A multi-operator integrated emergency coordination method and system and a storage medium

Abstract

The application provides a multi-operation subject integrated emergency coordination method and system and a storage medium. The method comprises the following steps: using a preset multi-operation subject dynamic capability evaluation system to dynamically evaluate the capability of personnel subordinate to each operation subject under different indexes; analyzing the demand of an emergency task in different emergency processing dimensions, obtaining the personnel capability indexes associated with the demand of the emergency task in different emergency processing dimensions based on a preset mapping relationship; and using a pre-trained multi-objective optimization matching model to intelligently match the personnel subordinate to different operation subjects to the emergency task according to the capability of the personnel subordinate to each operation subject under different indexes and the personnel capability dimension indexes associated with the demand of the emergency task in different emergency processing dimensions, so that the matched personnel cooperatively process the emergency task.

Description

Technical Field

[0001] This invention relates to the field of emergency management technology for integrated passenger transport hubs, and in particular to an integrated emergency coordination method, system, and storage medium for multiple operating entities. Background Technology

[0002] Passenger transport hubs are operated by multiple entities, making collaborative management a top priority in emergency management. Multi-entity integrated emergency coordination refers to an emergency management model in the complex scenarios of large-scale integrated transport hubs, requiring efficient collaboration and unified command among multiple independently operating or managed entities such as railways, civil aviation, subways, and municipal transportation to respond to emergencies (such as natural disasters, accidents, public health incidents, and social security incidents). The types of operating entities include independently operating or managed entities such as railways, civil aviation, subways, and municipal transportation.

[0003] Traditional multi-entity emergency coordination methods have many problems: they rely heavily on static plans, leading to rigid responses that cannot adapt to dynamic changes on the ground; personnel deployment is highly subjective, with command decisions relying heavily on personal experience and lacking precise matching of personnel capabilities with task requirements, easily resulting in "person-job mismatch" or missing key capabilities; cross-departmental collaboration barriers are high, with information silos existing between various operating entities, resource status is not transparent, and it is difficult to form a unified and efficient command system; and there is a lack of scientific decision support, with the allocation of emergency resources (especially human resources) lacking a global optimization perspective, and response decisions being highly subjective.

[0004] These problems severely restrict the efficiency and effectiveness of multi-entity, cross-departmental emergency collaboration. Existing technologies typically rely on pre-defined division of responsibilities and static personnel rosters for scheduling, failing to dynamically assess personnel's actual capabilities, availability, and fatigue levels. Each entity operates independently, making it difficult to quickly form the optimal team composition in complex emergency scenarios. Emergency command systems primarily focus on information reporting and process monitoring, providing insufficient support for the core decision-making process of "how to scientifically match people with tasks."

[0005] Furthermore, with the increasing complexity and integration of urban functions, especially the continuous emergence of large-scale integrated transportation hubs, higher requirements are being placed on the refinement and intelligence of emergency management.

[0006] Therefore, how to design an integrated emergency collaboration method for multiple operating entities that can break down barriers between entities and achieve dynamic, accurate, and intelligent matching and collaboration of emergency human resources is a technical problem that urgently needs to be solved. Summary of the Invention

[0007] In order to achieve dynamic, accurate, and intelligent matching of emergency human resources and eliminate or improve the defects of existing technologies such as inaccurate matching of emergency resources, low coordination efficiency, and strong subjectivity in response decisions, this invention proposes an integrated emergency coordination method, system, and storage medium for multiple operating entities.

[0008] One aspect of the present invention provides an integrated emergency coordination method for multiple operating entities. The method includes the following steps: dynamically evaluating the capabilities of personnel belonging to various operating entities under different indicators using a pre-set dynamic capability assessment system; analyzing the needs of emergency tasks across different emergency handling dimensions, and obtaining personnel capability indicators associated with the needs of emergency tasks across different emergency handling dimensions based on a pre-set mapping relationship; and intelligently matching personnel belonging to different operating entities for emergency tasks using a pre-trained multi-objective optimization matching model, based on the capabilities of personnel belonging to various operating entities under different indicators and the personnel capability dimension indicators associated with the needs of emergency tasks across different emergency handling dimensions, and the matched personnel collaboratively handling the emergency tasks.

[0009] In some embodiments of the present invention, the multi-operating entity dynamic capability assessment system includes an emergency responsibility matrix, a multi-level personnel classification framework, a capability indicator system, and a dynamic capability database. The step of dynamically assessing the capabilities of personnel belonging to various operating entities under different indicators using the preset multi-operating entity dynamic capability assessment system includes: dividing the functions of each operating entity using the emergency responsibility matrix; using the multi-level personnel classification framework to coordinate and manage the emergency organization level, plan responsibility division, and emergency response level of each operating entity; assessing the capabilities of personnel belonging to various operating entities according to the set rules and set indicators included in the capability indicator system; and storing and continuously updating the capability assessment results of personnel belonging to various operating entities.

[0010] In some embodiments of the present invention, the requirements of emergency tasks obtained from parsing across different emergency handling dimensions are represented in vector form; the emergency handling dimensions include one or more of the following: task urgency, required capabilities under different indicators, required equipment type, supported robot capabilities, task geographic coordinates, time constraints for completion, risk coefficient of the task itself, dependencies between tasks, and resource sharing requirements; before the step of intelligently matching personnel belonging to different operating entities for emergency tasks using a pre-trained multi-objective optimization matching model, the method further includes: dynamically prioritizing emergency tasks based on warning level, the impact range of emergencies related to the emergency task, and / or the importance of key nodes; wherein, the key nodes include preset locations and time periods.

[0011] In some embodiments of the present invention, the multi-objective optimization matching model sets multiple objectives including matching effectiveness objectives, organizational collaboration objectives, risk management objectives, and / or adaptability objectives; the inputs of the multi-objective optimization matching model include personnel resource information of each operating entity, emergency task demand information, and / or environmental and contextual data, wherein the personnel resource information includes basic personnel data, capability assessment data, availability information, and historical performance data; the step of using the pre-trained multi-objective optimization matching model to intelligently match personnel belonging to different operating entities for emergency tasks includes: generating a Pareto optimal solution set using a decomposition-evolutionary multi-objective optimization algorithm, and optimizing the generated Pareto optimal solution set based on a hierarchical analysis decision model, thereby generating an emergency collaboration plan including a personnel-task allocation table, a time schedule table, and / or a resource allocation list.

[0012] In some embodiments of the present invention, for the generated emergency coordination scheme, the method further includes: using a machine learning model trained based on historical emergency response data to predictively optimize the matching results, wherein the machine learning model employs a fast decision-making algorithm that approximates the ideal solution ranking method.

[0013] In some embodiments of the present invention, after generating the emergency coordination plan, the method further includes: during the process of matching personnel coordinating the handling of the emergency task, monitoring the fatigue status of the personnel through wearable devices and / or regional video surveillance; when the monitored fatigue status of the personnel reaches a set range, generating and updating the emergency coordination plan, and arranging for the personnel to rest in the updated emergency coordination plan.

[0014] In some embodiments of the present invention, the method further includes: summarizing the capabilities of personnel of all operating entities under different indicators of dynamic evaluation; analyzing in advance the capabilities that personnel do not possess based on the needs of emergency tasks in different emergency handling dimensions; selecting robots to supplement the capabilities; and intelligently matching and coordinating the robots and personnel belonging to various operating entities to handle the emergency tasks. Among these capabilities, the capabilities that personnel do not possess include special environment rescue capabilities, and the special environment includes dense smoke core areas, high temperature areas, and / or high pressure areas.

[0015] In some embodiments of the present invention, the type of the operating entity is a transportation entity, the capabilities of the personnel belonging to each transportation entity are reflected as transportation capacity, and the multi-objective optimization matching model is a transportation capacity matching model; the method further includes: based on passenger-side demand indicators including arrival passenger flow characteristics, individual passenger attributes and transfer selection behavior, transportation entity-side supply indicators including physical conditions, operation organization and information services, and combined with environmental factors including weather conditions, urban traffic conditions, major events and holidays, a transportation capacity matching model that balances departure and arrival at the hub is constructed.

[0016] Corresponding to the above methods, the present invention also provides an integrated emergency coordination system for multiple operating entities, including a processor, a memory, and a computer program / instructions stored in the memory. The processor is used to execute the computer program / instructions, and when the computer program / instructions are executed, the system implements the steps of any of the methods described in the above embodiments.

[0017] In accordance with the above methods, the present invention also provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implements the steps of the method as described in any of the above embodiments.

[0018] The multi-operation entity integrated emergency coordination method proposed in this invention can comprehensively analyze the capabilities of personnel belonging to various operation entities through the construction of a multi-operation entity dynamic capability assessment system, and analyze the needs of emergency tasks in different emergency handling dimensions. Based on a preset mapping relationship, the needs are associated with personnel capability indicators, emergency tasks are decomposed into multi-objective optimization problems, and a multi-objective optimization matching model is used to match personnel belonging to different operation entities according to emergency tasks, thereby realizing intelligent multi-operation entity integrated emergency coordination.

[0019] Additional advantages, objects, and features of the invention will be set forth in part in the description which follows, and will also become apparent in part to those skilled in the art upon studying the description, or may be learned by practice of the invention. The objects and other advantages of the invention can be realized and obtained by means of the structures specifically pointed out in the description and drawings.

[0020] Those skilled in the art will understand that the objectives and advantages achievable with the present invention are not limited to those specifically described above, and that the above and other objectives achievable with the present invention will become clearer from the following detailed description. Attached Figure Description

[0021] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, are not intended to limit the scope of the invention. In the drawings: Figure 1 This is a flowchart of a multi-operation entity integrated emergency coordination method in some embodiments of the present invention.

[0022] Figure 2 This is a schematic diagram of the computer equipment included in the system. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the embodiments and accompanying drawings. Here, the illustrative embodiments and descriptions of this invention are used to explain the invention, but are not intended to limit the invention.

[0024] It should also be noted that, in order to avoid obscuring the invention with unnecessary details, only the structures and / or processing steps closely related to the solution according to the invention are shown in the accompanying drawings, while other details that are not closely related to the invention are omitted.

[0025] It should be emphasized that the term "including / comprises" as used herein refers to the presence of a feature, element, step, or component, but does not exclude the presence or addition of one or more other features, elements, steps, or components.

[0026] It should also be noted that, unless otherwise specified, the term "connection" in this article can refer not only to a direct connection, but also to an indirect connection involving an intermediary.

[0027] In the following description, embodiments of the invention will be illustrated with reference to the accompanying drawings. In the drawings, the same reference numerals represent the same or similar parts, or the same or similar steps.

[0028] To improve the accuracy and rationality of personnel scheduling during emergency response and collaborative handling, and to enhance the collaborative capabilities of personnel from multiple operational entities, this invention proposes an integrated emergency coordination method involving multiple operational entities. This method dynamically assesses personnel capabilities by constructing a dynamic capability assessment system for multiple operational entities, analyzes the needs of emergency tasks, and establishes a mapping relationship between needs and personnel capabilities, thereby enabling intelligent matching based on a multi-objective optimization model.

[0029] Figure 1 This is a flowchart of a multi-operating entity integrated emergency coordination method in some embodiments of the present invention. The method includes the following steps: Step S110: Utilize a pre-set dynamic capability assessment system for multiple operating entities to dynamically assess the capabilities of personnel belonging to each operating entity under different indicators.

[0030] The aforementioned multi-operating entity dynamic capability assessment system may include an emergency responsibility matrix, a multi-level personnel classification framework, a capability indicator system, and a dynamic capability database. Among them: (1) the emergency responsibility matrix is ​​used to locate the functions of each operating entity; (2) the multi-level personnel classification framework is used to coordinate and manage each operating entity, and the content of the coordinated management covers different emergency organization levels, plan responsibility division, and emergency response level in the operating entity; (3) the capability indicator system is an indicator for assessing the capabilities of personnel according to the set rules; (4) the dynamic capability database is used to continuously store and update the capabilities of personnel (implying periodic assessment of personnel capabilities).

[0031] Step S120: Analyze the requirements of emergency tasks in different emergency handling dimensions, and obtain personnel capability indicators related to the requirements of emergency tasks in different emergency handling dimensions based on the preset mapping relationship.

[0032] Emergency tasks can be analyzed from the perspectives of emergency response standards, the nature of the emergency, the handling stage, and / or the characteristics of the hub operator. The analysis of emergency tasks includes classifying emergency handling dimensions and breaking down the requirements of emergency tasks in different emergency handling dimensions.

[0033] In step S120, based on the emergency task analysis results, a correspondence matrix between emergency tasks and required professional skills can be established to associate abstract task requirements with specific personnel capability indicators.

[0034] Step S130: Based on the capabilities of personnel belonging to various operating entities under different indicators, and the personnel capability dimension indicators associated with the needs of emergency tasks in different emergency handling dimensions, a pre-trained multi-objective optimization matching model is used to intelligently match personnel belonging to different operating entities for emergency tasks, and the matched personnel collaboratively handle the emergency tasks.

[0035] Among them, the Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA / D) can be used to generate Pareto optimal solution sets, and the solution sets can be optimized based on the hierarchical analysis decision model to generate emergency coordination solutions.

[0036] The multi-operation entity integrated emergency coordination method proposed in this invention can comprehensively analyze the capabilities of personnel belonging to each operation entity through the construction of a multi-operation entity dynamic capability assessment system, and analyze the needs of emergency tasks in different emergency handling dimensions. Based on a preset mapping relationship, the needs are associated with personnel capability indicators, and the emergency task is decomposed into a multi-objective optimal solution problem. Then, a multi-objective optimization matching model is used to match personnel belonging to different operation entities according to the emergency task, thereby realizing intelligent multi-operation entity integrated emergency coordination.

[0037] In some embodiments of the present invention, the multi-operating entity dynamic capability assessment system includes an emergency responsibility matrix, a multi-level personnel classification framework, a capability indicator system, and a dynamic capability database.

[0038] Accordingly, in the above embodiments, the step of dynamically assessing the capabilities of personnel belonging to various operating entities under different indicators using a pre-set multi-operating entity dynamic capability assessment system includes: (1) dividing the functions of each operating entity using the emergency responsibility matrix; (2) managing the emergency organization level, plan responsibility division, and emergency response level of each operating entity using the multi-level personnel classification framework; (3) assessing the capabilities of personnel belonging to various operating entities according to the set rules and set indicators included in the capability indicator system; and (4) storing and continuously updating the capability assessment results of personnel belonging to various operating entities.

[0039] In a specific embodiment of this invention, under emergency conditions, the aforementioned emergency responsibility matrix typically designates the hub emergency center / joint command headquarters as the "responsible party" (A) for emergency decision-making and command, possessing unified command and dispatch authority, and organizing and coordinating multiple forces to complete the emergency response. Operating groups, railways, airports, subways, etc., become the "responsible parties" (R) for emergency response and on-site execution, requiring them to directly activate their own emergency mechanisms and cooperate with the center to complete specific handling tasks. Hospitals / emergency centers become the "supporters" (S), providing crucial assistance in maintaining order, traffic management, medical care, and evacuation, and rapidly assembling professional forces depending on the type of event. The Municipal Transportation Commission primarily acts as the "consultant" (C), while also undertaking support and leading responsibilities for specific tasks (such as emergency traffic management) when necessary. Information must be updated in real-time to the "informers" (I), such as the Municipal Emergency Committee, higher-level authorities, media, and the public, forming a complete emergency information flow with multi-level reporting and simultaneous release. The skills of personnel under each operating entity are differentiated according to the aforementioned capabilities.

[0040] By employing this embodiment of the invention, a pre-built dynamic capability assessment system for multiple operating entities can be used to locate the functions of each operating entity, manage different emergency organization levels, division of responsibilities in contingency plans, and emergency response levels within the operating entities, thereby gaining a comprehensive understanding of the structure, members, and capabilities of all operating entities.

[0041] In some embodiments of the present invention, the requirements of emergency tasks obtained from parsing across different emergency handling dimensions are represented in vector form. In simpler terms, this means that the emergency tasks are standardized and decomposed, and then the task requirements are represented in vector form.

[0042] Here is an example of its vector representation: ; The urgency of this task; The required level of each skill type; Required equipment / materials type or configurable robot capabilities; : Mission geographic coordinates; The timeframe for completion is a mandatory requirement. Risk factor of the task itself; Dependencies or resource sharing requirements between tasks.

[0043] In some embodiments of the present invention, the emergency handling dimensions include one or more of the following: task urgency, required capabilities under different indicators, required equipment type, supported robot capabilities, task geographic coordinates, time constraints for completion, risk coefficient of the task itself, dependencies between tasks, and resource sharing requirements.

[0044] The aforementioned emergency response dimensions include one or more of the following: task urgency, required capabilities under different indicators, required equipment type, supported robot capabilities, task geographic coordinates, time constraints for completion, risk coefficient of the task itself, dependencies between tasks, and resource sharing requirements. This invention is not limited to these; the emergency response dimensions listed above are merely examples.

[0045] By employing this embodiment of the invention, emergency tasks can be classified and analyzed to obtain their requirements in different emergency handling dimensions. Based on the comprehensive analysis of the requirements in different dimensions, the demand for personnel capabilities can be improved, which is conducive to matching suitable personnel for emergency tasks and generating emergency coordination plans for mobilizing suitable personnel.

[0046] In some embodiments of the present invention, the multi-objective optimization matching model sets multiple objectives including matching effectiveness objectives, organizational collaboration objectives, risk management objectives, and / or adaptability objectives. The inputs to the multi-objective optimization matching model include personnel resource information of each operating entity, emergency task demand information, and / or environmental and contextual data. The personnel resource information includes basic personnel data, capability assessment data, availability information, and historical performance data.

[0047] The multi-objective optimization matching model described above is merely an example, and the present invention is not limited thereto. Setting multiple objectives helps to constrain the final generated result from multiple perspectives, ensuring that the generated result meets the expected requirements of each objective.

[0048] Accordingly, in some embodiments of the present invention, the step of using a pre-trained multi-objective optimization matching model to intelligently match personnel belonging to different operating entities for emergency tasks includes: generating a Pareto optimal solution set using a multi-objective optimization algorithm based on decomposition and evolution, and optimizing the generated Pareto optimal solution set based on a hierarchical analysis decision model, thereby generating an emergency coordination plan that includes a personnel-task allocation table, a time schedule table, and / or a resource allocation list.

[0049] By employing this embodiment of the invention, a multi-objective optimization matching model can be used to specifically match the most suitable mobilization method for personnel belonging to different operating entities for emergency tasks. This helps to ensure high efficiency in the collaborative processing of emergency tasks while avoiding redundancy in the collaborative processing teams.

[0050] In some embodiments of the present invention, for the generated emergency coordination scheme, the method further includes: using a machine learning model trained based on historical emergency response data to predictively optimize the matching results, wherein the machine learning model employs a fast decision-making algorithm that approximates the ideal solution ranking method.

[0051] The embodiment of this invention employs a fast decision-making algorithm based on the approximation of ideal solutions ranking method. This algorithm considers both the proximity to the ideal solution and the proximity to the negative ideal solution, comprehensively evaluating the merits of the indicators. It also relies on the original data and established standards, which can reduce subjective bias and help ensure the objectivity and wide applicability of the solution.

[0052] In some embodiments of the present invention, after generating the emergency coordination plan, the method further includes: during the process of matching personnel coordinating the handling of the emergency task, monitoring the fatigue status of the personnel through wearable devices and / or regional video surveillance; when the monitored fatigue status of the personnel reaches a set range, generating and updating the emergency coordination plan, and arranging for the personnel to rest in the updated emergency coordination plan.

[0053] The fatigue level of personnel can be defined as "moderate fatigue," which can be determined by factors such as heart rate, HRV, frequency of yawning, degree of inattention, and degree of slow reaction time. Rest refers to reducing the assigned workload and duration, taking short breaks, adjusting the task order, and prioritizing tasks requiring lower levels of focus.

[0054] Using this invention, wearable devices and regional video surveillance, either in combination or individually, can be used to monitor the working status of personnel within an emergency task area. When fatigue is detected and reaches a set range, the emergency coordination plan can be updated to allow personnel within the area to rest.

[0055] In some embodiments of the present invention, the method further includes: summarizing the capabilities of personnel from all operating entities under different indicators under dynamic evaluation; pre-analyzing the capabilities that personnel lack based on the needs of emergency tasks in different emergency handling dimensions; selecting robots to supplement these capabilities; and intelligently matching and collaboratively handling the emergency tasks with the robots and personnel belonging to each operating entity. The capabilities that personnel lack include special environment rescue capabilities, such as dense smoke core areas, high-temperature areas, and / or high-pressure areas.

[0056] By employing this embodiment of the invention, it is possible to introduce robots to assist in solving some problems that are intractable to humans, thereby compensating for the shortcomings of human capabilities.

[0057] In some embodiments of the present invention, the type of the operating entity is a transportation entity, the capabilities of the personnel belonging to each transportation entity are reflected as transportation capacity, and the multi-objective optimization matching model is a transportation capacity matching model.

[0058] In some embodiments of the present invention, the method further includes: constructing a capacity matching model that balances departure and arrival at the hub based on passenger-side demand indicators including arrival passenger flow characteristics, individual passenger attributes and transfer selection behavior, transportation entity-side supply indicators including physical conditions, operation organization and information services, and environmental factors including weather conditions, urban traffic conditions, major events and holidays.

[0059] By adopting this embodiment of the invention, in the scenario of multi-transport entity capacity matching, a capacity matching model can be constructed to balance the departure and arrival of hubs, meet the collaborative processing needs in emergency transportation scenarios, and satisfy various indicators such as transfer time, congestion, economy, and reliability, so as to maximize the efficiency of passenger evacuation.

[0060] In one embodiment of the present invention, the method includes the following steps: (1) Pre-configure several robots and use the configured robots to supplement the personnel capabilities of each operating entity.

[0061] The pre-configuration of several robots to supplement the personnel capabilities of various operating entities includes: ① When a task is identified as having high urgency and personnel skill gaps, a human-machine collaboration spectrum is established based on multi-dimensional robot capability profiles, and a human-machine collaboration reinforcement mechanism is initiated; ② A matching model between robot emergency response capabilities and personnel skill gaps is constructed, robot resources are incorporated as a supplement into the multi-objective optimization matching model, a task decomposition and allocation method for human-machine collaborative emergency response is designed, robots are matched, and a human-machine collaboration solution is generated to supplement the shortcomings in emergency response capabilities.

[0062] (2) Establish a dynamic capability assessment system for multiple operating entities to achieve dynamic and multi-dimensional assessment of the capabilities of personnel of each operating entity.

[0063] The establishment of a dynamic capability assessment system for multiple operating entities includes: ① constructing an emergency responsibility matrix for multiple operating entities and establishing a multi-level personnel classification framework covering different emergency organization levels, plan responsibility divisions, and emergency response levels within the operating entities; ② designing a capability indicator system covering professional skills, emergency decision-making capabilities, and collaborative combat capabilities, including assessment indicators for multiple dimensions such as traffic operation management, safety assurance, emergency rescue, information and communication, cross-departmental coordination, and / or passenger services; ③ establishing a dynamic capability database, which integrates dynamic data such as historical emergency response performance, feedback from regular training and drill assessments, and records of personnel rotation and experience accumulation, to achieve continuous updating and assessment of personnel capabilities, thereby eliminating static personnel files and solving the problems of "mismatch between personnel and positions" or "outdated capabilities."

[0064] The aforementioned multi-level personnel classification framework includes: ① classification according to different levels such as hub emergency response teams, emergency response command centers, and emergency response centers; ② personnel categories based on the division of responsibilities in the plan (such as management committees, transportation, railways, airports, etc.); ③ classification of personnel responsibilities corresponding to the four levels of emergency response (Levels I-IV).

[0065] (3) Construct an emergency task requirements analysis framework to standardize the decomposition of emergency tasks, map capability requirements, and evaluate priorities.

[0066] The aforementioned framework for constructing emergency task requirements analysis includes: ① classifying and decomposing emergency tasks based on emergency response standards, the nature of the emergency, the stage of handling, and / or the characteristics of the hub operation entity; ② quantifying emergency task requirements in multiple dimensions, constructing a mapping relationship between task capability requirements, establishing a correspondence matrix between emergency response tasks and required professional skills, and associating abstract task requirements with specific personnel capability indicators.

[0067] Optionally, the above-mentioned framework for constructing emergency task requirements analysis may also include: ③ establishing a task priority assessment mechanism, which dynamically assesses the priority of tasks based on the warning level, scope of impact, and / or importance of key nodes.

[0068] (4) Based on the multi-objective optimization matching model, the personnel in the dynamic capability assessment system are intelligently matched with the tasks in the emergency task demand analysis framework to generate an emergency collaboration plan.

[0069] In emergency scenarios involving personnel evacuation, the evaluation focuses on the capacity of each transportation entity, thereby intelligently generating a multi-transport entity capacity matching scheme for collaborative transportation.

[0070] (5) The personnel task matching scheme is dynamically adjusted and optimized based on the real-time changes in the emergency response. This can be achieved by using a machine learning model trained on historical emergency response data to predictively optimize the matching results. The aforementioned machine learning model for decision support can be a fast decision-making algorithm based on the Top-Order Solution Approximation Method (TOPSIS). Using this algorithm can meet the timeliness requirements of emergency response, thereby providing decision-makers with the optimal match that satisfies their preferences.

[0071] By employing this embodiment of the invention, intelligent integrated emergency collaborative processing involving multiple operating entities can be achieved.

[0072] In a specific embodiment of the present invention, the standardized capability profile vector representation of each robot is as follows: The explanations for each part are as follows: Robot type identifier (e.g., reconnaissance drone, firefighting robot, material transport AGV, security patrol robot).

[0073] Skill Vectors. Precisely mapped to the human skill system (S1-S6). Reconnaissance Drones: Score highly in S2-Security Assurance (security hazard identification) and S4-Information and Communication (data analysis capabilities). Firefighting Robots: Score highly in S3-Emergency Rescue (firefighting skills, special environment rescue). Medical Assistance Robots: Can provide remote diagnostic support or medication delivery in S3-Emergency Rescue (emergency medical care capabilities). Multilingual Broadcasting Robots: Can supplement S6-Passenger Services (multilingual communication, psychological counseling).

[0074] (Environmental adaptability): Evaluate its operational performance in harsh environments such as dense smoke, standing water, confined spaces, and strong electromagnetic interference.

[0075] (Battery life and load): Operating time, charging / refueling time, maximum load capacity.

[0076] (Communication Protocol): The data interface standard with the emergency command system, and whether it can be seamlessly integrated.

[0077] (Payload / Task Payload): The collective term for the equipment, modules, or materials carried by a robot to perform a specific task.

[0078] In a specific embodiment of the present invention, the aforementioned human-machine collaboration spectrum includes capability substitution, capability enhancement, and capability cooperation. Its meanings are as follows: ① Capability substitution refers to the complete replacement of humans in high-risk environments (such as the core area of ​​a fire or a chemical spill zone) to perform tasks. In this case, the optimization model should prioritize robots and set the personnel constraint for the corresponding area to 0. ② Capability enhancement refers to robots acting as "tools" or "exoskeletons" for humans, enhancing their capabilities. For example, workers wear powered exoskeletons to lift heavy objects, and drones provide commanders with real-time aerial vision. In the model, for ③ Capability collaboration refers to the joint completion of tasks by humans and robots as team members, with robots leading the way and conducting reconnaissance, while humans follow behind to perform detailed operations and make decisions, satisfying the "robot sub-tasks" and "human sub-tasks" in the task decomposition, as well as the corresponding timing or dependency constraints.

[0079] In a specific embodiment of the present invention, a human-machine collaborative enhancement mechanism is activated to identify capability gaps, and then robot matching is performed to generate a human-machine collaborative solution. The relevant content is as follows, using a dense smoke environment as an example. The capability gap identified in the dense smoke environment is: the "fire reconnaissance" mission requires S3-special environment rescue capability, but on-site personnel may not have the equipment and ability to enter the core area of ​​dense smoke. The system identifies this skill gap. Robot matching refers to the system matching a reconnaissance robot / drone equipped with a thermal imaging camera and a toxic gas detector from the robot capability database. Its SkillVector scores high on S2 and S3 related indicators, and EnvAdapt is suitable for dense smoke environments.

[0080] The steps described above for matching robots and generating human-robot collaboration solutions may include: ① Task 1 (Robot Execution): Dispatch two high-temperature resistant reconnaissance robots into the fire scene to transmit real-time data on the fire source location, temperature, toxic gas concentration, and thermal imaging distribution map of trapped personnel.

[0081] ②Task 2 (Human-machine collaboration): Command center personnel (with S4-data analysis capabilities) mark the optimal rescue route and evacuation passage on the 3D map based on the data transmitted back by the robot, and push this information to the on-site firefighters and evacuation guides in real time.

[0082] ③Task 3 (Personnel Execution): Firefighters (possessing S3-fire rescue skills) will carry appropriate firefighting equipment and enter along a safe path based on the precise information provided by the robot to carry out precise firefighting and rescue.

[0083] ④ Task 4 (Human-Robot Collaboration): The patrol robot (equipped with S6 multilingual communication capabilities) continuously broadcasts multilingual evacuation instructions in the outer evacuation area to calm passengers and alleviate the pressure on passenger service personnel. Furthermore, the success rate of a person's collaborative tasks with a certain type of robot can be recorded, forming a dynamic "human-robot trust" parameter. Cross-collaboration and The level of trust between humans and machines influences this choice; priority should be given to "human-machine combinations" with a good history of successful collaboration.

[0084] In a specific embodiment of the present invention, the above-mentioned fast decision-making algorithm based on TOPSIS includes: ① Construct a judgment matrix: Make judgments based on the "nine-scale method" (1 = equally important, 3 = slightly important, ..., 9 = extremely important). Judgment content: the importance of "passenger evacuation time" vs. "handling cost", "passenger evacuation time" vs. "resource allocation balance", and "handling cost" vs. "resource allocation balance" (e.g., time is "extremely important" than cost, scale is 9; time is "very important" than balance, scale is 7; balance is "slightly important" than cost, scale is 3).

[0085] ② Table 2 shows an example of calculating the weight vector: Table 2 By calculating the largest eigenvalue and the corresponding eigenvector of the matrix and then normalizing them, the system can derive the commander's preference weight vector. This weight vector accurately reflects the commander's decision-making intent at this moment: approximately 80% of the focus is on time, 15% on balance, and only about 5% on cost.

[0086] ③ Determine the positive and negative ideal solutions.

[0087] Positive ideal solution (PIS / Z+): Find the optimal value for each column.

[0088] .

[0089] Negative Ideal Solution (NIS / Z-): Find the worst value (i.e. the maximum value) for each column.

[0090] .

[0091] ④ Calculate the weighted distance: The system uses the preference weights W of the commanders to calculate the weighted Euclidean distance from each scheme to the positive and negative ideal solutions.

[0092] Distance to the ideal solution ( ): .

[0093] This distance measures the solution. There are "multiple undesirable" solutions. The distance to the negative ideal solution ( ): This distance measures the solution. There's a saying that "more is never bad."

[0094] ⑤ Calculate and rank the relative proximity: For each scheme Calculate its relative closeness to the ideal solution. . Between [0, 1]. The closer the value is to 1, the closer the solution is to the positive ideal solution, and the further it is from the negative ideal solution, meaning the better the overall performance. All solutions are then categorized according to... The values ​​are sorted from highest to lowest, and the highest value is the optimal decision.

[0095] In a specific embodiment of the present invention, the above-mentioned multi-objective optimization algorithm MOEA / D based on decomposition and evolution includes: (1) Representation of symbols, sets, and decision variables: Set P = {p1,..., pn} is the set of personnel; T = {t1,..., tm} is the set of tasks; S = {s1,..., sk} is the set of skills; D = {d1,..., do} is the set of departments; R = {r1,..., rφ} is the set of robots; L = {l1,..., lω} is the set of command levels. Parameters: Personnel information {Department Dept(pi)∈D, Job level Level(pi)∈L, Skill(pi, sk)∈R+, Location Loc(pi), Fatigue index Fatigue(pi), Historical task completion rate / collaboration score Hisperf(pi), Key location marker IsKey(pi) is 1 if it is a key personnel, otherwise it is 0}; Task requirement information Task The coordinates of the location where the event occurred; :Task skills The minimum requirements; :Task Command level Personnel requirements (e.g., one on-site supervisor is required); :Task Total number of people required; :Task The urgency level is weighted (red alert is 1.0, blue alert is 0.2); :Task The latest response time limit.}Environment and Context Data The current emergency type E (such as fire, equipment failure, security incident, etc.); From position arrive Estimated travel time} Robot-assisted capabilities :robot In simulation skills The ability value above; :robot Is it currently available? Decision variables: x(pi, tj)∈{0,1}: personnel-task allocation; y(rq, tj)∈{0,1}: robot-task allocation.

[0096] (2) Set the objective function: Normalize each sub-objective to [0,1] and explicitly form it as a vector so that MOEA / D decomposition can be performed.

[0097] Define the normalization operator norm(·): normalizes according to historical or observable maximum and minimum values.

[0098] Target vector F(X,Y) = [F1, F2, F3, F4], Maximize matching efficiency; Maximize organizational synergy; Minimize risk management; Maximize adaptability.

[0099] (2-1) Objective Maximize matching efficiency This is a composite objective, composed of three weighted sub-objectives. The formula is as follows: (Maximize capability matching) (Calculate the sum of the dot products of the personnel skill vector and the task requirement vector for each matching pair).

[0100] (Minimize response time): (Minimize the total travel time of all dispatched personnel).

[0101] (Optimization of resource utilization): (Minimize the extent to which personnel levels exceed the required levels in non-urgent tasks. Use a negative sign to maximize uniformity.)

[0102] (2-2) Objective Maximize organizational synergy (Cross-departmental collaboration efficiency): Collaboration matrix This indicates the efficiency of collaboration between departments.

[0103] (Chain of command integrity): A plan to punish chaotic command. in, This is a function that determines whether a person is a commander. This is intended to ensure that each mission has exactly one commander.

[0104] (Information flow smoothness): Historical collaboration scores are used as a proxy indicator.

[0105] (2-3) Objectives Minimize risk management.

[0106] (Key Personnel Availability): Minimize the number of key personnel scheduled.

[0107] (Emergency response reserve): Maximize the total capability value of unallocated senior talent.

[0108] (Personnel Fatigue): Minimize the total fatigue of dispatched personnel.

[0109] (2-4) Objectives Maximize adaptability.

[0110] (Optimability of the plan): The higher the skill redundancy of the dispatched team, the more flexible it is.

[0111] (Human-machine collaboration efficiency): Robots can enhance certain skills.

[0112] (Maximize the total skill value after human-machine combination) (Upgrade responsiveness): Maximize the number of unused personnel and robots.

[0113] (3) Set constraints: The constraints must be met, including unique allocation of personnel within a single time period, unique allocation of robots, number of personnel in a task, task skill constraints (including robots), command level constraints, and time window / response time limit constraints.

[0114] ① Unique personnel assignment: Each person can be assigned to at most one task. .

[0115] ② Unique robot assignment: Each available robot can be assigned to at most one task. .

[0116] ③ Task number constraint: The number of people assigned to each task must meet the requirements. .

[0117] ④ Task skill constraints (including robots): The skill requirements for each task must be met by both humans and machines.

[0118] ⑤ Command level constraints: The command structure for each mission must meet the requirements.

[0119] Where (I(·) is an indicator function, which is 1 if the condition is true, and 0 otherwise) ⑥ Time window / response time limit: Or add it to the target as a penalty. In a specific embodiment of the present invention, an example of a capability indicator system is provided. The capability indicator system includes: Capability ① - Traffic Operation Management Skills - Passenger flow management ability, traffic coordination and control, handling of sudden congestion, hub guidance and command (Passenger flow management ability measures the ability to organize evacuation in high-density crowds; traffic coordination and control measures the ability to coordinate the connection of multiple modes of transportation; handling of sudden congestion measures the ability to quickly identify and resolve traffic congestion; hub guidance and command measures the ability to guide passengers in complex spaces).

[0120] Capability ② - Safety Assurance Skills - Safety Hazard Identification, Emergency Response, Security Equipment Operation, Hazardous Materials Handling (Safety Hazard Identification measures sensitivity to identifying potential safety risks; Emergency Response measures the ability to handle various types of sudden safety incidents; Security Equipment Operation measures proficiency in using security monitoring and inspection equipment; Hazardous Materials Handling measures professional ability to identify and handle hazardous materials).

[0121] Capability ③ - Emergency Rescue Skills - Emergency first aid capabilities, fire rescue skills, special environment rescue, and mass rescue organization (Emergency first aid capabilities measure the professional level of providing emergency medical assistance; fire rescue skills measure the professional ability to rescue from disasters such as fires; special environment rescue measures the ability to rescue in enclosed spaces, high altitudes, and other environments; mass rescue organization measures the ability to organize large-scale rescue operations).

[0122] Capability 4 - Information and Communication Skills - Emergency communication operation, information system management, data analysis ability, multi-system collaborative operation (Emergency communication operation, measuring proficiency in using various emergency communication equipment; information system management, measuring the ability to maintain the normal operation of the hub information system; data analysis ability, measuring the ability to analyze and monitor data and identify anomalies; multi-system collaborative operation, measuring the ability to coordinate the collaborative work of multiple information systems).

[0123] Capability ⑤ - Cross-departmental coordination skills - Multi-party collaboration ability, resource allocation ability, command and coordination ability, and information sharing efficiency (Multi-party collaboration ability measures the ability to work in collaboration with railways, airports, subways, etc.; resource allocation ability measures the ability to allocate cross-departmental resources in emergency situations; command and coordination ability measures the ability to command and coordinate in mixed formation teams; information sharing efficiency measures the ability to promote the rapid flow of cross-departmental information).

[0124] Competency 6 - Passenger Service Skills - Special Group Service, Multilingual Communication, Psychological Counseling, and Complaint Handling (Special Group Service measures the ability to serve the elderly, infirm, disabled, pregnant women, and other special groups; Multilingual Communication measures the ability to communicate in multiple languages; Psychological Counseling measures the ability to soothe anxious passengers; Complaint Handling measures the ability to handle emergency complaints and conflicts).

[0125] In a specific embodiment of the present invention, the task priority assessment mechanism includes: ① designing task priorities based on the four-level early warning color system (red, orange, yellow, and blue) in the contingency plan; ② assessing the urgency of tasks based on the scope of impact of the emergency (single unit, two or more units, the entire hub area, and peripheral areas); ③ scoring the importance of tasks according to key nodes (important locations, major holidays, and periods of important social activities); and ④ making decisions to dynamically adjust task priorities based on the above task priorities, urgency assessments, and importance scores.

[0126] In a specific embodiment of the present invention, the emergency responsibility matrix includes: the hub emergency center / joint command headquarters typically acts as the "responsible party" (A) for emergency decision-making and command, possessing unified command and dispatch authority, and organizing and coordinating multiple forces to complete the emergency response. Operating groups, railways, airports, subways, etc., become the "responsible parties" (R) for emergency response and on-site execution, needing to directly activate their own emergency mechanisms and cooperate with the center to complete specific handling tasks. Hospitals / emergency centers, etc., become the "supporters" (S), providing crucial assistance in order maintenance, traffic management, medical rescue, evacuation and resettlement, and rapidly assembling professional forces depending on the type of event. The municipal transportation commission primarily acts as the "consultant" (C), while also undertaking support and leading responsibilities for specific tasks (such as emergency traffic management) when necessary. Information must be updated in real time to the "informers" (I), such as the municipal emergency commission, higher-level authorities, media, and the general public, forming a complete emergency information flow with multi-level reporting and simultaneous release. Table 1 shows an example of emergency state RASCI coding using the above method.

[0127] Based on the specific embodiments described above, the skills of personnel under each operating entity are differentiated according to the aforementioned capabilities.

[0128] Table 1 Examples of RASCI coding in emergency situations In another specific embodiment of the present invention, the overall process of solving the emergency coordination scheme can be broken down as follows: preprocessing → initial feasible solution generation → main optimization MOEA / D-DRA (or RVEA) → local refinement. The details are as follows: (1) Parameter preprocessing.

[0129] Data clustering: Cluster tasks and personnel according to geography (distance), task type and skill requirements to form several sub-problems (which can be done in parallel) to reduce the search space and accelerate online response.

[0130] Key position identification: Mark key positions with the IsKey flag and the necessary command personnel set for initial integer planning assurance.

[0131] (2) Generation of initial feasible solutions (constraints first): First, for each task sub-cluster, use integer linear programming or heuristic greedy algorithm to generate a baseline solution set that satisfies hard constraints (command level, minimum skill, minimum number of people, whether within the time limit): minimize "over-allocation of senior personnel" or minimize "overall response time" as the initial objective preference.

[0132] If integer programming is not feasible, it degenerates into a heuristic greedy algorithm: prioritize allocation based on urgency and skill matching to ensure that key positions and minimum skill requirements are met; output several baseline feasible solutions as the initial population source for MOEA / D.

[0133] (3) Main optimization engine—MOEA / D-DRA (or RVEA) generates Pareto sets. MOEA / D-DRA is selected as the first choice. The key point of MOEA / D is: decompose the original four objectives F1..F4 into L sub-problems, and each sub-problem corresponds to a weight vector. Each subproblem is evaluated using a scalarization function (Tchebycheff or weighted sum + correction). Neighborhood collaboration: Each subproblem exchanges information and mutation operations only with its neighboring subproblems. Dynamic resource allocation (DRA) enhancement: Dynamically allocates search resources (adjusting the priority of subproblems being selected for updates within iterations) to improve convergence efficiency and coverage. Specific parameters: Population / Number of subproblems L = 200; Neighborhood size: 30; Mutation / crossover: Task exchange mutation (randomly selecting two individuals to exchange their tasks); Local replacement mutation (replacing one individual within the same task with a similarly capable candidate from the pool); Generations: 1500. Constraint handling: Immediate repair after generating new individuals: If hard constraints are violated, the repair module (based on integer programming or heuristic replacement) is invoked to make it feasible; if repair is not possible, the individual is discarded or penalized. Output: Retains the Pareto front candidate set (archive) and a representative sample set.

[0134] (4) Local refinement (post-processing of Pareto solutions). Perform local search for each candidate solution: The Hungarian algorithm / assignment method can be used (converting the sub-matching for a certain task in the task-personnel allocation to a binary match, and using the Hungarian method to find the optimal local replacement in the candidate pool to reduce response time or fatigue) to perform mandatory checks on key positions (if a solution has an unreasonable configuration in key positions, it is forcibly replaced by integer programming according to priority and re-evaluated). The time is controlled by setting an upper limit on the number of local refinement iterations (maximum 50 local changes per solution).

[0135] Corresponding to the above method, the present invention also provides an integrated emergency coordination system for multiple operating entities. The system includes a computer device, which includes a processor and a memory. The memory stores computer instructions, and the processor is used to execute the computer instructions stored in the memory. When the computer instructions are executed by the processor, the system implements the steps of the method described above.

[0136] The multi-operating entity integrated emergency coordination method and system proposed in this invention can achieve precise, efficient, and scientific matching of emergency human resources by constructing a dynamic personnel capability assessment system and task requirement analysis framework, and by using a multi-objective optimization matching model. It abandons the traditional emergency response model that relies on static plans and human experience-based decision-making, improves the collaborative combat capability and emergency response efficiency among multiple operating entities in complex scenarios such as large transportation hubs, and enhances the dynamic adaptability and robustness of emergency plans.

[0137] See Figure 2 The computer device 00 includes: a processor 01, a memory 02, and a computer program stored on the memory 02 and executable on the processor 01. When the processor 01 executes the computer program, it implements the method steps proposed in any of the above embodiments.

[0138] The processor 01 is connected to the memory 02, such as via a bus 03. The processor 01 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor 01 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The bus 03 may include a pathway for transmitting information between the aforementioned components. The bus 03 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 03 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 The text uses only a single thick line to represent a bus, but this does not imply that there is only one bus or one type of bus. Memory 02 stores a computer program corresponding to the human factors data server access control method described in the above embodiments of this application. This computer program is executed under the control of processor 01. Processor 01 executes the computer program stored in memory 02 to implement the content shown in the aforementioned method embodiments.

[0139] Corresponding to the methods described above, the present invention also provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implements the steps of the method as described in any of the above embodiments. The computer-readable storage medium may be a tangible storage medium, such as random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, floppy disk, hard disk, removable storage disk, CD-ROM, or any other form of storage medium known in the art.

[0140] Corresponding to the above methods, the present invention also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the steps of the method as described in any of the above embodiments.

[0141] Those skilled in the art will understand that the exemplary components, systems, and methods described in conjunction with the embodiments disclosed herein can be implemented in hardware, software, or a combination of both. Whether implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this invention. When implemented in hardware, it can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this invention are programs or code segments used to perform the desired tasks. The programs or code segments can be stored in a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried in a carrier wave.

[0142] It should be clarified that the present invention is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of the present invention.

[0143] In this invention, features described and / or illustrated for one embodiment may be used in the same or similar manner in one or more other embodiments, and / or combined with or in place of features of other embodiments.

[0144] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, various modifications and variations of the embodiments of the present invention are possible. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A multi-operating entity integrated emergency coordination method, characterized in that, include: By utilizing a pre-set dynamic capability assessment system for multiple operating entities, the capabilities of personnel belonging to each operating entity under different indicators are dynamically assessed. Analyze the requirements of emergency tasks across different emergency response dimensions, and based on a pre-defined mapping relationship, obtain personnel capability indicators that are associated with the requirements of emergency tasks across different emergency response dimensions. Based on the capabilities of personnel belonging to various operating entities under different indicators, and the personnel capability dimension indicators associated with the needs of emergency tasks in different emergency handling dimensions, a pre-trained multi-objective optimization matching model is used to intelligently match personnel belonging to different operating entities for emergency tasks, and the matched personnel collaboratively handle the emergency tasks.

2. The method according to claim 1, characterized in that, The multi-operating entity dynamic capability assessment system includes an emergency responsibility matrix, a multi-level personnel classification framework, a capability indicator system, and a dynamic capability database. The steps of dynamically evaluating the capabilities of personnel belonging to various operating entities under different indicators using a pre-set multi-operating entity dynamic capability assessment system include: The functions of each operating entity are divided using the aforementioned emergency responsibility matrix; The multi-level personnel classification framework is used to coordinate and manage the emergency organization levels, contingency plan responsibilities, and emergency response levels of various operating entities. The capabilities of personnel belonging to each operating entity are assessed according to the set rules and set indicators included in the capability indicator system. Store and continuously update the competency assessment results for personnel belonging to each operating entity.

3. The method according to claim 1, characterized in that, The emergency task requirements obtained from the analysis, across different emergency response dimensions, are represented in vector form. The emergency response dimensions include one or more of the following: task urgency, required capabilities under different indicators, required equipment type, supported robot capabilities, task geographic coordinates, time constraints for completion, risk coefficient of the task itself, dependencies between tasks, and resource sharing requirements. Before using a pre-trained multi-objective optimization matching model to intelligently match personnel belonging to different operating entities for emergency tasks, the method further includes: dynamically prioritizing emergency tasks based on warning level, the scope of impact of emergencies related to the emergency task, and / or the importance of key nodes; wherein the key nodes include preset locations and time periods.

4. The method according to claim 1, characterized in that, The multi-objective optimization matching model sets multiple objectives, including matching effectiveness objective, organizational synergy objective, risk management objective, and / or adaptability objective; The inputs to the multi-objective optimization matching model include personnel resource information of each operating entity, emergency task demand information and / or environmental and contextual data. The personnel resource information includes basic personnel data, capability assessment data, availability information and historical performance data. The step of using a pre-trained multi-objective optimization matching model to intelligently match personnel belonging to different operating entities for emergency tasks includes: generating a Pareto optimal solution set using a multi-objective optimization algorithm based on decomposition and evolution, and optimizing the generated Pareto optimal solution set based on a hierarchical analysis decision model to generate an emergency coordination plan that includes a personnel-task allocation table, a time schedule table, and / or a resource allocation list.

5. The method according to claim 4, characterized in that, For the generated emergency coordination plan, the method further includes: using a machine learning model trained based on historical emergency response data to predictively optimize the matching results, wherein the machine learning model adopts a fast decision-making algorithm that approximates the ideal solution ranking method.

6. The method according to claim 4, characterized in that, After generating the emergency coordination plan, the method further includes: during the process of matching personnel coordinating the handling of the emergency task, monitoring the fatigue status of the personnel through wearable devices and / or regional video surveillance; when the monitored fatigue status of the personnel reaches a set range, generating and updating the emergency coordination plan, and arranging for the personnel to rest in the updated emergency coordination plan.

7. The method according to claim 1, characterized in that, The method also includes: summarizing the capabilities of personnel under different indicators of all operating entities under dynamic evaluation; analyzing in advance the capabilities that personnel do not possess based on the needs of emergency tasks in different emergency handling dimensions; selecting robots to fill the gaps; and intelligently matching and coordinating the emergency tasks with the robots and personnel belonging to each operating entity. Among these, the capabilities that personnel lack include the ability to conduct rescue operations in special environments, such as dense smoke core areas, high temperature areas, and / or high pressure areas.

8. The method according to claim 1, characterized in that, The type of operating entity is a transportation entity, the capabilities of the personnel belonging to each transportation entity are reflected in the transportation capacity, and the multi-objective optimization matching model is a transportation capacity matching model; The method also includes: based on passenger-side demand indicators including arrival passenger flow characteristics, individual passenger attributes and transfer selection behavior, and transportation entity-side supply indicators including physical conditions, operation organization and information services, combined with environmental factors including weather conditions, urban traffic conditions, major events and holidays, a capacity matching model that balances departure and arrival at the hub is constructed.

9. A multi-operator integrated emergency coordination system, comprising a processor, a memory, and computer programs / instructions stored in the memory, characterized in that, The processor is configured to execute the computer program / instructions, and when the computer program / instructions are executed, the system implements the steps of the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method as described in any one of claims 1 to 8.

Images