency matching degree is greater than the standard matching degree is the best executable emergency dispatch plan.

10. The artificial intelligence-based emergency command and dispatch method according to claim 9, characterized in that: Determining the best emergency dispatch plan based on the emergency type, dispatch distance and nearest rescue point includes: If the emergency event type is an internal personnel abnormality, the best emergency dispatch plan is that the train continues to move forward and the nearest rescue point performs emergency dispatch; If the emergency event type is not an internal personnel abnormality, the best emergency dispatch plan is to stop the train and conduct emergency dispatch from the rescue point with the shortest dispatch distance.

Images