A method, equipment and medium for intelligent decomposition and scheduling of fire and rescue missions

Abstract

This invention discloses an intelligent decomposition and scheduling method, equipment, and medium for fire and rescue missions. The method includes the following steps: conducting fire situation analysis to obtain the analysis results; determining multiple fire and rescue missions to be executed based on the analysis results; performing detailed modeling for each fire and rescue mission; generating a scheduling scheme for the fire and rescue missions through multi-objective optimization; and executing the fire and rescue missions according to the generated scheduling scheme. This invention provides a task decomposition framework that automatically identifies tasks by combining rules, cases, and templates, avoiding omissions and improving completeness and accuracy; it also establishes a multi-dimensional personnel capability model for quantitative evaluation, achieving precise matching of personnel and tasks; and employs a multi-objective optimization algorithm to optimize time, risk, and quality, generating a Pareto optimal solution set for decision-making. Furthermore, it achieves real-time monitoring, anomaly detection, and dynamic rescheduling, responding promptly to changes and ensuring the continuous effectiveness of the scheduling scheme.

Description

Technical Field

[0001] This invention relates to the field of task scheduling technology, specifically to a method, equipment, and medium for intelligent decomposition and scheduling of fire and rescue tasks. Background Technology

[0002] Firefighting and rescue are highly complex emergency operations involving multiple tasks such as firefighting, personnel evacuation, water supply, on-site security, and medical assistance. These tasks are subject to complex dependencies and resource competition; therefore, the scientific breakdown of tasks and the rational allocation of personnel directly affect rescue efficiency and success rate.

[0003] However, traditional task breakdown and personnel deployment mainly rely on the commander's experience and on-site judgment. Under the high-pressure environment of a fire, the commander needs to process a large amount of information and make multiple decisions simultaneously, which can easily lead to oversights or suboptimal decisions.

[0004] Currently, the firefighting field mainly relies on contingency plans and commanders' experience to develop standard operational plans for different scenarios, specifying task assignments. Commanders make on-the-spot decisions based on the fire situation and coordinate the actions of various teams via walkie-talkies. However, this method, which depends on experience and contingency plans, has significant limitations: First, the plans lack sufficient flexibility and are difficult to cope with complex and ever-changing fire scenes; second, human decision-making is inefficient and prone to overlooking critical tasks; and finally, each plan is only optimized for the current scenario, lacking quantifiable optimization goals and scientific scheduling algorithms. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method, equipment and medium for intelligent decomposition and scheduling of fire and rescue tasks.

[0006] The first aspect of this invention provides an intelligent decomposition and scheduling method for fire and rescue missions, comprising the following steps: Conduct fire situation analysis and obtain the analysis results of the fire situation; Based on the analysis of the fire situation, several fire rescue tasks that need to be carried out were determined; Detailed modeling is performed for each fire and rescue mission that needs to be carried out; The dispatching scheme for fire and rescue missions is generated through multi-objective optimization, and the fire and rescue missions are executed according to the generated dispatching scheme.

[0007] Furthermore, the fire situation analysis specifically includes the following steps: Obtain multi-dimensional fire scene information; Feature extraction is performed on the multi-dimensional fire scene information to obtain building features, fire features, personnel features, risk features, environmental features, and resource features of the fire scene situation. These features are then output as the analysis results.

[0008] Furthermore, based on the analysis of the fire situation, multiple fire rescue tasks that need to be carried out are determined, specifically through the following steps: Establish a task library, which includes multiple fire and rescue tasks; Feature keywords were extracted from the analysis results of the fire situation, resulting in multiple feature keywords; The rule engine is invoked to identify rules, and multiple fire and rescue tasks that match the feature keywords are determined from the task library as target fire and rescue tasks; Based on the target fire and rescue mission, a similar case search is performed in historical fire and rescue cases to determine the target fire and rescue case; Based on the fire rescue tasks involved in the target fire rescue case, the identified target fire rescue tasks are optimized and adjusted, and the adjustment results serve as multiple fire rescue tasks that need to be executed.

[0009] Furthermore, the step of searching for similar cases in historical fire and rescue cases based on the target fire and rescue mission specifically includes the following steps: A historical fire and rescue case dataset is established; the historical fire and rescue case dataset contains multiple historical fire and rescue cases, and each historical fire and rescue case corresponds to multiple fire and rescue tasks. The identified target fire and rescue missions are matched with the corresponding fire and rescue missions for each historical fire and rescue case in the dataset. Historical fire and rescue cases in which the target fire and rescue mission appears more frequently than a preset frequency threshold are used as target fire and rescue cases.

[0010] Furthermore, the detailed modeling of each fire and rescue task to be performed includes the following steps: For each fire and rescue mission to be performed, time attribute modeling, spatial attribute modeling, resource requirement modeling, and priority modeling are performed. The time attribute modeling includes the start time, duration, and end time of the fire and rescue mission; the spatial attribute modeling includes the spatial orientation of the fire and rescue mission; the resource requirement modeling includes the personnel requirements, equipment requirements, and material requirements of the fire and rescue mission; and the priority modeling includes the priority of the fire and rescue mission. Determine the dependencies between each fire and rescue mission that needs to be performed and other fire and rescue missions that need to be performed.

[0011] Furthermore, prior to the step of generating a dispatch plan for fire and rescue missions through multi-objective optimization, a step of quantitatively assessing personnel is also included, specifically comprising the following steps: Input fire and rescue personnel data; the fire and rescue personnel data includes static personnel data and dynamic personnel data; Based on the static and dynamic personnel data, an individual ability assessment is conducted on each firefighter in terms of skills, qualifications, experience, physical fitness, and psychological dimensions to obtain an ability vector for each firefighter. The comprehensive capability score of each firefighter is calculated based on capability vectors.

[0012] Furthermore, the method of generating a dispatching scheme for fire and rescue missions through multi-objective optimization specifically includes the following steps: Construct a personnel-task matrix based on the required fire and rescue missions and the capabilities of fire and rescue personnel; Define the core objectives of fire and rescue missions; these core objectives include minimizing total completion time, minimizing total personnel risk, maximizing overall mission completion quality, minimizing resource consumption, and maximizing load balancing. Several personnel-task assignment lists are generated as the initial population. The initial population is optimized using a non-dominated sorting genetic algorithm to obtain the Pareto optimal solution after the non-dominated sorting genetic algorithm has converged. The Pareto optimal solution is translated into a textual expression and used as a scheduling plan for fire and rescue missions.

[0013] Furthermore, the optimization of the initial population using a non-dominated sorting genetic algorithm specifically includes the following steps: For each core objective, an objective function is established, and the value of each individual in the population is calculated in each objective function. Multiple quintuples of data are obtained as the solution set for each individual in the population. The solution set is sorted non-dominated, and the crowding distance between solution sets is calculated. The Pareto front individuals are then output. New populations are generated by selecting, crossovering, and mutating individuals using Pareto frontier individuals. The new population is added to the non-dominated sorting genetic algorithm, and the process of calculating the value of each individual in each objective function is returned until the Pareto front individuals converge.

[0014] Another aspect of the present invention discloses an electronic device, including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the above-described intelligent decomposition and scheduling method for fire and rescue tasks.

[0015] In another aspect, the present invention discloses a computer-readable storage medium storing a program that is executed by a processor to implement the above-described intelligent decomposition and scheduling method for fire and rescue tasks.

[0016] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0017] The embodiments of this invention offer the following advantages: First, it provides a systematic task decomposition framework that automatically identifies required tasks by combining rules, cases, and templates to avoid omissions, thereby improving the completeness and accuracy of task decomposition. Based on this, a multi-dimensional personnel capability model is established. By quantitatively assessing personnel capabilities and calculating task suitability, precise matching of personnel and tasks is achieved, enhancing the scientific nature of scheduling. Furthermore, the system employs a multi-objective optimization algorithm that can simultaneously optimize multiple objectives such as time, risk, and quality, generating a Pareto optimal solution set, providing decision-makers with diverse options. Finally, this invention also implements real-time monitoring, anomaly detection, and dynamic rescheduling functions for task execution, enabling timely responses to changes in the fire situation and ensuring the continued effectiveness of the scheduling plan.

[0018] Additional aspects and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description or may be learned by practice of the invention. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of the basic steps of an intelligent decomposition and scheduling method for fire rescue missions according to the present invention; Figure 2 This is a schematic diagram illustrating the priority modeling effect of the task modeling steps in the method of this invention; Figure 3 This is a schematic diagram illustrating the effect of the personnel quantitative assessment step in the method of this invention; Figure 4 This is a schematic diagram of the implementation process of the multi-objective optimization step in the method of the present invention; Figure 5This is a schematic diagram of the implementation process of dynamic task scheduling in the method of the present invention; Figure 6 This is a schematic diagram of the structure of an electronic device according to the present invention; Figure 7 This is a schematic diagram of a computer-readable storage medium structure according to the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0022] Traditional task breakdown and personnel dispatch rely primarily on the commander's experience and on-site judgment. However, under the high-pressure environment of a fire, commanders need to process large amounts of information and make multiple decisions simultaneously, which can easily lead to oversights or suboptimal decisions. The development of technologies such as artificial intelligence and operations research has provided new possibilities for intelligent dispatching in fire and rescue operations.

[0023] Therefore, the first embodiment of the present invention provides an intelligent decomposition and scheduling method for fire and rescue tasks, such as... Figure 1 As shown, it includes the following steps: S1. Conduct fire situation analysis and obtain the analysis results of the fire situation; S2. Based on the analysis of the fire situation, determine the multiple fire rescue tasks that need to be carried out; S3. Detailed modeling of each fire and rescue mission that needs to be performed; S4. Generate a dispatch plan for fire and rescue missions through multi-objective optimization, and execute fire and rescue missions according to the generated dispatch plan.

[0024] This invention deeply integrates task modeling and multi-objective optimization mechanisms to construct a complete intelligent fire rescue task decomposition and scheduling scheme, from situational awareness to task decomposition, and from optimization planning to dynamic execution.

[0025] The implementation process of each step of this invention is described in detail below: S1. Conduct fire situation analysis to obtain the analysis results of the fire situation.

[0026] In step S1, the fire situation analysis specifically includes the following steps: S1-1. Obtain multi-dimensional fire scene information.

[0027] In this embodiment of the invention, fire scene information of different dimensions can be obtained through multiple channels. For example, the fire incident address, unit name, burning materials described by the alarm caller, whether anyone is trapped, and the initial burning location can be obtained through the data interface of the fire protection system; or, through operations such as thermal imaging detection, environmental monitoring, and building structure detection by drones, parameters such as the fire location, spread direction, burned area, temperature distribution, smoke concentration, types and concentrations of toxic gases (CO, HCN, etc.), wind direction and speed, and building deformation data can be obtained. In addition, preset fire scene-related data can be imported into a database, such as building structure, floor plan, location of fire protection facilities, evacuation routes, hazardous materials storage points, and fire hydrant locations. By obtaining multi-dimensional fire scene information, multi-dimensional fire scene features can be extracted in this embodiment of the invention for task decomposition, modeling, and optimization.

[0028] S1-2. Feature extraction is performed on multi-dimensional fire scene information to obtain building features, fire features, personnel features, risk features, environmental features, and resource features of the fire scene situation. These features are then output as the analysis results.

[0029] After acquiring multi-dimensional fire scene information, this embodiment of the invention performs feature extraction on the fire scene information. In a preferred embodiment, information from different sources is first overlaid and calibrated on a unified spatiotemporal reference. For example, a building BIM model can be established, and then the UAV thermal imaging image is matched with the building floor plan to accurately locate the room on fire.

[0030] In terms of feature extraction, this embodiment of the invention mainly extracts feature information in six dimensions, including building features, fire features, personnel features, risk features, environmental features, and resource features. Building features include building type (e.g., floor height, underground space, span per floor), building structure (e.g., brick-concrete structure, frame structure), and building usage (e.g., residential, factory, shopping mall). Fire features include fire scale level (e.g., small-scale fire, medium-scale fire, large-scale fire), fire development stage (e.g., initial stage, development stage, intense stage), and characteristics of combustible materials contained in the building. Personnel features include whether anyone is trapped (yes / no), the estimated number of trapped persons, and their possible locations. Risk features include the specific location and distance from external risk sources that may affect the fire (e.g., explosives, chemicals, high-voltage power lines). Environmental features include wind direction and speed, temperature, and traffic conditions on the day of the fire. Resource features include available personnel and firefighting resources capable of reaching the fire scene. This invention, through multi-dimensional feature extraction operations, can map fire scene features to specific fire rescue tasks for task decomposition, modeling, and scheduling.

[0031] S2. Based on the analysis of the fire situation, determine the multiple fire rescue tasks that need to be carried out.

[0032] In step S2, based on the analysis of the fire situation, multiple fire rescue tasks that need to be performed are determined, specifically through the following steps: S2-1. Establish a task library, which includes multiple fire and rescue tasks.

[0033] In this embodiment of the invention, a standard task library is first established, which stores various specific fire and rescue tasks, including firefighting tasks, evacuation tasks, support tasks, alert tasks, and command tasks. Each fire and rescue task includes the task name and description, required skills and qualifications, required number of personnel, required equipment list, estimated execution time, risk level, and preceding and subsequent tasks.

[0034] As specific examples, firefighting tasks include: interior attack firefighting (entering the building to extinguish fire), exterior attack firefighting (suppressing fire from the outside), foam firefighting (using foam extinguishing agents), dry powder firefighting (using dry powder extinguishing agents), and firebreaks (setting up firebreaks); evacuation tasks include: personnel search and rescue (searching for trapped personnel), evacuation guidance (guiding personnel to evacuate), medical rescue (on-site first aid), and psychological support (soothing trapped personnel); support tasks include: water supply support (establishing a water supply system), communication support (maintaining uninterrupted communication), lighting support (providing on-site lighting), and breaching operations (breaking down doors, windows, and walls); security tasks include: on-site security (setting up warning lines), traffic control (managing traffic), personnel count (counting participating personnel), and safety monitoring (monitoring on-site safety); and command tasks include: on-site command (unified command and coordination), information collection (collecting fire scene information), plan development (developing rescue plans), and reporting to superiors (reporting the situation to superiors).

[0035] S2-2. Feature keywords are extracted from the analysis results of the fire situation to obtain multiple feature keywords.

[0036] In this embodiment of the invention, feature keywords are extracted from the multi-dimensional feature information extracted in step S1 to determine the feature keywords of the fire scene (such as high-rise buildings, people trapped, dust, medium-sized fire, etc.).

[0037] S2-3. Call the rule engine to perform rule recognition, and determine multiple fire rescue tasks that match the feature keywords from the task library as the target fire rescue task.

[0038] The rule engine invoked in this embodiment of the invention can automatically identify the required tasks based on fire scene characteristics. The rule engine loads multiple task rules associated with different keywords and matches fire rescue tasks based on the rule recognition of these keywords. For example, for keywords related to building characteristics, after recognizing the keyword "high-rise building," the rule engine will automatically match high-altitude rescue tasks; after recognizing the keyword "underground space," it will automatically match smoke extraction and lighting tasks; after recognizing the keyword "large-span building," it will automatically match building structure monitoring tasks; and if it recognizes the keyword "timber structure building," it will match fire isolation tasks. Similarly, for keywords related to fire intensity characteristics, the rule engine will match basic firefighting tasks for small fires, add water supply and evacuation tasks for medium fires, and for large or extremely large fires, it may add multi-point firefighting and reinforcement coordination tasks for comprehensive task deployment. For other keywords, such as "people trapped" or "injured", the rule engine will automatically match search and rescue missions, evacuation guidance missions, and medical rescue missions; if keywords such as "hazardous chemicals", "explosion risk", or "collapse risk" appear, the rule engine will match chemical defense missions, safe distance warning missions, and structural reinforcement missions.

[0039] S2-4. Based on the target fire and rescue mission, conduct a similar case search in historical fire and rescue cases to identify the target fire and rescue case.

[0040] In steps S2-4, a similar case search is performed in historical fire and rescue cases based on the target fire and rescue mission. This specifically includes the following steps: S2-4-1. Establish a historical fire and rescue case dataset; the historical fire and rescue case dataset contains multiple historical fire and rescue cases, and each historical fire and rescue case corresponds to multiple fire and rescue tasks; S2-4-2. Match the identified target fire and rescue task with the corresponding fire and rescue task for each historical fire and rescue case in the dataset; S2-4-3. Historical fire and rescue cases in which the frequency of occurrence of the target fire and rescue mission is higher than a preset frequency threshold are used as target fire and rescue cases.

[0041] In this embodiment of the invention, after determining the target fire rescue mission, the target fire rescue mission is further matched against a historical fire rescue case dataset. By comparing dimensions such as building, fire intensity, and risk, multiple fire rescue cases that are similar to the current fire scene are identified, and these cases are used as target fire rescue cases to supplement and improve the current fire rescue mission.

[0042] S2-5. Based on the fire rescue tasks involved in the target fire rescue case, optimize and adjust the identified target fire rescue tasks, and the adjustment results shall be used as multiple fire rescue tasks to be executed.

[0043] After identifying the target fire and rescue case, this embodiment of the invention adds, reduces, or adjusts the target fire and rescue tasks based on the target fire and rescue case. For example, if multiple cases in the target fire and rescue case involve a specific fire and rescue task, that task can be added to the target fire and rescue tasks, while simultaneously excluding or replacing target fire and rescue tasks that conflict with that task. This embodiment of the invention, through a rule engine, can establish a systematic task decomposition framework, automatically identify the required tasks based on the fire scene situation, and form a target fire and rescue task list.

[0044] S3. Detailed modeling of each fire and rescue mission that needs to be performed.

[0045] In step S3, a detailed model is created for each fire and rescue task that needs to be performed, which includes the following steps: S3-1. Perform time attribute modeling, spatial attribute modeling, resource requirement modeling, and priority modeling for each fire and rescue mission to be performed; among which, time attribute modeling includes the start time, duration, and end time of the fire and rescue mission; spatial attribute modeling includes the spatial orientation of the fire and rescue mission; resource requirement modeling includes the personnel requirements, equipment requirements, and material requirements of the fire and rescue mission; priority modeling includes the priority of the fire and rescue mission.

[0046] In step S3-1, after obtaining the fire rescue tasks to be performed, each fire rescue task is modeled to adapt it to the current fire scenario.

[0047] For example, time-based modeling requires determining the start time, duration, and end time of a fire rescue mission. Time modeling can be derived from situational analysis or estimated from empirical databases or formula libraries based on parameters such as mission type, fire scale, and environmental complexity. For spatial attribute modeling, spatial parameters for each mission can be determined based on building layout, fire location, and building collapse conditions. For resource attribute modeling, the personnel and equipment requirements for fire rescue missions can be summarized, and then the equipment wear and tear and shareable equipment can be determined, thus allocating sufficient personnel and equipment for each mission. Finally, priority modeling, such as... Figure 2 As shown, the priority of different tasks can be determined by factors such as building layout, task type, and fire situation. For example, the priority of personnel search and rescue tasks can be adjusted to the highest level, and the priority of fire fighting tasks on lower floors can be set higher than that of fire fighting tasks on higher floors.

[0048] S3-2. Determine the dependencies between each fire and rescue task that needs to be performed and other fire and rescue tasks that need to be performed.

[0049] Since different fire and rescue tasks have a sequential execution relationship, this embodiment of the invention will automatically infer and label the dependencies between task pairs based on the information recorded in the fire and rescue tasks. Dependencies include prerequisite dependencies, parallel dependencies, mutual exclusion dependencies, triggering dependencies, and conditional dependencies. Prerequisite dependencies refer to tasks A being completed before tasks B, such as "T06 water supply guarantee" being a prerequisite for "T01 interior attack and fire extinguishing" (no water, no attack); parallel relationships refer to tasks A and B being able to be executed simultaneously, such as "T01 interior attack and fire extinguishing" (fourth floor) and "T03 personnel search and rescue" (fifth floor) being able to be executed concurrently when spatially isolated and resources do not conflict; mutual exclusion relationships refer to tasks A and B being unable to be executed simultaneously due to competition for the same critical resource (such as the only large demolition vehicle); triggering relationships refer to tasks A being completed or having a specific result automatically triggering the start of task B, such as the "finding trapped personnel" task triggering the "medical rescue preparation" task; conditional dependencies refer to tasks B being executed depending on a certain result condition of task A, such as whether the "demolition" task is carried out depends on whether the "fire reconnaissance" confirms whether the door is locked, etc. This invention visualizes and structures the dependencies between fire rescue tasks in the form of directed acyclic graphs or temporal network graphs (e.g., Figure 3 (T0→T6→T1→T2 in the model). In this embodiment of the invention, by modeling the fire rescue mission and determining the dependencies between the missions, the order of tasks, parallel relationships, and resource competition relationships can be clarified, and a reasonable mission execution plan can be generated.

[0050] S4. Generate a dispatch plan for fire and rescue missions through multi-objective optimization, and execute fire and rescue missions according to the generated dispatch plan.

[0051] In some embodiments, before performing step S4, a step of quantitatively assessing the personnel is included, specifically including the following steps: S4-0-1. Input fire and rescue personnel data; fire and rescue personnel data includes static personnel data and dynamic personnel data.

[0052] In this embodiment of the invention, the static data of fire and rescue personnel is obtained through the corresponding fire personnel file system, including training records, skill certification list (firefighting, demolition, first aid, etc.), qualification certificate level (junior / intermediate / senior firefighter, special operation certificate), years of service, types and number of rescue cases participated in, command experience, and other parameters; dynamic data is obtained through individual equipment or duty system, including physical condition, psychological state, heart rate, fatigue level, etc.

[0053] S4-0-2. Based on static and dynamic personnel data, conduct individual ability assessments for each firefighter in terms of skills, qualifications, experience, physical fitness, and psychological dimensions to obtain an ability vector for each firefighter. S4-0-3. Calculate the comprehensive capability score of each firefighter based on capability vectors.

[0054] After acquiring data on fire and rescue personnel, this embodiment of the invention quantifies and scores each firefighter across five core dimensions. Specifically, this embodiment first establishes a multi-dimensional capability model for firefighters, and then assesses individual capabilities across five dimensions: skills, qualifications, experience, physical fitness, and psychological state. For example, the skills dimension is scored based on the firefighter's mastery of firefighting skills (water hose operation, foam extinguishing, dry powder extinguishing, etc.), rescue skills (rope rescue, breaching skills, medical first aid, etc.), driving skills (fire truck driving, special vehicle operation, etc.), and professional skills (chemical protection, diving, high-altitude operations, etc.). The qualifications dimension is scored based on the firefighter's qualifications (primary / intermediate / advanced), special operations qualifications (breaching, chemical protection, high-altitude operations, etc.), command qualifications (squad leader, company commander, battalion commander, etc.), and professional certificates (first responder, diver, etc.). The experience dimension is scored based on the firefighter's years of service, number of firefighting operations, successful cases, and training duration. The physical fitness dimension is primarily assessed based on factors such as strength (load-bearing capacity, pulling force, pushing force), endurance (continuous working time, cardiopulmonary function), speed (running speed, reaction speed), and agility (body coordination, balance). The psychological dimension is primarily assessed based on factors such as resilience, decisiveness, teamwork, and sense of responsibility. Finally, the scores from the five dimensions are mapped to a range of 0-100, and a weighted sum is calculated to determine the comprehensive ability score for each firefighter. Figure 3 As shown. This embodiment of the invention achieves precise matching of personnel to tasks by quantitatively assessing multiple dimensions of personnel's abilities, including skills, experience, physical strength, and psychological qualities.

[0055] In another embodiment, team capability assessment can be conducted by combining the scores of multiple individuals to determine parameters such as the skill coverage (whether the skill set of team members covers the skills required for the task), capability complementarity (whether the capabilities of team members are complementary), teamwork synergy (the history of collaboration among team members), and leadership (whether there are experienced leaders in the team), in order to evaluate the collective effectiveness of the personnel combination.

[0056] In another embodiment, the required equipment can be calculated based on factors such as mission type, fire scene environment, and operation time to accurately determine the types and quantities of equipment needed. Through global calculations of personnel and equipment, precise matching of personnel, equipment, and missions can be achieved, improving the scientific nature of mission scheduling.

[0057] In step S4, a dispatching plan for the fire and rescue mission is generated through multi-objective optimization, such as... Figure 4 As shown, the specific steps include: S4-1. Construct a personnel-task matrix based on the fire and rescue missions to be performed and the capabilities of the fire and rescue personnel.

[0058] In this embodiment of the invention, the scheduling problem is formalized as a multi-objective optimization problem. First, the fire and rescue tasks to be performed and the capabilities of the fire and rescue personnel are obtained to construct a personnel-task matrix. The personnel-task matrix is ​​then used to determine the correspondence between personnel and tasks for multi-objective optimization.

[0059] S4-2. Define the core objectives of fire and rescue missions; the core objectives include minimizing total completion time, minimizing total personnel risk, maximizing overall mission completion quality, minimizing resource consumption, and maximizing load balancing.

[0060] To perform multi-objective optimization, this embodiment of the invention sets multiple core objectives as optimization targets.

[0061] Objective 1: Minimize total completion time: Find the latest completion time among all tasks and minimize it. Objective 1 drives the scheme to be as compact and parallel as possible.

[0062] Objective 2: Minimize total personnel risk: For each task, multiply its risk level by the number of personnel performing it and sum them up. Objective 2 serves to drive the assignment of high-risk tasks to more experienced and better-protected personnel, or to adjust the execution methods.

[0063] Objective 3: Maximize overall task completion quality: For each task, sum or average the suitability of assigned personnel, then weight and aggregate the results for all tasks. Objective 3 aims to maximize the match between personnel and tasks.

[0064] Objective 4: Minimize resource consumption: Estimate the total cost of equipment wear and tear, material consumption (water, foam), and manpower. Objective 4 aims to conserve firefighting resources.

[0065] Objective 5: Maximize load balancing: Measure the fairness of workload for all firefighters. Objective 5 aims to prevent some personnel from becoming overworked.

[0066] Meanwhile, embodiments of the present invention propose the following constraints as boundary conditions for solving multi-objective optimization problems: Task constraints: Each task must be assigned sufficient personnel, task dependencies must be satisfied, and task time windows must be met.

[0067] Personnel constraints: Each person can only perform one task at a time, personnel skills must meet the task requirements, and personnel working hours cannot exceed the upper limit.

[0068] Resource constraints: Equipment allocation shall not exceed the available quantity, and material consumption shall not exceed the inventory.

[0069] Safety constraints: Dangerous tasks require multiple people to work together, and there are limits on the duration of continuous high-intensity work.

[0070] S4-3. Generate several personnel-task assignment lists as the initial population, and use the non-dominated sorting genetic algorithm to optimize the initial population to obtain the Pareto optimal solution after the non-dominated sorting genetic algorithm converges. This invention employs a non-dominated sorting genetic algorithm for multi-objective optimization, specifically including the following steps: S4-3-1. Establish an objective function for each core objective, calculate the value of each individual in the population in each objective function, and obtain multiple quintuple data as the solution set for each individual in the population; S4-3-2. Perform non-dominated sorting on the solution set, calculate the crowding distance between solution sets, and output the Pareto front individuals; S4-3-3. Use Pareto front individuals for selection, crossover, and mutation to generate a new population; S4-3-4. Add the new population to the non-dominated sorting genetic algorithm and return to the step of calculating the value of each individual in each objective function for each individual in the population until the Pareto front individuals converge.

[0071] Specifically, in this embodiment of the invention, 100-200 initial feasible personnel-task allocation lists are generated randomly or using simple heuristic rules (such as greedy allocation) as scheduling schemes, forming the first-generation population. Next, for each individual in the population (i.e., each scheduling scheme), its value on the five objective functions mentioned above is calculated as a solution set. Then, all solution sets are compared, and those that are better on at least one objective and no worse on all other objectives are identified and ranked in the first layer of the Pareto front. Finally, the crowding distance of the solution sets is calculated, and the solution sets that meet the distance requirement are considered as Pareto front individuals to measure the diversity of the solution sets and avoid the algorithm converging to a point on a local front.

[0072] After obtaining the first generation of Pareto front individuals, this embodiment of the invention uses these individuals for selection, crossover, and mutation to generate a new population. For example, methods such as tournament selection can be used to prioritize the mating of superior individuals; then, simulating biological hybridization, parent individuals are randomly paired, and the allocation of some tasks is exchanged to generate new offspring; finally, the allocation of certain tasks among the offspring individuals is randomly changed with a certain probability to introduce new variations and avoid premature convergence.

[0073] In some embodiments, repair and merging operations between individuals can also be introduced. The repair operation automatically repairs offspring schemes that may violate constraints (such as skill mismatch or dependency conflict) after crossover mutation, making them feasible. The merging operation combines the parent and offspring populations, selecting a new generation based on ranking and crowding, while retaining the historical best solution. Finally, the new population is added to the non-dominated ranking genetic algorithm until the Pareto front improvement stabilizes or the maximum number of iterations is reached, outputting the converged solution set as the Pareto optimal solution.

[0074] S4-4. Transform the Pareto optimal solution into a textual expression, and use it as a scheduling plan for fire and rescue missions, and execute it.

[0075] Step S4-4 is used to decode each "chromosome" in the Pareto solution set into a specific scheduling instruction, including: Personnel allocation table: Which firefighters will perform each task.

[0076] Task sequence diagram (Gantt chart): The start and end times of each task and their sequential relationship.

[0077] Equipment allocation list: Allocation plan for key equipment.

[0078] After being converted into textual expression, the embodiments of the present invention will further classify and label the solution set, as shown below: Option A (Time Priority): Shortest total time, but may have slightly higher risk or load.

[0079] Option B (Safety First): Lowest overall risk, but may take longer.

[0080] Option C (Quality Balanced): Optimal personnel matching and load balancing.

[0081] Option D (Compromise): The objectives are relatively balanced.

[0082] This invention employs a multi-objective optimization algorithm to simultaneously optimize multiple objectives such as time, risk, and quality, generating a Pareto optimal solution set and providing decision-makers with multiple options. Furthermore, this invention incorporates load balancing as one of the optimization objectives, ensuring that the workload of each firefighter is distributed as evenly as possible, thereby improving overall efficiency and safety.

[0083] In some embodiments, the fire situation may change at any time during firefighting operations, potentially causing anomalies in the dispatching plan. In such cases, this embodiment of the invention can promptly handle the anomaly through a rescheduling operation S5, thereby ensuring the smooth execution of the dispatching plan.

[0084] In a preferred embodiment, the rescheduling operation S5 specifically includes the following steps: S5-1. Monitor the execution of the scheduling scheme in real time.

[0085] In this embodiment of the invention, the execution status flow, personnel and equipment status flow, and environmental situation change flow of fire rescue missions can be obtained through personnel terminals, IoT sensors, and other devices for deviation detection.

[0086] S5-2. Perform deviation detection on the scheduling scheme.

[0087] In this embodiment of the invention, key indicators of the scheme are monitored and compared based on the acquired various stream data. For example, key indicators include time deviation (whether the task timed out), resource status deviation (whether there were casualties or equipment overruns), and environmental situation deviation (whether the fire spread exceeded the expected range). Then, based on the task dependency graph, the chain effect of individual deviations is automatically analyzed to determine whether rescheduling is necessary.

[0088] S5-3. Make rescheduling decisions and generate improved scheduling schemes.

[0089] When rescheduling is required, embodiments of the present invention provide two processing methods: local rescheduling and global rescheduling.

[0090] For local rescheduling, embodiments of the present invention use rule-based replacement or fast heuristic algorithms. For example, they can automatically select the most suitable personnel from standby or low-load personnel to replace fatigued or injured personnel; or automatically deploy spare equipment to the scene; and automatically adjust the start time of subsequent non-critical tasks within the allowable dependency range. The local rescheduling scheme can adjust the parameters of fire rescue tasks that are yet to be executed without changing the overall task framework.

[0091] For the global rescheduling scheme, this embodiment of the invention uses the multi-objective optimization algorithm in step S4 to obtain a new scheduling scheme based on the new fire scene, personnel and equipment conditions, and then replaces the original scheme for execution.

[0092] S5-4. Replace the current scheduling scheme with an improved scheduling scheme.

[0093] After generating a new scheduling scheme, this embodiment of the invention uses the new scheme to take over the execution of the original scheme. The new scheduling scheme inherits the completed results of the original scheme, avoiding duplication of work or conflicts. Through the rescheduling step, this embodiment of the invention can adjust the scheduling scheme in real time according to the task execution progress, changes in the fire situation, and emergencies, in order to adapt to changes in the fire situation.

[0094] Below is the execution flow of a specific task breakdown and personnel dispatch plan for a factory dormitory building fire: A fire broke out in a factory dormitory building, with the fire starting on the fourth floor and five people trapped on the fifth floor. The process of task decomposition and personnel scheduling using the method of this invention is as follows: (1) Fire situation analysis: The system obtains fire scene information: Building type: 6-story brick-concrete dormitory building.

[0095] Fire scale: The fourth-floor east-facing dormitory room, with an area of ​​approximately 15 square meters, has a fire intensity of level 4.

[0096] Personnel situation: There are 5 people trapped on the fifth floor.

[0097] Special risks: There is a flour mill 30 meters to the east, posing a risk of dust explosion; the dormitory is equipped with polyurethane insulation material.

[0098] Available resources: 36 people in 6 cars at Chang'an Station, fully equipped.

[0099] (2) Automatic task decomposition: The system automatically identifies tasks based on the fire situation.

[0100] Rule-based recognition: Building type = dormitory building → personnel evacuation task; Fire size = medium fire → internal firefighting and water supply support tasks; There are trapped people → Search and rescue mission; Risk of flour milling → Fireproof isolation task; Polyurethane materials are used for foam fire extinguishing tasks. Case-based recommendation: Three similar cases were found; Common tasks in the case include: interior firefighting, personnel search and rescue, evacuation guidance, water supply guarantee, on-site security, and medical rescue.

[0101] Task list generation: Level 1 task: Fire control, personnel rescue, and on-site support.

[0102] Level 2 task: 1.1 Internal fire suppression (fourth floor); 1.2 Firebreak (flour mill direction); 2.1 Search and rescue of personnel (fifth floor), 2.2 Evacuation guidance (other personnel on the fifth floor), 2.3 Medical rescue (trapped personnel); 3.1 Water supply guarantee, 3.2 On-site security, 3.3 Communication and liaison, 3.4 On-site command.

[0103] (3) Detailed task modeling Detailed modeling is performed for each task.

[0104] Take "internal attack and fire suppression" as an example: Task attributes: Task ID: T01; Mission Name: Fire Extinguishing from the Fourth Floor Interior; Task type: Firefighting; Task Description: Enter the fourth floor through the main entrance staircase and control the fire in the east-facing dormitory room; Mission objective: Extinguish open flames and prevent the fire from spreading.

[0105] Time attribute: Estimated start time: 5 minutes after arrival at the site (after the water supply system is established); Estimated duration: 15 minutes; Deadline: 30 minutes (to prevent the fire from spreading to the fifth floor).

[0106] Resource requirements: Personnel required: 4 people (1 commander + 3 combatants); Skill requirements: Firefighting skills ≥ 80 points, demolition skills ≥ 70 points; Qualification requirements: Intermediate level or above firefighter; Equipment requirements: 4 sets of protective clothing, 4 sets of breathing apparatus, 2 water guns, 1 foam gun, and 1 set of breaching tools.

[0107] Risk attributes: Risk level: High; Main risks: high temperature, dense smoke, toxic polyurethane gases, and flashback; Protection requirements: Protective clothing and breathing apparatus must be worn, and a thermal imaging device must be carried.

[0108] Priority: Urgency level: Level 5; Importance level: Level 5; Overall priority: 25.

[0109] Dependencies: Pre-mission task: T06 Water supply guarantee; Parallel task: T03 Personnel search and rescue; Subsequent task: T02 Fire prevention and isolation.

[0110] (4) Personnel competency assessment Competency assessments were conducted on 36 firefighters (example 3): Firefighter A (Squad Leader): Skills: Firefighting 95 points, Demolition 90 points, Rescue 85 points; Qualifications: Senior firefighter, squad leader; Experience: 8 years, 200 combat engagements; Physical fitness: 90 points; Psychological score: 95 points (strong stress resistance, with command experience); Current status: Good Overall ability: 92 points.

[0111] Firefighter B (combatant): Skills: Firefighting 85 points, Demolition 80 points, Rescue 75 points; Qualification: Intermediate firefighter; Experience: 5 years, 120 combat engagements; Physical fitness: 85 points; Psychology: 80 points; Current status: Good; Overall ability: 81 points.

[0112] Firefighter C (newbie): Skills: Firefighting 70 points, Demolition 65 points, Rescue 60 points; Qualification: Junior Firefighter; Experience: 2 years, 30 combat engagements; Physical fitness: 90 points; Psychology: 70 points; Current status: Good; Overall ability: 71 points.

[0113] Task compatibility calculation (taking the "Internal attack and fire suppression" task as an example): Firefighter A's suitability: Fit score = 0.97; Firefighter B's fit is 0.82; Firefighter C's fit is 0.65.

[0114] (5) Scheduling optimization Multi-objective optimization using the NSGA-II algorithm: Optimization goal: Objective 1: Minimize the total completion time; Objective 2: Minimize personnel risk; Objective 3: Maximize the quality of task completion.

[0115] Constraints: Allocate sufficient personnel to each task; Each person can only perform one task at a time; Personnel skills meet task requirements; The quantity of equipment meets the demand.

[0116] Algorithm parameters: Population size: 100; Number of iterations: 200 generations; Crossover probability: 0.9; Mutation probability: 0.1.

[0117] Optimization results: Generate 3 Pareto optimal solutions: Option A (Time Priority): Total completion time: 25 minutes; Total risk value: 180; Average fit: 0.85; Features: High degree of task parallelism and compact personnel allocation.

[0118] Option B (Safety First): Total completion time: 32 minutes; Total risk value: 120; Average fit: 0.88; Features: Dangerous tasks are assigned to experienced personnel, and buffer zones are provided between tasks.

[0119] Option C (Quality First): Total completion time: 28 minutes; Total risk value: 150; Average fit: 0.92; Features: Highest personnel-task match.

[0120] The commander selects option C (quality priority), with the specific allocation as follows: T01 Internal Attack Fire Extinguishing: Personnel: Firefighter A (Squad Leader), Firefighter B, Firefighter D, Firefighter E; Equipment: 4 sets of protective clothing, 4 sets of breathing apparatus, 2 water guns, 1 foam gun, 1 set of demolition tools; Start time: 12:20 (5 minutes after arrival at the scene); Estimated completion time: 12:35.

[0121] T03 Personnel Search and Rescue: Personnel: Firefighter F (Squad Leader), Firefighter G, Firefighter H; Equipment: 3 sets of protective clothing, 3 sets of breathing apparatus, rescue ropes, stretcher; Start time: 12:20 (in parallel with the internal attack and fire suppression); Estimated completion time: 12:35.

[0122] T04 Evacuation Guidance: Personnel: Firefighter I, Firefighter J; Equipment: Walkie-talkie, flashlight; Start time: 12:20; Expected completion time: 12:30.

[0123] T06 Water Supply Guarantee: Personnel: Firefighter K (driver), Firefighter L, Firefighter M; Equipment: Vehicle No. 1, Vehicle No. 2, water hoses; Start time: 12:15 (earliest start time); Expected outcome: Continuous water supply.

[0124] T07 On-site security: Personnel: Firefighter N, Firefighter O; Equipment: Warning tape, walkie-talkie; Start time: 12:15; Expected outcome: Continued vigilance.

[0125] T02 Fireproof isolation: Personnel: Firefighter P, Firefighter Q, Firefighter R; Equipment: Water gun, water curtain generator; Start time: 12:25 (after initial control of the fire through internal attack); Estimated completion time: 12:40.

[0126] The remaining personnel serve as reserves or perform other auxiliary tasks.

[0127] (6) Dynamic adjustment At 12:22, the system detected an anomaly: Abnormal situation: Mission T01 (internal attack and fire suppression) is progressing slowly. Polyurethane material has been found to be burning, and it is necessary to switch to foam fire suppression. Firefighter B reported that his fatigue level had risen to 40% (due to high-intensity work). System response: The system automatically suggests switching to type B foam and adjusting the mixing ratio to 6%. Firefighter B is experiencing high fatigue; it is recommended that they be rotated out after 15 minutes. Designate firefighter S as the replacement and prepare in advance; At 12:30, task T04 (evacuation guidance) was completed ahead of schedule, and firefighters I and J were free.

[0128] System response: Firefighters I and J have been detected as available. The system automatically recommends assigning it to task T02 (fireproof isolation) and starting the task ahead of time. The commander confirmed that mission T02 would start earlier than scheduled at 12:30. At 12:35, missions T01 (internal attack and firefighting) and T03 (personnel search and rescue) were completed.

[0129] System response: Update task status; Assess firefighter fatigue levels; firefighters A, B, and F are at high fatigue levels and are scheduled for short rest. Other personnel moved on to the final stages of the work.

[0130] This embodiment achieves the following objectives: Through systematic task decomposition, nine main tasks were identified, forming a complete task list to avoid omissions; through quantitative personnel capability assessment and task suitability calculation, precise matching of personnel and tasks was achieved; through multi-objective optimization algorithms, three Pareto optimal solutions were generated for the commander to choose from; through dynamic monitoring and adjustment, timely responses were made to changes in the fire scene and personnel status, maintaining the effectiveness of the dispatch plan; the entire rescue process was orderly and efficient, completing the main tasks within 25 minutes and successfully rescuing all trapped personnel.

[0131] Figure 6 This is a schematic diagram of the electronic device proposed in the second embodiment of the present invention. In this embodiment, the memory stores program instructions for implementing the intelligent decomposition and scheduling method for fire and rescue tasks in any of the above embodiments. The processor executes the program instructions stored in the memory to perform intelligent decomposition and scheduling of fire and rescue tasks. The processor can also be called a CPU (Central Processing Unit). The processor may be an integrated circuit chip with signal processing capabilities. The processor can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0132] The methods described in the first embodiment of the present invention are applicable to the embodiments of the present electronic device. The specific functions implemented by the embodiments of the present electronic device are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above methods.

[0133] Figure 7This is a schematic diagram of the structure of a computer-readable storage medium according to the third embodiment of the present invention. The computer-readable storage medium of the fourth embodiment of the present invention stores program instructions capable of implementing the above-described intelligent decomposition and scheduling method for fire and rescue tasks. These program instructions can be stored in the storage medium in the form of a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of various embodiments of the present invention. The aforementioned computer-readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets.

[0134] The methods described in the first embodiment of the present invention are applicable to the computer-readable storage medium embodiment. The specific functions implemented by the computer-readable storage medium embodiment are the same as those in the above method embodiment, and the beneficial effects achieved are also the same as those achieved by the above method.

[0135] This embodiment also provides a computer program product. When the computer program product is run on a computer, it causes the computer to perform the above-mentioned related steps to realize the intelligent decomposition and scheduling method for fire rescue tasks provided in the above embodiment.

[0136] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the embodiments of the present invention are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0137] Those skilled in the art will understand that modules in the device of the embodiments of the present invention can be adaptively modified and placed in one or more devices different from those embodiments. Modules, units, or components in the embodiments of the present invention can be combined into a single module, unit, or component, and further, they can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the corresponding claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the corresponding claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0138] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0139] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0140] Furthermore, the various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to mutually. In particular, for embodiments such as apparatus and devices, since they are basically similar to the method embodiments, the relevant parts can be referred to the description of the method embodiments. The apparatus, devices, and other embodiments described above are merely illustrative, and the modules, units, etc., described as separate components may or may not be physically separate, that is, they may be located in one place or distributed in multiple places, such as nodes in a system network. Specifically, some or all of the modules and units can be selected according to actual needs to achieve the purpose of the above-described embodiment solutions. Those skilled in the art can understand and implement this without creative effort.

[0141] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0142] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0143] Furthermore, the terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying relative importance, or implicitly specifying the number of technical features indicated in this embodiment. Therefore, features defined with terms such as "first" and "second" in the embodiments of this invention can explicitly or implicitly indicate that the embodiment includes at least one of those features. In the description of this invention, the word "multiple" means at least two or more, such as two, three, four, etc., unless otherwise explicitly specified in the embodiments.

[0144] In embodiments of the present invention, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of the present invention may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0145] Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention. Other embodiments of the present invention will readily conceive of by considering the specification and practicing the invention. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

Claims

1. A fire rescue task intelligent decomposition and scheduling method, characterized in that, Includes the following steps: Conduct fire situation analysis and obtain the analysis results of the fire situation; Based on the analysis of the fire situation, several fire rescue tasks that need to be carried out were determined; Detailed modeling is performed for each fire and rescue mission that needs to be carried out; The dispatching scheme for fire and rescue missions is generated through multi-objective optimization, and the fire and rescue missions are executed according to the generated dispatching scheme.

2. The intelligent decomposition and scheduling method for fire rescue tasks according to claim 1, characterized in that, The fire situation analysis specifically includes the following steps: Obtain multi-dimensional fire scene information; Feature extraction is performed on the multi-dimensional fire scene information to obtain building features, fire features, personnel features, risk features, environmental features, and resource features of the fire scene situation. These features are then output as the analysis results.

3. The intelligent fire rescue task decomposition and scheduling method according to claim 1, characterized in that, Based on the analysis of the fire situation, multiple fire rescue tasks that need to be carried out are determined, specifically through the following steps: Establish a task library, which includes multiple fire and rescue tasks; Feature keywords were extracted from the analysis results of the fire situation, resulting in multiple feature keywords; The rule engine is invoked to identify rules, and multiple fire and rescue tasks that match the feature keywords are determined from the task library as target fire and rescue tasks; Based on the target fire and rescue mission, a similar case search is performed in historical fire and rescue cases to determine the target fire and rescue case; Based on the fire rescue tasks involved in the target fire rescue case, the identified target fire rescue tasks are optimized and adjusted, and the adjustment results serve as multiple fire rescue tasks that need to be executed.

4. The intelligent decomposition and scheduling method for fire and rescue missions according to claim 3, characterized in that, The process of searching for similar cases in historical fire and rescue cases based on the target fire and rescue mission specifically includes the following steps: A historical fire and rescue case dataset is established; the historical fire and rescue case dataset contains multiple historical fire and rescue cases, and each historical fire and rescue case corresponds to multiple fire and rescue tasks. The identified target fire and rescue missions are matched with the corresponding fire and rescue missions for each historical fire and rescue case in the dataset. Historical fire and rescue cases in which the target fire and rescue mission appears more frequently than a preset frequency threshold are used as target fire and rescue cases.

5. The intelligent decomposition and scheduling method for fire and rescue missions according to claim 1, characterized in that, The detailed modeling of each fire and rescue task to be performed includes the following steps: For each fire and rescue mission to be performed, time attribute modeling, spatial attribute modeling, resource requirement modeling, and priority modeling are performed. The time attribute modeling includes the start time, duration, and end time of the fire and rescue mission; the spatial attribute modeling includes the spatial orientation of the fire and rescue mission; the resource requirement modeling includes the personnel requirements, equipment requirements, and material requirements of the fire and rescue mission; and the priority modeling includes the priority of the fire and rescue mission. Determine the dependencies between each fire and rescue mission that needs to be performed and other fire and rescue missions that need to be performed.

6. The intelligent decomposition and scheduling method for fire and rescue missions according to claim 1, characterized in that, Before the step of generating a dispatch plan for fire and rescue missions through multi-objective optimization, a step of quantitatively assessing personnel is also included, specifically including the following steps: Input fire and rescue personnel data; the fire and rescue personnel data includes static personnel data and dynamic personnel data; Based on the static and dynamic personnel data, an individual ability assessment is conducted on each firefighter in terms of skills, qualifications, experience, physical fitness, and psychological dimensions to obtain an ability vector for each firefighter. The comprehensive capability score of each firefighter is calculated based on capability vectors.

7. The intelligent decomposition and scheduling method for fire and rescue missions according to claim 1, characterized in that, The method of generating a dispatching scheme for fire and rescue missions through multi-objective optimization specifically includes the following steps: Construct a personnel-task matrix based on the required fire and rescue missions and the capabilities of fire and rescue personnel; Define the core objectives of fire and rescue missions; these core objectives include minimizing total completion time, minimizing total personnel risk, maximizing overall mission completion quality, minimizing resource consumption, and maximizing load balancing. Several personnel-task assignment lists are generated as the initial population. The initial population is optimized using a non-dominated sorting genetic algorithm to obtain the Pareto optimal solution after the non-dominated sorting genetic algorithm has converged. The Pareto optimal solution is translated into a textual expression and used as a scheduling plan for fire and rescue missions.

8. The intelligent decomposition and scheduling method for fire and rescue missions according to claim 7, characterized in that, The optimization of the initial population using a non-dominated sorting genetic algorithm specifically includes the following steps: For each core objective, an objective function is established, and the value of each individual in the population is calculated in each objective function. Multiple quintuples of data are obtained as the solution set for each individual in the population. The solution set is sorted non-dominated, and the crowding distance between solution sets is calculated. The Pareto front individuals are then output. New populations are generated by selecting, crossovering, and mutating individuals using Pareto frontier individuals. The new population is added to the non-dominated sorting genetic algorithm, and the process of calculating the value of each individual in each objective function is returned until the Pareto front individuals converge.

9. An electronic device, characterized in that, Including the processor and memory; The memory is used to store programs; The processor executes the program to implement a method for intelligent decomposition and scheduling of fire rescue tasks as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program, which is executed by a processor to implement a method for intelligent decomposition and scheduling of fire and rescue tasks as described in any one of claims 1-8.

Images