Intelligent fire scene fire rescue system and control method

Abstract

According to the intelligent fire scene fire rescue system and the control method, state data and temperature change information of firemen are collected, and the gradient analysis reverse tracking technology is used for positioning fire source distribution; fire spreading prediction is performed based on the fire source distribution data, an evacuation path scheme from danger to a safe area is constructed, and a safe operation range is formulated; performing task splitting on the rescue target to generate a fragmented task set, and performing dynamic recombination based on the firefighter state to generate a task allocation scheme; establishing a rescuer and rescued person two-way state confirmation channel, performing rescue effect evaluation and failure risk analysis, and optimizing task combination; carrying out monitoring and abnormal mode recognition on the rescue process, and carrying out safety evaluation in combination with an evacuation path scheme; and according to a safety state monitoring result, a rescue target is adjusted, risk conversion is carried out to generate controllable risk parameters, a rescue strategy is formulated, and intelligent safety rescue of ensuring exit first and then maximizing the rescue effect is realized.

Description

Technical Field

[0001] The present invention relates to the field of intelligent firefighting and rescue technology, and in particular to an intelligent fire scene firefighting and rescue system and a control method. Background Art

[0002] With the acceleration of urbanization and the increasing complexity of building structures, fire accidents are characterized by rapid spread, difficulty in rescue, and heavy casualties, placing higher demands on the intelligence level and emergency response capabilities of firefighting and rescue. Traditional firefighting and rescue relies primarily on experience and manual decision-making. In complex fire environments, incomplete information, and time pressures, these factors often lead to delayed decision-making, improper resource allocation, and low rescue efficiency.

[0003] Existing firefighting and rescue systems suffer from numerous technical limitations: They lack the ability to accurately identify and dynamically track fire sources, resulting in blind rescue operations and an inability to formulate targeted rescue strategies. Rescue task allocation often relies on static plans or simple divisions of labor, lacking intelligent dynamic adjustment mechanisms based on personnel status and task complexity. Safety assessment and risk control methods are limited, lacking real-time monitoring of the rescue process and anomaly warning capabilities. Rescue decisions often rely on the commander's personal experience, lacking scientific decision-making support based on data analysis and intelligent algorithms. These technical bottlenecks severely restrict the effectiveness of firefighting and rescue in complex locations such as high-rise buildings, underground spaces, and chemical plants. There is an urgent need to develop a next-generation intelligent fire scene firefighting and rescue system with intelligent perception, autonomous decision-making, and dynamic optimization capabilities. Summary of the Invention

[0004] The present invention provides an intelligent fire scene firefighting and rescue system and control method, which aims to realize intelligent rescue decision-making and precise rescue operation in complex fire scene environment, integrate core technologies such as intelligent fire source identification, safe path planning, dynamic task allocation, two-way status confirmation, real-time abnormal warning, and risk adaptive control, and carry out intelligent management and control of the entire firefighting and rescue process, realize precise positioning of fire source, autonomous allocation of rescue tasks, dynamic assessment of safety risks, and real-time optimization of rescue strategies, and build an intelligent fire scene firefighting and rescue system with environmental perception, intelligent decision-making, adaptive adjustment, and collaborative operation capabilities.

[0005] The first aspect of the present invention provides an intelligent fire scene fire rescue control method, comprising the following steps:

[0006] Collect firefighter location information and vital sign data to generate firefighter status data, obtain temperature change information around the firefighter, perform gradient analysis on the temperature change information, and reversely track the fire source location to generate fire source distribution data;

[0007] Performing fire spread prediction based on the fire source distribution data to generate a dangerous area distribution, identifying the boundary area of ​​the dangerous area distribution to generate a relatively safe area, constructing an evacuation path plan from the dangerous area distribution to the relatively safe area, and formulating a rescue action boundary based on the evacuation path plan to generate a safe operation range;

[0008] Obtaining rescue target information, breaking down the rescue target information into tasks to generate a fragmented rescue task set, and dynamically reorganizing the fragmented rescue task set based on the firefighter status data to generate a personalized task allocation plan;

[0009] performing a rescue operation within the safe operating range according to the personalized task allocation plan to generate a rescue execution record, establishing a two-way status confirmation channel between the rescuer and the rescued based on the rescue execution record, and obtaining two-way confirmation data through the two-way status confirmation channel;

[0010] Performing an effectiveness analysis of the rescue operation based on the two-way confirmation data to obtain rescue effect evaluation data, performing a failure risk analysis on the rescue effect evaluation data to identify potential failure factors, and adjusting the fragmented rescue task set according to the potential failure factors to generate an optimized task combination;

[0011] Monitoring the optimized task combination to obtain rescue process data, performing abnormal pattern recognition on the rescue process data to generate abnormal warning signals, and performing safety assessment based on the evacuation path plan and the abnormal warning signals to generate safety status monitoring results;

[0012] According to the safety status monitoring results, the current rescue target is dynamically adjusted to generate a redefined rescue standard, the redefined rescue standard is converted into a risk dimension to generate a controllable risk parameter, and a rescue strategy is formulated based on the controllable risk parameter to generate a final control instruction to complete the intelligent fire scene fire rescue control.

[0013] A second aspect of the present invention provides an intelligent fire scene firefighting and rescue system, comprising:

[0014] A data acquisition module is used to collect firefighter location information and vital sign data to generate firefighter status data, obtain temperature change information around the firefighter, perform gradient analysis on the temperature change information, and reversely track the fire source location to generate fire source distribution data;

[0015] a path planning module, configured to predict the spread of fire based on the fire source distribution data to generate a dangerous area distribution, identify the boundary areas of the dangerous area distribution to generate relatively safe areas, construct an evacuation path plan from the dangerous area distribution to the relatively safe area, and formulate a rescue action boundary based on the evacuation path plan to generate a safe operation range;

[0016] A task assignment module is used to obtain rescue target information, decompose the rescue target information into tasks to generate a fragmented rescue task set, and dynamically reorganize the fragmented rescue task set based on the firefighter status data to generate a personalized task assignment plan;

[0017] a rescue execution module, configured to execute a rescue operation within the safe operation range according to the personalized task allocation plan, generate a rescue execution record, establish a two-way status confirmation channel between the rescuer and the rescued based on the rescue execution record, and obtain two-way confirmation data through the two-way status confirmation channel;

[0018] an effect evaluation module, configured to perform an effectiveness analysis of the rescue operation based on the bidirectional confirmation data to obtain rescue effect evaluation data, perform a failure risk analysis on the rescue effect evaluation data to identify potential failure factors, and adjust the fragmented rescue task set according to the potential failure factors to generate an optimized task combination;

[0019] a safety monitoring module, configured to monitor the optimized task combination to obtain rescue process data, perform abnormal pattern recognition on the rescue process data to generate abnormal warning signals, and perform safety assessment based on the evacuation path plan and the abnormal warning signals to generate safety status monitoring results;

[0020] The strategy control module is used to dynamically adjust the current rescue target according to the safety status monitoring results to generate a redefined rescue standard, convert the risk dimension of the redefined rescue standard to generate a controllable risk parameter, formulate a rescue strategy based on the controllable risk parameter to generate a final control instruction, and complete the intelligent fire scene fire rescue control.

[0021] The beneficial effects of the present invention are reflected in the following points: First, through the reverse tracking of fire source positioning technology through temperature gradient analysis, a fundamental transformation from "blind search" to "precise positioning" is achieved. Combined with the real-time monitoring of the multi-dimensional status of firefighters, it breaks through the key technical bottlenecks of unknown fire source location and insufficient understanding of personnel status in traditional rescue operations, significantly improving the pertinence and scientific nature of rescue operations, and laying a solid foundation for the formulation of precise rescue strategies. Secondly, an innovative mechanism for dynamic allocation of fragmented tasks and two-way status confirmation is established, achieving a major breakthrough from "extensive human wave tactics" to "refined collaborative operations". Through the intelligent matching of tasks and personnel capabilities and real-time two-way feedback of the rescue process, it fundamentally solves the core problems of unreasonable task allocation and opaque execution status in traditional rescue operations, effectively improving rescue efficiency and success rate. Finally, a safety assurance system based on abnormal warning and risk adaptive control was constructed, realizing a rescue safety mode in which "active safety protection" replaced "passive experience reliance". Through a closed-loop control mechanism of real-time monitoring, dynamic warning, and intelligent adjustment, the technical difficulties of single safety assurance means and insufficient risk control capabilities in traditional rescue were fundamentally solved, ensuring the maximization of rescue effects under the premise of "rescuer safety first", and forming an intelligent firefighting and rescue technology system with autonomous decision-making and adaptive adjustment capabilities.

[0022] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings herein illustrate specific examples of the technical solutions described in the present invention, and together with the specific implementation methods constitute a part of the specification, and are used to explain the technical solutions, principles and effects of the present invention.

[0024] Unless otherwise specified or defined, the same reference numerals in different drawings represent the same or similar technical features, and the same or similar technical features may also be represented by different reference numerals.

[0025] Figure 1 It is a flow chart of an intelligent fire scene fire rescue control method of the present invention.

[0026] Figure 2 It is a structural block diagram of an intelligent fire scene firefighting and rescue system of the present invention. DETAILED DESCRIPTION

[0027] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0028] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0029] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0030] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0031] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0032] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0033] The technical solutions of the embodiments of this application are introduced below.

[0034] like Figure 1As shown, an embodiment of the present invention provides an intelligent fire scene fire rescue control method, including the following steps S110 to S170:

[0035] Step S110 , collecting firefighter location information and vital sign data to generate firefighter status data, obtaining temperature change information around the firefighter, performing gradient analysis on the temperature change information, and reversely tracing the fire source location to generate fire source distribution data.

[0036] Specifically, firefighter location information and vital sign data are collected to generate firefighter status data. This information is collected using Beidou satellite positioning and inertial navigation unit fusion positioning technology, providing meter-level positioning accuracy in outdoor environments. UWB ultra-wideband indoor positioning enables precise positioning inside buildings. The positioning device continuously updates the firefighter's three-dimensional coordinate position, movement velocity vector, and heading angle, ensuring data synchronization through a unified time base. Vital sign data collection relies on a physiological monitoring sensor array integrated into the protective suit. Heart rate monitoring uses a photoplethysmography sensor, body temperature monitoring is achieved through the collaboration of a core temperature sensor and a skin temperature sensor, blood oxygen saturation is monitored using dual-wavelength pulse oximetry technology, respiratory rate is measured by chest impedance change detection, and motion status is detected using a combination of a three-axis accelerometer and gyroscope. Data fusion processing utilizes a multi-source fusion algorithm for spatiotemporal alignment, and a Kalman filter algorithm is used to smooth physiological data fluctuations to calculate the firefighter's fatigue index, stress level, and health status rating. For example, during a fire rescue operation at a high-rise office building, when firefighter Zhang entered the smoke-filled 12th floor, monitoring data showed his heart rate rapidly increased from 78 beats per minute (BPM) to 142 BPM, his core body temperature rose from 36.6°C to 38.1°C, and his blood oxygen saturation dropped from 98% to 91%. The data fusion algorithm calculated that his fatigue index reached a high level. Through multi-dimensional data collection and intelligent fusion analysis, firefighter status data is generated.

[0037] Obtaining temperature information around firefighters. This temperature information collection is based on a dual monitoring architecture combining a distributed sensor network and mobile thermal imaging equipment. The distributed temperature sensor network utilizes industrial-grade digital temperature sensors deployed in a grid-like layout at key locations within the building, including stairwells, main evacuation routes, and equipment rooms, forming a comprehensive temperature monitoring network. Mobile temperature collection is achieved through portable infrared thermal imaging devices carried by firefighters. These devices are mounted on the side of their helmets or on their chest protectors, capturing real-time two-dimensional temperature distribution images within their field of view. Thermal imaging data is transmitted in real time via a wireless link to data processing equipment in the on-site command vehicle. The received temperature data undergoes comprehensive preprocessing, including key steps such as timestamp synchronization and correction, GPS coordinate unification, and data integrity verification. Data standardization converts temperature data in various formats from different sensors into a unified format. For example, at the fire scene of a large shopping mall, a fixed sensor network provided real-time temperature data from key locations on each floor. Simultaneously, thermal imaging equipment carried by five firefighters collected a large amount of temperature image information from different angles. After processing, a temperature distribution dataset covering the entire mall was constructed. Complete multi-link processing and quality control work and obtain temperature change information.

[0038] In some embodiments, the performing of gradient analysis on the temperature change information and reverse tracing of the fire source location to generate fire source distribution data includes: performing multi-point temperature gradient analysis on the temperature change information to obtain a gradient vector field; constructing a temperature change trend graph based on the gradient vector field; performing reverse path tracing using the temperature change trend graph to generate a candidate fire source location; and generating fire source distribution data based on the candidate fire source location.

[0039] First, a multi-point temperature gradient analysis is performed on the temperature change information to obtain the gradient vector field. The temperature gradient analysis uses the numerical differentiation method to determine the rate of change of the temperature field in all directions by calculating the temperature difference and the corresponding spatial distance between adjacent measurement points in space. In a two-dimensional plane, the temperature partial derivatives in the x- and y-directions are calculated to form a plane gradient vector; in three-dimensional space, the temperature gradient in the z-direction is further calculated to construct a complete three-dimensional gradient vector field. First, a multi-point temperature gradient analysis is performed on the temperature change information to obtain the gradient vector field. The temperature gradient analysis uses the numerical differentiation method to determine the rate of change of the temperature field in all directions by calculating the temperature difference and the corresponding spatial distance between adjacent measurement points in space. The mathematical expression of the temperature gradient vector is: Gradient strength calculation formula: Where T(x, y, z) represents the temperature value at the spatial position (x, y, z). represent the partial derivatives of temperature in the x, y, and z directions, respectively. represents the intensity of the temperature gradient. In a two-dimensional plane, partial temperature derivatives in the x and y directions are calculated to form a plane gradient vector. In three-dimensional space, the temperature gradient in the z direction is further calculated to construct a complete three-dimensional gradient vector field. Numerical calculations employ a central difference scheme to improve accuracy. Data quality issues are addressed during the construction of the gradient vector field, including identifying and removing anomalous measurements and handling missing data due to sensor failure. Spatial interpolation algorithms are used to fill in areas with missing data, and low-pass filtering is used to smooth the gradient field. Finally, a spatially gridded gradient data structure is established, storing the magnitude and direction of the gradient vector for each grid node. For example, in a chemical plant fire incident, gradient analysis identified a significant high-temperature gradient center in the southeast corner of the reaction workshop. The temperature gradient vectors in this area exhibited a typical radial distribution pattern. Through numerical calculations and data processing, a gradient vector field is established.

[0040] Next, a temperature trend map is constructed based on the gradient vector field. A visualization method combining isotherm plotting technology and temperature distribution cloud maps is used to convert discrete temperature measurement data and gradient information into a continuous spatial distribution image. Isotherms are generated using a contour tracing algorithm, setting reasonable temperature intervals based on the temperature range to generate a complete family of isotherms from ambient temperature to the high-temperature area of ​​the fire scene. The temperature distribution cloud map uses color mapping technology to map temperature values ​​into a visually friendly color distribution, typically using a gradient from blue to red. Gradient vector information is integrated into the trend map, and arrows are used to indicate the direction and intensity of temperature changes. The arrow length is proportional to the gradient intensity. A time series temperature trend map is constructed to illustrate the spatiotemporal evolution of the temperature field. For example, during a fire rescue operation in an underground parking garage, the temperature trend map showed that the fire originated from a parking space in Area B, with high-temperature isotherms gradually spreading outward in an elliptical pattern, along the parking garage's ventilation ducts and driveway layout. The temperature trend map is constructed using visualization technology and data fusion methods.

[0041] Then, reverse path tracking is performed using the temperature trend graph to generate candidate fire source locations. By analyzing the temperature trend graph, areas with dense high-temperature isotherms are identified as tracking starting points. From these starting points, numerical path integration is performed in the opposite direction of the gradient vector, tracing the reverse path of the temperature rise and finding areas where multiple paths converge as potential fire source locations. The differential equation for reverse path tracking is: Path integral equation: Where x(t) represents the path position at time t, x0 is the coordinate of the starting point, and the negative sign indicates movement in the opposite direction of the gradient. The integration process begins at x0 and tracks the path toward the fire source. Path tracking utilizes the fourth-order Runge-Kutta numerical integration method. The algorithm employs a multi-start tracking strategy, simultaneously initiating reverse tracking from multiple high-temperature areas identified in the trend graph. Various termination conditions are set during the tracking process, including when the gradient intensity drops below a preset threshold or when the tracking distance exceeds a reasonable range. Path aggregation analysis utilizes a density clustering algorithm to identify and analyze the spatial convergence patterns of multiple tracking paths. The credibility of candidate fire source locations is determined based on the density and concentration of these paths. The algorithm also considers the local characteristics of the gradient field to comprehensively evaluate and rank candidate locations. For example, in a high-rise residential building fire, 15 reverse tracking paths were initiated from multiple high-temperature areas identified in the trend graph on the 12th floor. Eleven of these paths clearly converged to the kitchen area of ​​Room 1202, three to the electrical distribution box in the hallway, and one to the stairwell. Through numerical calculations and cluster analysis, the candidate fire source locations were determined.

[0042] Finally, fire source distribution data is generated based on the candidate fire source locations. Based on the candidate fire source locations and their credibility assessment results, a probability distribution modeling approach is used to quantify the candidate locations. A probability weighting model for the candidate locations is established using the path convergence density, number of converged paths, and comprehensive evaluation ranking results. Probability distribution modeling expands the discrete candidate locations into a continuous spatial probability field. Using spatial interpolation and probability diffusion techniques, a probability gradient distribution is constructed around the candidate locations. A Bayesian fusion approach is used to integrate the probability contributions of multiple candidate locations to generate a unified fire source probability distribution map. Fire source distribution data is stored in a gridded format, with each grid cell recording the probability and confidence level of the fire source. For example, in a high-rise residential building fire case, the kitchen area of ​​Room 1202 was assigned the highest fire source probability due to the convergence of 11 paths. The distribution box area in the corridor received a medium probability due to the convergence of three paths. The stairwell received a lower probability due to the convergence of only one path. Fire source distribution data is generated based on the credibility of the candidate locations and probability modeling.

[0043] Step S120: Based on the fire source distribution data, a fire spread prediction is performed to generate a dangerous area distribution, the boundary area of ​​the dangerous area distribution is identified to generate a relatively safe area, an evacuation path plan is constructed from the dangerous area distribution to the relatively safe area, and the rescue action boundary is formulated according to the evacuation path plan to generate a safe operation range.

[0044] Specifically, fire spread prediction is performed based on fire source distribution data to generate a distribution of hazardous areas. Fire spread prediction employs a prediction method based on physical combustion models and numerical simulation. Fire source distribution data is used as initial conditions, and the spatiotemporal prediction of fire development is performed in combination with building structural information, combustible material distribution, and environmental conditions. The combustion model considers the three primary modes of flame propagation: heat conduction, convection, and radiation, describing the spatiotemporal evolution of the temperature, velocity, and concentration fields via a system of partial differential equations. Numerical simulation employs the finite element method to solve the combustion equations, with the meshing adaptively adjusted based on the building's geometry. The prediction process considers the combustion characteristics of building materials, the impact of ventilation conditions on fire spread speed, and the effectiveness of fire extinguishing measures such as fire sprinklers. Prediction results are presented as temperature distribution, smoke concentration distribution, and flame front position. The prediction area is divided into different hazard levels by setting hazard thresholds. For example, in a fire prediction for an office building, based on the fire source distribution data for the 15th-floor conference room, the prediction model showed that the fire would spread rapidly along the open office area. The flame front was expected to reach the east side of the floor within 15 minutes, and the high-temperature area would cover two-thirds of the entire floor within 30 minutes. Through physical modeling and numerical simulation calculations, the distribution of dangerous areas was generated.

[0045] Identify the boundaries of the hazardous area distribution and generate relatively safe areas. Using contour tracing technology, the outer boundaries of the hazardous area are determined by setting safety thresholds. The threshold selection takes into account personnel safety standards and rescue operation requirements. Relatively safe areas are generated based on a buffer zone analysis of the hazardous area boundary. A safety buffer distance is set outside the hazardous area, calculated based on the fire spread rate and personnel movement speed. The safety zone assessment considers the spatial distance from the hazard source, ventilation conditions, structural stability, fire protection coverage, and accessibility of evacuation routes. The assessment algorithm calculates a comprehensive safety index for each spatial location, prioritizing areas with multiple evacuation exits, strong structures, and good ventilation as relatively safe areas. For example, in a shopping mall fire scenario, the hazardous area distribution indicated that the clothing and electrical appliance areas on the east side of the first floor were high-risk areas. The boundary identification algorithm extracted the irregular boundary lines of the hazardous area and identified the atrium area on the west side of the first floor, the north side of the second floor dining area, and part of the underground parking lot as relatively safe areas. Based on boundary identification and safety assessment analysis, relatively safe areas are generated.

[0046] In some embodiments, constructing an evacuation path plan from the dangerous area distribution to the relatively safe area includes: performing boundary identification on the dangerous area distribution to obtain dangerous boundary coordinates; determining the shortest evacuation distance based on the dangerous boundary coordinates and the relatively safe area; designing multiple alternative evacuation paths according to the shortest evacuation distance; and performing safety assessment on the multiple alternative evacuation paths to generate an evacuation path plan.

[0047] Boundary identification is performed on hazardous area distribution to obtain hazardous boundary coordinates. Boundary extraction utilizes contour tracing technology and a contour detection algorithm. Area boundaries are determined by setting a hazard threshold. This algorithm can handle complex, irregular boundary shapes and multiple, isolated hazardous areas. The coordinate extraction process discretizes the boundary line into a series of key control points, each of which records precise 2D or 3D spatial coordinate information. The coordinate system uses the unified internal coordinate system of the building to ensure compatibility with other spatial data. The boundary coordinate data structure contains attribute information such as the boundary point sequence, boundary segment direction, boundary type, and hazard level. The algorithm also performs boundary smoothing to eliminate jagged edges caused by data noise. For example, in a chemical plant fire, the hazardous area boundary identification algorithm extracted the complex polygonal boundary of the reaction workshop, including several key boundary control points. The boundary coordinates were accurate to the centimeter level, forming a complete hazardous boundary contour description. After boundary detection and coordinate extraction, the hazardous boundary coordinate data was obtained.

[0048] The shortest evacuation distance is determined based on the coordinates of the danger boundary and the relatively safe zone. A topological network model of the building is established, with spatial units such as corridors, rooms, and stairwells as network nodes, and connections such as doors, passages, and stairways as network edges. Each edge is assigned weights such as length, travel time, and safety factor. Distance calculation uses a multi-source shortest path algorithm, using the coordinates of the danger boundary as the starting point set and the relatively safe zone as the target point set. The algorithm then finds the shortest path from all starting points to the target point. This algorithm considers actual internal building traffic conditions, including constraints such as passage width, stairway capacity, and door opening status. The calculation results generate a distance field distribution map, showing the evacuation distance and optimal direction from each location within the danger zone to the nearest safe zone. Distance data is stored in a matrix format, recording the shortest distance, path length, and estimated travel time between boundary points and safe zones. For example, in a shopping mall fire, the shortest evacuation distance from a critical control point on the east side of the danger boundary on the second floor to the safe zone in the west atrium on the first floor ranged from 65 to 95 meters, with an average evacuation distance of 78 meters and an estimated travel time of 4 to 6 minutes. Determine the distribution of the shortest evacuation distance through network modeling and path calculation.

[0049] Multiple alternative evacuation routes are designed based on the shortest evacuation distance. First, multiple locally optimal path corridors are identified in the distance field, representing different evacuation directions and path options. Path generation uses the K shortest path algorithm and path diversity optimization technology to maximize the spatial separation between paths while ensuring reasonable path lengths. The design process considers path load balancing and allocates paths based on expected passenger flow and channel capacity to avoid all personnel concentrating on a single path. The algorithm also considers the fault tolerance of the path to ensure that other alternative paths are still available when a main path is blocked. Each designed path contains detailed information such as the path node sequence, segment distance, cumulative length, estimated travel time, and recommended passenger flow capacity. The path is represented using a directed path graph that clearly identifies the evacuation direction and key decision points. For example, in an office building fire scenario, based on a minimum evacuation distance analysis, three primary alternative evacuation routes were designed from the eighth-floor danger zone: the east fire staircase (52 meters in total length), the west evacuation staircase (48 meters in total length), and the central staircase (65 meters in total length). These routes were spatially separated, effectively dispersing the flow of people. Multiple alternative evacuation routes were designed based on the principles of distance optimization and diversity.

[0050] A safety assessment of multiple alternative evacuation routes is conducted to generate an evacuation route plan. Evaluation metrics include key dimensions such as route safety, traffic efficiency, structural reliability, environmental adaptability, and emergency availability. The route safety assessment analyzes the fire risk level, smoke diffusion impact, structural stability, and firefighting facility coverage of the routed areas. The traffic efficiency assessment includes analysis of the total route length, expected evacuation time, identification of channel bottlenecks, and crowd-carrying capacity. The evaluation algorithm utilizes a weighted scoring method and a risk assessment matrix to calculate a comprehensive safety index and prioritize each route. The assessment also considers the timeframe of fire spread, analyzing the availability and safety of each route over different time periods. Ultimately, a hierarchical configuration plan is developed, encompassing primary, alternative, and emergency routes, clearly defining the usage conditions, applicable scenarios, and switching criteria for each route. The evacuation route plan also includes detailed crowd distribution strategies, route capacity control, and a dynamic scheduling mechanism. For example, in a hotel fire, a safety assessment revealed that the east fire stairway was the preferred route due to its independent smoke control system and shorter evacuation distance. The west evacuation stairway was designated as the primary alternative, while the central stairway was designated as an emergency backup route due to potential smoke exposure. After completing the safety assessment and route configuration, an evacuation route plan was developed.

[0051] In some embodiments, formulating the rescue action boundary and generating a safe operating range based on the evacuation path plan includes: analyzing the evacuation time requirement based on the evacuation path plan to obtain time safety parameters; determining the rescue action boundary based on the time safety parameters; and generating a safe operating range based on the rescue action boundary.

[0052] First, based on the evacuation route plan, evacuation time requirements are analyzed to obtain temporal safety parameters. This temporal safety analysis utilizes the previously generated evacuation route plan to perform detailed time calculations. By analyzing the evacuation time requirements of personnel in different areas, the time constraints for rescue operations are determined. This time calculation considers the impact of population density, movement speed characteristics, path capacity, and bottleneck effects on evacuation efficiency. Evacuation time is calculated using a crowd evacuation dynamics model, taking into account the movement characteristics of different groups and their behavior patterns in emergency situations. Fire spread time prediction, based on the previously generated distribution of hazardous areas, determines the critical time points at which each area becomes impassable. A safety margin is set to ensure sufficient evacuation time for rescue personnel, typically as a specific percentage of the minimum evacuation time. Temporal safety parameters include key indicators such as area evacuation time, path validity window, rescue mission execution time, and safe evacuation reserve time. For example, in a factory fire, the complete evacuation of a workshop required 12 minutes, and the safe and effective time for the main evacuation route was 18 minutes. After considering the safety margin, the maximum allowable time for rescue operations was determined to be 8 minutes. Through detailed time analysis and safety margin calculation, key temporal safety parameters are obtained.

[0053] Then, the rescue action boundary is determined based on the temporal safety parameters. Based on the temporal safety parameters obtained above, the rescue action boundary is determined using spatiotemporal analysis methods to define the safe time window and spatial scope of the rescue operation. The temporal boundary specifies the safe operation time limit for each area, while the spatial boundary defines the safe access area within a given timeframe. Dynamic analysis is used to determine the boundary, requiring real-time adjustment and updating of the action boundary as the fire progresses and time passes. The rescue action boundary is represented as a spatiotemporal graph, clearly describing the temporal trends and boundary evolution of the safe operation area. Boundary delineation considers the time requirements and risk characteristics of different rescue tasks, establishing corresponding action boundaries for different task types, such as personnel search and rescue, equipment recovery, and fire reconnaissance. Boundary information includes accurate time nodes, spatial coordinates, and safety level identifiers. For example, in a residential building fire, based on an 8-minute safe operation time window, the rescue action boundary was determined to include the first-floor lobby, the west side of the second floor, and the north side of the third floor. This boundary gradually shrinks over time. Based on the above spatiotemporal analysis and dynamic modeling, the rescue action safety boundary is delineated.

[0054] Finally, a safe operating range (SAAR) is generated based on the rescue operation boundary. This SAAR utilizes the previously determined rescue operation boundary to develop a detailed rescue operation area plan and operational guidance. The SAAR includes comprehensive information such as the safe access area, recommended operation time, entry and exit routes, and emergency response plans. The SAAR planning considers the priorities and resource requirements of different rescue tasks, prioritizing rescue operations for high-value targets and vulnerable individuals. Safety monitoring points and communication relay points are set within the range to ensure real-time communication between rescue personnel and the command center. The SAAR utilizes a hierarchical management strategy, dividing the operation area into core, buffer, and emergency areas based on safety levels. Operational guidance includes specific task assignments, personnel deployment, equipment requirements, and safety precautions. The range planning also includes a dynamic adjustment mechanism to promptly update the SAAR and safety measures based on changing on-site conditions. For example, in a chemical plant fire rescue, the SAAR included the front half of the reactor, the main corridor, and the adjacent office area. Two entry routes and three exit routes were established, along with five safety monitoring points and three communication relay points. The SAAR is generated. Combining boundary constraints and actual mission requirements, a complete safe operating range was finally established.

[0055] Step S130: Obtain rescue target information, decompose the rescue target information into tasks to generate a fragmented rescue task set, and dynamically reorganize the fragmented rescue task set based on firefighter status data to generate a personalized task allocation plan.

[0056] Specifically, rescue target information is obtained. On-site reconnaissance information is acquired through video equipment, thermal imaging cameras, and acoustic detectors carried by firefighters, providing real-time information on the location, number, status, and surrounding environment of trapped personnel. Building information, including static data such as floor plans, room layouts, occupancy capacity, and functional usage, is obtained through building information models and fire records. Personnel registration information, derived from access control records, attendance clocks, visitor registration, and security monitoring, provides basic data on personnel distribution. Real-time monitoring information is dynamically updated through smoke detectors, emergency call systems, mobile phone signal positioning, and life detection equipment. An information fusion algorithm verifies the spatiotemporal correlation and consistency of multi-source data, identifies and eliminates conflicting information, and establishes a credibility assessment mechanism. Target priority assessment is performed based on a comprehensive ranking of factors such as human safety, property value, environmental impact, and rescue difficulty. Information representation utilizes a structured data format, encompassing attributes such as target location, target type, urgency, rescue difficulty, and time constraints. For example, in a hotel fire, rescue target information indicated that there were 12 trapped guests in the eighth-floor guestroom area, including three elderly people in room 808, requiring priority rescue. Eight people were trapped in the fifth-floor conference room, but the area was close to the emergency exit, making rescue relatively easy. Through multi-source information fusion and priority analysis, rescue target information was generated.

[0057] In some embodiments, decomposing the rescue target information into tasks to generate a fragmented rescue task set includes: performing a complexity analysis on the rescue target information to obtain a task complexity assessment; decomposing the rescue task into minimum execution units based on the task complexity assessment; performing a correlation analysis on the minimum execution units to generate task dependencies; and generating a fragmented rescue task set based on the task dependencies.

[0058] Perform complexity analysis on the rescue target information to obtain a task complexity assessment. The time complexity assessment considers the expected execution time, time window constraints, and timing dependencies of the rescue task, and analyzes the time sensitivity and urgency of the task. The spatial complexity assessment analyzes the spatial distribution, accessibility, and environmental complexity of the rescue target, including factors such as floor height, narrowness of the passage, obstacle distribution, and space constraints. The resource complexity assessment considers the human resources, equipment resources, and technical resources required for the rescue mission, and analyzes the complexity of resource allocation and the possibility of resource conflicts. The coordination complexity assessment analyzes the mutual influence between multiple rescue targets, the coordination requirements between rescue teams, and the complexity of command and control. The comprehensive assessment formula for task complexity is C=w1·C t +w2·C s +w3·C r +w4·C o , Constraints: w1+w+w3+w4=1, and w1, w2, w3, w4≥0, where C represents the comprehensive complexity index, C t is the time complexity, C s is the space complexity, C r is the resource complexity, C o To coordinate complexity, w i are the weight coefficients for each dimension. Complexity calculation uses a weighted scoring model, and the complexity of each dimension is quantitatively assessed using an expert knowledge base and historical case data. The algorithm also considers the impact of uncertainty on complexity, using fuzzy logic and probabilistic analysis to address the increased complexity caused by incomplete information and environmental changes. For example, in a fire at a shopping mall, the rescue mission in the first-floor electrical appliance section was assessed as high complexity due to the involvement of flammable and explosive items, the open space but dense smoke, and the need for specialized equipment and multi-team coordination. However, the rescue mission in the third-floor dining area was rated as medium complexity due to the concentrated personnel, relatively simple access routes, and standard equipment requirements. Based on multi-dimensional analysis and quantitative assessment, the task complexity assessment results are obtained.

[0059] Based on task complexity assessment, the rescue mission is broken down into its smallest executable units. Decomposition adheres to the principles of single responsibility, independent execution, clear inputs and outputs, and measurable completion. Hierarchical decomposition begins with the primary phases of the rescue mission and gradually refines them into specific operational steps. Each level of decomposition maintains logical integrity and operational feasibility. Functional decomposition breaks down complex functions into basic functional combinations based on the mission's functional characteristics, ensuring that each smallest unit has a clear functional definition and execution standards. The decomposition process considers a balance between the granularity of the execution units, ensuring sufficient granularity to support flexible combination while avoiding the management complexity caused by excessive decomposition. The smallest execution unit includes a detailed task description, execution conditions, required resources, expected time, completion standards, and quality requirements. Unit definitions utilize a standardized format to facilitate subsequent assembly and scheduling. For example, in an office building fire, the complex task of "rescuing trapped personnel on the eighth floor" was broken down into smallest execution units, including "arriving at the eighth floor," "searching for trapped personnel," "assessing personnel status," "selecting rescue methods," "performing rescue operations," and "escorting to a safe area." Each unit has specific operational specifications and completion markers. Through hierarchical and functional decomposition, a minimum execution unit library is established.

[0060] Correlation analysis is performed on the minimum execution units to generate task dependencies. Logical relationship analysis identifies the prerequisites, trigger conditions, and constraints between execution units, determining which units must complete before execution. Timing relationship analysis determines the temporal sequence of execution units, the possibility of parallel execution, and time window constraints, and establishes a temporal dependency graph. Resource relationship analysis identifies execution units that need to share resources, analyzes resource conflicts and resource coordination requirements, and establishes a resource dependency matrix. Spatial relationship analysis considers the spatial location requirements and movement path dependencies of execution units, identifying spatial conflicts and spatial coordination requirements. Dependency modeling uses a directed acyclic graph structure, with nodes representing minimum execution units and edges representing dependencies. Edge attributes include dependency type, strength, and constraints. The algorithm also performs consistency checks on dependencies to identify and resolve issues such as circular dependencies, conflicting dependencies, and unsatisfiable dependencies. Dependency optimization uses critical path analysis and parallelism analysis to find the dependency configuration that optimizes execution efficiency. For example, in a factory fire rescue, the "Search for trapped personnel" unit must be executed after the "Arrival at the accident area" unit is completed. "Assessing personnel status" and "Preparing rescue equipment" can be executed in parallel, and "Executing rescue operations" depends on the completion of the first two units, forming a clear dependency network. Through correlation mining and dependency modeling, a task dependency graph is generated.

[0061] A fragmented rescue task set is generated based on task dependencies. This set generation considers dependency constraints to ensure that the execution units within each task fragment are executed in the correct order and that fragments can be combined in parallel or serially. The algorithm uses topological sorting and strongly connected component decomposition techniques to identify independently executable task subgraphs, forming relatively independent task fragments. This fragment division balances execution efficiency and complexity management, leveraging opportunities for parallel execution while controlling the number of fragments and the complexity of inter-fragment coordination. Each task fragment contains a complete sequence of execution units, a list of resource requirements, an estimated execution time, preconditions, and outputs. The task set also includes inter-fragment coordination mechanisms, synchronization point settings, and exception handling plans. Set optimization uses critical path analysis and load balancing techniques to find fragment combinations that minimize execution time and optimize resource utilization. For example, in a hospital fire rescue operation, the fragmented task set includes relatively independent task fragments such as "emergency transfer of intensive care unit personnel," "protection of operating room equipment," "safe disposal of the drug warehouse," and "clearing of evacuation routes." Each fragment consists of several minimal execution units, and fragments are synchronized through time nodes and resource coordination. Through dependency analysis and fragmented organization, a collection of fragmented rescue tasks is constructed.

[0062] In some embodiments, the dynamic reorganization of the fragmented rescue task set based on the firefighter status data to generate a personalized task allocation plan includes: performing an ability assessment on the firefighter status data to obtain personal ability indicators; matching the fragmented rescue tasks based on the personal ability indicators to obtain task matching results; dynamically reorganizing according to the task matching results to obtain a reorganized task sequence; and generating a personalized task allocation plan based on the reorganized task sequence.

[0063] Firefighter status data is used to assess individual competency indicators. Assessment dimensions include key aspects such as physical, technical, experienced, and psychological capabilities. The physical competency assessment analyzes firefighters' physical endurance and sustained work capacity based on vital sign data, fatigue index, physical reserve, and health status. The technical competency assessment assesses firefighters' technical competency in various rescue missions based on professional skill level, equipment proficiency, special skills certifications, and training records. The experienced competency assessment quantifies the value of firefighters' practical experience based on historical rescue participation records, experience in similar scenarios, emergency response success rates, and teamwork performance. The psychological competency assessment analyzes firefighters' psychological adaptability in high-pressure environments based on stress tolerance indicators, decision-making response speed, risk assessment, and team communication skills. Capacity calculation utilizes fuzzy comprehensive evaluation and neural network methods, integrating static capability profiles and dynamic status monitoring data to generate real-time capability assessment results. The assessment also considers the timeliness and decay characteristics of capabilities, predicting capability trends based on mission duration and intensity. For example, during a high-rise residential fire, firefighter Li's physical ability assessment showed low fatigue and ample energy. His technical skills were outstanding in high-altitude rescues, his experience was extensive in similar building rescues, and his mental ability was sufficient to remain calm in complex environments. His overall ability indicators were suitable for undertaking challenging rescue missions. Based on multi-dimensional assessment and dynamic analysis, individual ability indicators were obtained.

[0064] Matching fragmented rescue tasks based on individual ability indicators yields task matching results. First, perform an ability requirement analysis for each task segment to identify the specific requirements and importance of physical, technical, experiential, and psychological abilities. Ability requirement modeling utilizes multi-attribute decision-making theory to establish a task-ability requirement matrix, clarifying the level of demand for different ability dimensions for each type of task. The formula for calculating the degree of match between personnel and tasks is: The fitness function is: Constraints: w1+w2+...+w n =1, and all w k ≥0, where M(i, j) represents the matching degree between person i and task j. represents the kth capability index of person i, represents the demand level of task j for the kth capability, w kis the weight coefficient for the kth capability. The matching calculation utilizes a multi-objective optimization algorithm to identify a staffing solution with the highest capability utilization efficiency and strongest capability complementarity, while meeting mission capability requirements. The algorithm considers multiple optimization objectives, including capability matching, capability margin, capability complementarity, and load balancing, and finds a balanced solution using a Pareto optimal solution set. The matching results are presented as a matching matrix and matching score, recording the degree of match and recommended priority for each firefighter and each task segment. For example, in a shopping mall fire, the high-altitude rescue mission segment was the most compatible with firefighter Wang, who holds a high-altitude work certification and extensive high-rise rescue experience. The equipment operation mission segment was the best match for firefighter Zhang, who is proficient in specialized rescue equipment. The chemical disposal mission was the best match for firefighter Liu, who possesses hazardous chemical disposal qualifications. Through intelligent matching and multi-objective optimization, the task matching results are obtained.

[0065] Dynamic reorganization is performed based on task matching results to obtain a reorganized task sequence. Based on the matching results, the urgency and feasibility of task segments are reassessed, prioritizing those with high matching and criticality. Sequence optimization utilizes dynamic programming and genetic algorithms to find a task execution sequence that minimizes total execution time and minimizes resource conflicts, while satisfying task dependencies. The reorganization algorithm also considers load balancing and complementary capabilities, preventing some personnel from being overloaded while others are idle, while ensuring team complementarity and synergy. A dynamic adjustment mechanism updates the task sequence and personnel allocation in real time based on feedback during task execution to adapt to changing on-site conditions. The reorganization results are presented in the form of a time Gantt chart and task network diagram, clearly demonstrating the timing and personnel allocation of task execution. For example, during a factory fire rescue, the equipment rescue task, originally scheduled later, was brought forward due to the matching of specialized technicians. Personnel search and rescue tasks were regrouped based on personnel capabilities, forming two parallel search and rescue teams, significantly improving overall rescue efficiency. Through dynamic scheduling and sequence optimization, a reorganized task sequence is obtained.

[0066] A personalized task allocation plan is generated based on the reorganized task sequence. Using the reorganized task sequence, a detailed, personalized rescue action plan and execution guidance is developed. The allocation plan includes complete information about each firefighter's specific task schedule, execution time, work location, required equipment, cooperating partners, and safety precautions. The personalized design tailors task execution strategies and operational specifications based on each firefighter's capabilities, current status, and task match. Plan generation considers both operational feasibility and safety, allocating sufficient capacity margins and safety measures for each task. The allocation strategy also incorporates a task rotation mechanism and fatigue management measures, arranging personnel rest and job rotations based on task intensity and duration. Contingency plans are designed to address potential emergencies such as personnel injuries, equipment failures, and environmental changes, creating appropriate task reallocation and personnel scheduling strategies. The plan representation utilizes a multi-level structure, encompassing information at different levels, including an overall allocation overview, team task division, detailed individual arrangements, and contingency plans. A quality control mechanism ensures the effectiveness of the task allocation plan through task completion standards, quality checkpoints, and performance evaluation indicators. For example, during a hospital fire rescue operation, a personalized task allocation plan assigned experienced firefighters complex critically ill patient transfers, physically fit young firefighters high-intensity equipment handling tasks, and technically skilled firefighters specialized equipment operation tasks. Each firefighter had a clear mission objective, execution path, and collaboration requirements. By combining personnel capabilities with mission execution requirements, a personalized task allocation plan was ultimately established.

[0067] Step S140: Perform rescue operations within a safe operating range according to the personalized task allocation plan to generate a rescue execution record, establish a two-way status confirmation channel between the rescuer and the rescued based on the rescue execution record, and obtain two-way confirmation data through the two-way status confirmation channel.

[0068] Rescue execution records are generated by executing rescue operations within the safe operating area according to the personalized task assignment plan. Specific execution instructions and operational guidance are issued to each rescue team based on the timeline, staffing, and task priorities specified in the task assignment plan. These instructions include information such as mission objectives, execution paths, operational specifications, and safety requirements. Safe operating area constraints ensure that all rescue operations are conducted within the predetermined safety boundary. GPS positioning technology is used to monitor the location and movement of rescue personnel in real time. During the operation, firefighters upload execution status information in real time using head-mounted cameras, voice recorders, and operational sensors. Video recording captures visual information of the rescue scene, audio recording captures communications and descriptions between rescue personnel, and operational sensors monitor the use and functional performance of rescue equipment. Execution record generation utilizes multimodal data fusion technology to synchronize and integrate video, audio, sensor data, and location information along a timeline. Structured storage of records includes key information such as execution time, location, personnel, tasks, operational steps, and completion status. For example, during a fire rescue operation in a high-rise apartment building, a firefighter search and rescue team, following a predetermined route based on a personalized task allocation plan, entered the 12th floor area and searched for trapped residents by breaking down doors and windows. Recordings of the entire process revealed the successful location of three trapped residents, and voice recordings demonstrated effective communication within the team. Through intelligent scheduling and multimodal recording, a detailed record of the rescue operation was created.

[0069] A two-way status confirmation channel is established between rescuers and victims based on rescue execution records. Communication technology options are varied depending on on-site environmental conditions, including wireless intercom systems for short-range voice communication, mobile communication networks utilizing cell phone signals for remote communication, emergency communication equipment consisting of portable signal transmitters and life detection communicators, and simple signaling devices using non-electronic methods such as percussion and light signals. The interactive interface design considers the physical and psychological state of the rescued, employing simple, intuitive operation and clear information presentation. The rescuer-side interface, integrated into the portable device, displays the rescued victim's basic information, health status, location, and communication status. The rescued-side interface utilizes voice dialogue, keystroke confirmation, gesture recognition, and physiological signal detection, depending on the specific situation. Channel testing and optimization ensure the stability and reliability of two-way communication, with signal strength testing and backup switching ensuring effective communication. For example, during a fire rescue operation at an underground shopping mall, rescuers used execution records to locate two workers trapped in a storage room on the first floor of the basement. They established voice contact with the trapped personnel using portable emergency communication equipment, allowing them to provide feedback on their physical condition and needs through simple keystrokes. Through communication technology integration and interactive design, a two-way status confirmation channel is established.

[0070] Bidirectional confirmation data is acquired through a bidirectional status confirmation channel. The data collection framework establishes two parallel data streams: rescuer status confirmation and rescued person status confirmation. Rescuer status confirmation includes information categories such as rescue progress reports documenting mission completion and follow-up plans, on-site environmental assessments including temperature, smoke, and structural stability, rescued person status observations documenting consciousness and physical condition, and safety status reports. Rescued person status confirmation includes information on their health status, collected through simplified question-and-answer sessions, including pain level and breathing status, level of consciousness and physical activity, psychological state and emotional response, environmental perception including temperature, smoke, and other environmental factors, and rescue request expressions, including specific requirements for rescue methods and medical needs. Data standardization converts confirmation information from different formats and sources into a unified data structure, establishing standard fields such as timestamp, data source, confirmation type, confirmation content, and credibility. Data quality control improves the accuracy of confirmation data through redundant confirmations and consistency checks. Real-time data synchronization ensures that the rescue command center has timely access to the latest bidirectional confirmation information. For example, during a factory fire rescue, rescuers confirmed they had reached the trapped workers' location and that the environment was safe and controllable. The three trapped workers were confirmed to be in good health, but one suffered from mild smoke poisoning and required medical attention. Rescuers confirmed they had on-site medical treatment capabilities, and the trapped workers confirmed their willingness to cooperate with the rescue operation. By utilizing standardized data collection and quality control mechanisms, complete, two-way confirmed data was ultimately obtained.

[0071] Step S150: Perform validity analysis of the rescue operation based on the two-way confirmation data to obtain rescue effect evaluation data, perform failure risk analysis on the rescue effect evaluation data to identify potential failure factors, and adjust the fragmented rescue task set according to the potential failure factors to generate an optimized task combination.

[0072] Specifically, rescue operation effectiveness analysis is conducted based on two-way confirmation data to obtain rescue effectiveness evaluation data. The analysis framework establishes a cross-validation mechanism between rescuer confirmation data and rescued person confirmation data. By comparing the two parties' different perspectives on the same rescue incident, the actual effectiveness and existing problems of the rescue operation are identified. Rescue progress effectiveness analysis evaluates the completion quality, time efficiency, and goal achievement of the task execution based on the rescuer's progress report and the rescued person's perceived feedback. Operational quality evaluation determines the extent to which the rescue operation improves the safety of the rescued person by analyzing the rescuer's on-site environmental assessment and changes in the rescued person's physical condition. Communication effectiveness analysis assesses the information transmission quality, response timeliness, and accuracy of understanding in the two-way confirmation channel. Resource utilization efficiency analysis combines the rescuer's resource needs and actual usage to evaluate the rationality of staffing, equipment use, and time allocation. The algorithm uses a fuzzy comprehensive evaluation method to establish a multi-dimensional effectiveness evaluation indicator system for each rescue operation. For example, during a fire rescue operation in an office building, two-way confirmation data analysis revealed that rescuers confirmed that the search was completed as planned on the eighth floor, but those rescued confirmed that two of them had become anxious while waiting. This analysis indicated that the search and rescue operation was technically effective, but psychological support needed improvement. This data was generated through two-way data cross-validation and multi-dimensional evaluation to evaluate rescue effectiveness.

[0073] Failure risk analysis is conducted on rescue effectiveness evaluation data to identify potential failure factors. A comprehensive risk scan is conducted from the perspectives of technical failure, process failure, personnel failure, and environmental failure. Technical failure analysis identifies potential technical issues such as equipment failure, communication interruption, and positioning deviation, and issues early warnings based on abnormal patterns in the effectiveness evaluation data. Process failure analysis examines weaknesses in process links such as task execution sequence, coordination, and timing, identifying process defects that may lead to rescue delays. Personnel failure analysis assesses human risks such as rescuer competency, fatigue, and psychological stress, and identifies personnel deficiencies through performance deviations in effectiveness evaluations. Environmental failure analysis considers the negative impact of environmental factors such as fire intensity fluctuations, structural damage, and weather on rescue effectiveness. An algorithm establishes a correlation analysis model for failure factors to identify compound risks that may arise from the combination of multiple factors. For example, during a factory fire rescue, failure risk analysis identified technical risks associated with communication equipment performance degradation in high-temperature environments, process risks associated with conflicting search and rescue tasks between personnel and equipment, and personnel risks associated with insufficient chemical handling experience on the part of some rescuers. Through systematic risk scanning and correlation analysis, key potential failure factors are identified.

[0074] In some embodiments, adjusting the fragmented rescue task set according to the potential failure factors to generate an optimized task combination includes: evaluating the impact of the potential failure factors to obtain a failure risk level; screening the task segments that need to be adjusted based on the failure risk level; reconfiguring the task segments that need to be adjusted to obtain an adjustment plan; and reorganizing the fragmented rescue tasks according to the adjustment plan to generate an optimized task combination.

[0075] Potential failure factors are assessed for their impact to determine a failure risk level. Assessment dimensions include key indicators such as scope of impact, severity of impact, probability of occurrence, and difficulty of response. The scope of impact assessment analyzes the number of tasks, personnel, and spatial extent that a failure factor could affect. The severity assessment considers the potential damage to rescue objectives, personnel safety, and time delays. The probability of occurrence assessment predicts the likelihood of a failure factor actually occurring based on historical data, current conditions, and environmental trends. The algorithm uses a fuzzy evaluation method to calculate a comprehensive risk index for each failure factor. Risk levels are categorized into three levels: high, medium, and low. High-risk factors have significant impacts and a high probability of occurrence; medium-risk factors have a moderate impact or probability; and low-risk factors have limited impact and a low probability of occurrence. For example, in a hospital fire rescue operation, high-temperature failure of communication equipment was rated high risk because it impacted global coordination and had a high probability of occurrence. Insufficient critical patient transfer equipment was rated medium risk because it had a local impact but a backup plan was available. Through multi-dimensional assessment and grading, a failure risk level classification was obtained.

[0076] Task segments requiring adjustment are screened based on their failure risk level. The screening strategy prioritizes high-risk failure factors and the task segments they directly impact, while also considering potential threats from medium-risk factors. Impact propagation analysis establishes a mapping between failure factors and task segments within the fragmented rescue task set, identifying the specific task segments each failure factor may impact and the extent of that impact. Task segment vulnerability assessment analyzes the sensitivity of each task segment within the fragmented rescue task set to different failure factors, identifying those with the highest vulnerability as key areas for adjustment. The algorithm considers dependencies between task segments to avoid negative impacts of adjustments to one segment on other segments within the set. The screening results are sorted by adjustment priority, forming a list of tasks requiring adjustment from the fragmented rescue task set. For example, in a shopping mall fire rescue operation, based on the high-risk communication disruption factor, task segments identified for adjustment from the fragmented rescue task set included floor-by-floor search and rescue coordination, equipment deployment, and personnel status monitoring. Through risk propagation analysis and prioritization, critical task segments requiring adjustment are identified within the fragmented rescue task set.

[0077] Reconfigure the task segments that require adjustment to obtain an adjustment plan. The configuration strategy employs different adjustment methods based on the characteristics of the failure factors, including task decomposition, task merging, task replacement, task enhancement, and task rescheduling. Task decomposition breaks down complex or high-risk task segments within a fragmented rescue task set into multiple simpler subtasks, reducing the impact of single-point failures. Task merging integrates related small task segments within the set into a unified task, improving execution efficiency. Task replacement replaces high-risk task segments within the set with lower-risk alternatives. Task enhancement strengthens the reliability of task segments within the set by adding backup resources and safety measures. The reconfiguration process considers practical constraints such as personnel capability matching, equipment resource constraints, and time window restrictions. The adjustment plan includes detailed task descriptions, personnel allocation, equipment configuration, and time scheduling. For example, in a hotel fire rescue, addressing the high risk of the elevator shaft search and rescue task segment within the fragmented rescue task set, the adjustment plan included breaking down the original single-team search and rescue into a two-team collaborative search and rescue, adding backup communication equipment, and adjusting the execution time to avoid periods of structural instability. Based on the risk characteristics and constraints, a detailed adjustment plan for the fragmented rescue task set is developed.

[0078] Based on the adjustment plan, fragmented rescue tasks are reorganized to generate an optimized task combination. The reorganization process first updates the task dependency graph within the fragmented rescue task set, reflecting the impact and changes of the adjusted task segments on the original dependencies. Task scheduling optimization utilizes a heuristic algorithm to find the optimal task execution sequence and resource allocation while satisfying the dependencies. Optimization objectives include minimizing total execution time, minimizing risk, and optimizing resource utilization. The algorithm considers the robustness of the task combination to ensure that the optimized task combination can cope with environmental changes and emergencies. The resulting optimized task combination is an improved version of the original fragmented rescue task set, including a complete task list, execution plan, resource allocation, and risk control measures. For example, in a factory fire rescue, the reorganization and optimization of the fragmented rescue task set reduced the original six parallel task segments to four mixed serial and parallel task segments. The high-risk chemical disposal task in the set was decomposed into three subtasks: environmental assessment, professional disposal, and safety monitoring. The overall risk level of the task combination was reduced from high to medium. Through the integration and combined optimization of the fragmented rescue task set, an optimized task combination was ultimately established.

[0079] Step S160 , monitor the optimized task combination to obtain rescue process data, perform abnormal pattern recognition on the rescue process data to generate abnormal warning signals, and perform safety assessment based on the evacuation path plan combined with the abnormal warning signals to generate safety status monitoring results.

[0080] Specifically, the optimized task combination is monitored to obtain rescue process data. A multi-dimensional data collection system is established, encompassing key dimensions such as task execution progress monitoring, personnel status monitoring, environmental change monitoring, and resource utilization monitoring. Task execution progress monitoring provides real-time insights into the execution status of each task segment within the optimized task combination through task completion status reporting and time tracking, ensuring that the optimized task combination progresses in an orderly manner according to the established plan. For example, in a personnel search and rescue mission during a high-rise office building fire, the monitoring module can capture in real time that the execution progress of this task segment within the optimized task combination is 75%, indicating that the rescue team has completed the search of the area east of the eighth floor. Personnel status monitoring continuously tracks the physiological state, location information, equipment status, and communication status of firefighters executing the optimized task combination. If monitoring detects that a personnel participating in the optimized task combination is in good physical condition but the pressure in the protective equipment cylinder is low, prompting timely equipment replacement is provided. Environmental change monitoring collects dynamic changes in fire scene environmental parameters that affect the execution of the optimized task combination, including temperature, smoke, and gas concentration, to assess the extent of the environmental impact on the execution of the optimized task combination. Resource usage monitoring records the usage and performance of resources such as rescue equipment, firefighting equipment, medical supplies, and communications equipment during the execution of the optimized task combination, ensuring sufficient resources for the optimized task combination. Through multi-dimensional real-time monitoring and data collection, comprehensive rescue process data for the execution of the optimized task combination is obtained.

[0081] Abnormal pattern recognition is performed on rescue process data to generate abnormal warning signals. A multi-layered anomaly detection system is established using a combination of statistical analysis, machine learning, and expert rules. Statistical analysis identifies abnormal fluctuations and trend deviations in rescue process data by setting normal value ranges, rate of change thresholds, and statistical control limits. In actual fire rescue operations in a high-rise office building, the algorithm was able to identify intermittent communication signal interruptions during the search and rescue mission on the eighth floor. Time series anomaly detection uses sliding window analysis to identify sudden changes and abnormal trends in the data. Trend analysis can capture this abnormal pattern of decreased efficiency, such as when the evacuation speed was 15% slower than expected. Multivariate anomaly detection considers the correlations between different monitoring indicators to identify abnormal combinations in multi-dimensional data. Anomaly severity assessment assigns a severity level to detected anomalies based on their type, duration, scope, and development trend. Early warning signal generation utilizes a tiered alert system, including minor anomaly alerts, major anomaly warnings, and severe anomaly alarms. When some rescue workers are detected to be showing signs of mild fatigue, combined with multiple anomalies such as communication interruption and decreased efficiency, the algorithm will generate important anomaly warning signals, reminding the command center to pay attention to communication support and personnel rotation needs, and ultimately generate graded anomaly warning signals.

[0082] Based on the evacuation route plan and abnormal warning signals, a safety assessment is conducted to generate safety status monitoring results. A dual evaluation system consisting of abnormal impact analysis and evacuation capacity assessment is established. The abnormal impact analysis assesses the specific impact of the abnormality on rescue safety based on the type and severity of the abnormal warning signal. The evacuation capacity assessment uses the path configuration, traffic capacity, and time parameters in the evacuation route plan, combined with the current occupant distribution and environmental conditions, to evaluate the safe evacuation capability under abnormal conditions. In a specific application of high-rise office building fire rescue, when evaluating based on the abnormal communication interruption warning signal, the algorithm checks the communication coverage of each path in the evacuation route plan. It finds that the main evacuation path on the east side is difficult to coordinate due to a communication failure, but the communication equipment on the backup path on the west side is still functioning normally. The time safety analysis calculates the time required to complete a safe evacuation under the current abnormal conditions and compares it with the fire spread forecast to assess the time safety margin. By calculating the current occupant distribution and available path capacity, the assessment results show that safe evacuation can be completed within 12 minutes, while the fire spread forecast indicates a safe time of 20 minutes, which is sufficient time safety margin. The comprehensive safety assessment uses a multi-factor weighting model to comprehensively calculate the impact of the anomaly, evacuation capabilities, route availability, and time safety to generate a safety status level. The safety status is categorized using a four-level system: green safe, yellow caution, orange warning, and red dangerous. Based on the above analysis, the comprehensive assessment results in a yellow caution status, recommending enhanced personnel guidance on the western route and expedited restoration of communications on the eastern route, ultimately forming the safety status monitoring results.

[0083] Step S170: Dynamically adjust the current rescue target according to the safety status monitoring results to generate a redefined rescue standard, convert the redefined rescue standard into a risk dimension to generate a controllable risk parameter, formulate a rescue strategy based on the controllable risk parameter to generate a final control instruction, and complete the intelligent fire scene fire rescue control.

[0084] Specifically, using safety status monitoring results, dynamic assessment and target reconstruction techniques enable real-time adjustment and optimization of current rescue objectives. The adjustment strategy determines the direction and magnitude of target adjustments based on the safety level, key risk factors, and dynamic trends in the safety status monitoring results. When the safety status level is green, the original rescue objectives and standards are maintained. When the safety status level is yellow, the priority and execution standards are moderately adjusted. When the safety status level is orange, warning, or red, dangerous, the rescue objectives are significantly adjusted, prioritizing personnel safety. The target adjustment process considers factors such as rescue resource constraints, time window limitations, and environmental trends. During a fire rescue operation in a high-rise office building, when the safety status monitoring results indicated a yellow, cautionary level and the primary risk factor was a loss of communication on the east side, the target adjustment algorithm changed the original "comprehensive search and rescue of all areas on the eighth floor" to "prioritize search and rescue of the west side with communication, temporarily suspending search and rescue of the east side until communication is restored." The redefinition of rescue criteria includes adjusted target content, execution priority, time requirements, safety margins, and resource allocation. The target reconstruction utilizes a multi-objective optimization approach to maximize rescue effectiveness while ensuring safety. The redefined rescue standards also include a dynamic adjustment mechanism that can be readjusted based on subsequent changes in the safety status. The redefined rescue standards are generated based on safety status analysis and target optimization.

[0085] In some embodiments, the risk dimension conversion of the redefined rescue standard to generate controllable risk parameters includes: identifying risk factors of the redefined rescue standard to obtain risk constituent elements; establishing a multi-dimensional risk assessment system based on the risk constituent elements; using the multi-dimensional risk assessment system to quantify risks; and generating controllable risk parameters based on the risk quantification results.

[0086] Leveraging redefined rescue standards, risk decomposition and factor extraction techniques systematically identify various risk factors that impact the implementation of rescue standards. Identification dimensions include key categories such as personnel risk factors, environmental risk factors, technical risk factors, and time risk factors. Personnel risk factors analyze the impact of factors such as rescue personnel's competence, fatigue, equipment condition, and collaborative efficiency on standard implementation. For example, in the redefined standards for high-rise office building fire rescue, when prioritizing the west side of the rescue area, personnel risk factors include the adequacy of the west rescue team's personnel and their familiarity with the area. Environmental risk factors assess potential threats to standard implementation from environmental factors such as fire growth, smoke spread, structural stability, and meteorological conditions. Technical risk factors identify the reliability and applicability of technical factors such as communications equipment, rescue equipment, monitoring equipment, and information processing technology. Time risk factors analyze the relationship between the time required to implement the redefined standards and the available time window. Element identification utilizes a combination of expert knowledge bases and historical case analysis to ensure comprehensive and accurate risk factor identification. Identification results are stored as a structured element list, with each element containing attributes such as type, impact, probability of occurrence, and control difficulty. Obtain risk components through systematic risk decomposition and factor extraction.

[0087] Based on risk components, a comprehensive assessment framework encompassing various risk factors is established through the use of hierarchical analysis and weighting techniques. This multi-layered framework comprises risk categories, risk factors, and risk indicators. The risk category layer categorizes and summarizes risk components according to their nature and characteristics. The risk factor layer provides a detailed breakdown of each risk category. The risk indicator layer establishes specific quantitative assessment indicators. Weighting is assigned using a combination of the analytic hierarchy process (AHP) and expert judgment to assign appropriate weights to risk factors at different levels. For example, in a high-rise office building fire rescue scenario, the assessment system might assign a 30% weight to personnel risk factors, a 40% weight to environmental risk factors, a 20% weight to technical risk factors, and a 10% weight to time risk factors. This weighting reflects the predominance of environmental risks in this scenario. System validation ensures the scientific nature and applicability of the assessment system through historical case studies and expert review. Standardization of assessment indicators ensures comparability and operability across different types of indicators. Ultimately, through the use of AHP and weighting techniques, a comprehensive multi-dimensional risk assessment system is established.

[0088] Utilizing a multidimensional risk assessment system, numerical calculations and statistical analysis techniques are used to convert qualitative risk descriptions into quantitative risk values. The quantitative approach employs a combination of fuzzy comprehensive evaluation, the analytic hierarchy process (AHP), and Monte Carlo simulation. Fuzzy comprehensive evaluation addresses the uncertainty and ambiguity in risk assessment, generating fuzzy evaluation results for each risk factor through the establishment of a fuzzy evaluation matrix and fuzzy operations. The AHP addresses the weighting relationships between risk factors, determining the relative importance of each factor through the construction of a judgment matrix and consistency testing. Monte Carlo simulation addresses the randomness and variability in risk assessment, estimating the probability distribution and confidence intervals of risk indicators through random sampling and probability distribution. In a specific application of high-rise office building fire rescue, the quantitative analysis might yield a personnel risk index of 0.3, an environmental risk index of 0.6, a technical risk index of 0.4, a time risk index of 0.2, and a comprehensive risk index of 0.43. The quantitative results also include a risk grading system, mapping continuous risk values ​​into discrete risk levels to facilitate decision-making and control. The quantitative analysis results are output as a risk assessment report, which includes quantitative values ​​for each risk category, grading, probability distribution, and trend analysis. Through numerical calculation and statistical analysis, the risk quantification results are finally obtained.

[0089] Exemplarily, generating controllable risk parameters based on the risk quantification processing results includes: dividing the risk quantification processing results into risk thresholds to obtain risk control boundaries; establishing a risk adjustment mechanism based on the risk control boundaries to generate an adjustment strategy; using the adjustment strategy to perform controllability conversion on the risk level to obtain a conversion coefficient; and generating controllable risk parameters based on the conversion coefficient.

[0090] First, the risk quantification results were classified into risk thresholds to obtain risk control boundaries. Using a combination of percentile analysis, K-means cluster analysis, and expert experience, the critical thresholds and control boundaries for different risk levels were determined based on the distribution characteristics of historical risk data and fire rescue safety standards. For high-rise office building fire rescue, the low-risk boundary was set at 0.0-0.3, the medium-low-risk boundary at 0.3-0.5, the medium-high-risk boundary at 0.5-0.7, and the high-risk boundary at 0.7-1.0. This boundary setting also took into account the different characteristics of different risk types. Then, a risk adjustment mechanism was established based on the risk control boundaries to generate adjustment strategies. Using a hierarchical response and escalating control model, a complete adjustment system was established, encompassing early warning mechanisms, proactive adjustment mechanisms, and emergency response mechanisms. When the current risk index of 0.43 falls within the medium-low risk boundary, the early warning mechanism was activated. Adjustment strategies included increasing staffing in the western area, strengthening the backup deployment of communication equipment, shortening the status reporting interval to every 5 minutes, and establishing a feedback control loop for dynamic adjustment. Next, the controllability conversion of the risk level is performed using the adjustment strategy to obtain the conversion coefficient. Through control effect analysis and historical data verification technology, the risk reduction ability and execution efficiency of each adjustment strategy are evaluated. Considering factors such as control ability, response time and resource constraints, the mathematical model of risk conversion is: R'=R×∏ i＝1 m(1-η i α i ), conversion coefficient calculation formula: k=R' / R=∏ i＝1 m(1-η i α i ), where R is the original risk level, R' is the adjusted risk level, η i is the maximum risk reduction capability of the i-th adjustment strategy, α i is the implementation intensity coefficient of the i-th strategy (0≤α i ≤1), m is the total number of adjustment strategies. Finally, controllable risk parameters are generated based on the conversion coefficient. Through parameter mapping and standardization technology, a functional relationship between the conversion coefficient and the control parameter is established, and the risk control information is converted into a standardized parameter form that can be directly used in the formulation of rescue strategies. Controllable risk parameters include a complete parameter system such as risk control level, adjustment intensity coefficient, personnel resource allocation ratio, equipment resource allocation ratio, logistics resource allocation ratio, time constraint coefficient and safety margin coefficient. For example, in a fire rescue in a high-rise office building, when the risk conversion coefficient indicates that the risk level is effectively controlled, the corresponding risk control level will be automatically generated as "medium controllable". Based on this, the appropriate adjustment intensity is determined, and personnel resources are reasonably allocated to search and rescue tasks in communicable areas. Equipment resources are focused on communication restoration and life detection, and logistics resources are reserved for support and emergency response. At the same time, reasonable time constraints and sufficient safety margins are set.

[0091] Based on controllable risk parameters, a rescue strategy is formulated and the final control instructions are generated. A combination of multi-objective optimization and constraint programming is employed to maximize rescue effectiveness and resource utilization efficiency while satisfying safety constraints. Optimization objectives include maximizing rescue success rate, minimizing execution time, minimizing resource consumption, and minimizing risk. Constraints include practical limitations such as personnel capacity, equipment resources, time window, and safety margin. In a high-rise office building fire rescue, based on controllable risk parameters, the strategy might determine the following: prioritize 65% of personnel resources to the west communication area, deploy 25% of equipment resources for communication restoration and life detection, and reserve 10% of logistical resources for support and emergency response. The rescue time target is set at completing the search and rescue in the west area within 15 minutes, with a safety margin factor of 1.2 to ensure sufficient safety time. Control instruction generation converts the abstract rescue strategy into specific operational instructions and task assignments. Instructions include personnel deployment, equipment deployment, time control, communication coordination, and security monitoring. The instruction format utilizes a standardized command and control protocol to ensure accurate communication and efficient execution. Command prioritization ensures the priority execution of critical commands, and a command tracking mechanism monitors the execution status and completion of commands. Final control commands are issued to each execution unit in the form of command packages, containing a complete task description, execution time, resource allocation, collaboration requirements, and safety reminders. Through strategy optimization and command generation, intelligent fire scene firefighting and rescue control is achieved, enabling automated control of the entire process from risk perception to intelligent decision-making.

[0092] In order to implement the intelligent fire scene fire rescue control method corresponding to the above method embodiment, to achieve the corresponding functions and technical effects. Figure 2 , Figure 2 The following is a block diagram of a smart fire scene firefighting and rescue system 200 provided in an embodiment of the present application. For ease of explanation, only the parts related to this embodiment are shown. The smart fire scene firefighting and rescue system 200 provided in an embodiment of the present application includes:

[0093] The data acquisition module 201 is used to collect firefighter location information and vital sign data to generate firefighter status data, obtain temperature change information around the firefighter, perform gradient analysis on the temperature change information, and reversely trace the fire source location to generate fire source distribution data;

[0094] A path planning module 202 is configured to predict fire spread based on the fire source distribution data to generate a dangerous area distribution, identify the boundary areas of the dangerous area distribution to generate relatively safe areas, construct an evacuation path plan from the dangerous area distribution to the relatively safe area, and formulate a rescue action boundary based on the evacuation path plan to generate a safe operation range;

[0095] The task assignment module 203 is configured to obtain rescue target information, decompose the rescue target information into tasks to generate a fragmented rescue task set, and dynamically reorganize the fragmented rescue task set based on the firefighter status data to generate a personalized task assignment plan;

[0096] The rescue execution module 204 is configured to execute a rescue operation within the safe operation range according to the personalized task allocation plan, generate a rescue execution record, establish a two-way status confirmation channel between the rescuer and the rescued based on the rescue execution record, and obtain two-way confirmation data through the two-way status confirmation channel;

[0097] An effectiveness evaluation module 205 is configured to perform an effectiveness analysis of the rescue operation based on the bidirectional confirmation data to obtain rescue effectiveness evaluation data, perform a failure risk analysis on the rescue effectiveness evaluation data to identify potential failure factors, and adjust the fragmented rescue task set according to the potential failure factors to generate an optimized task combination;

[0098] A safety monitoring module 206 is configured to monitor the optimized task combination to obtain rescue process data, identify abnormal patterns in the rescue process data to generate abnormal warning signals, and perform safety assessment based on the evacuation path plan and the abnormal warning signals to generate safety status monitoring results;

[0099] The strategy control module 207 is used to dynamically adjust the current rescue target according to the safety status monitoring results to generate a redefined rescue standard, convert the risk dimension of the redefined rescue standard to generate a controllable risk parameter, formulate a rescue strategy based on the controllable risk parameter to generate a final control instruction, and complete the intelligent fire scene fire rescue control.

[0100] The aforementioned intelligent fire scene fire rescue system 200 can implement the intelligent fire scene fire rescue control method of the aforementioned method embodiment. The optional options in the aforementioned method embodiment also apply to this embodiment and will not be described in detail here. The remaining contents of the embodiments of this application can be referenced to the contents of the aforementioned method embodiment and will not be further described in this embodiment.

[0101] The purpose of the above embodiments is to exemplify and deduce the technical solution of the present invention, and to fully describe the technical solution, purpose and effect of the present invention. Its purpose is to enable the public to have a more thorough and comprehensive understanding of the disclosed content of the present invention, and it does not limit the scope of protection of the present invention.

[0102] The above embodiments are not exhaustive and may include many other embodiments not listed above. Any replacements and improvements made without violating the concept of the present invention are within the scope of protection of the present invention.

Claims

1. An intelligent fire scene fire rescue control method, characterized in that: include: Collect firefighter location information and vital sign data to generate firefighter status data, obtain temperature change information around the firefighter, perform gradient analysis on the temperature change information, and reversely track the fire source location to generate fire source distribution data; Performing fire spread prediction based on the fire source distribution data to generate a dangerous area distribution, identifying the boundary area of ​​the dangerous area distribution to generate a relatively safe area, constructing an evacuation path plan from the dangerous area distribution to the relatively safe area, and formulating a rescue action boundary based on the evacuation path plan to generate a safe operation range; Obtaining rescue target information, breaking down the rescue target information into tasks to generate a fragmented rescue task set, and dynamically reorganizing the fragmented rescue task set based on the firefighter status data to generate a personalized task allocation plan; performing a rescue operation within the safe operating range according to the personalized task allocation plan to generate a rescue execution record, establishing a two-way status confirmation channel between the rescuer and the rescued based on the rescue execution record, and obtaining two-way confirmation data through the two-way status confirmation channel; Performing an effectiveness analysis of the rescue operation based on the two-way confirmation data to obtain rescue effect evaluation data, performing a failure risk analysis on the rescue effect evaluation data to identify potential failure factors, and adjusting the fragmented rescue task set according to the potential failure factors to generate an optimized task combination; Monitoring the optimized task combination to obtain rescue process data, performing abnormal pattern recognition on the rescue process data to generate abnormal warning signals, and performing safety assessment based on the evacuation path plan and the abnormal warning signals to generate safety status monitoring results; According to the safety status monitoring results, the current rescue target is dynamically adjusted to generate a redefined rescue standard, the redefined rescue standard is converted into a risk dimension to generate a controllable risk parameter, and a rescue strategy is formulated based on the controllable risk parameter to generate a final control instruction to complete the intelligent fire scene fire rescue control.

2. The method according to claim 1, characterized in that The step of performing gradient analysis on the temperature change information and reversely tracing the fire source position to generate fire source distribution data includes: Performing multi-point temperature gradient analysis on the temperature change information to obtain a gradient vector field; Constructing a temperature change trend graph based on the gradient vector field; Using the temperature change trend graph to perform reverse path tracking to generate candidate fire source locations; Fire source distribution data is generated according to the candidate fire source locations.

3. The method according to claim 1, characterized in that The constructing of an evacuation path plan from the dangerous area to the relatively safe area includes: Performing boundary identification on the dangerous area distribution to obtain dangerous boundary coordinates; Determine the shortest evacuation distance based on the dangerous boundary coordinates and the relatively safe area; Designing multiple alternative evacuation routes based on the shortest evacuation distance; A safety assessment is performed on the multiple alternative evacuation routes to generate an evacuation route plan.

4. The method according to claim 1, wherein The step of formulating a rescue action boundary according to the evacuation path plan to generate a safe operation range includes: Analyzing the evacuation time requirement based on the evacuation path plan to obtain a time safety parameter; Determining rescue operation boundaries based on the time safety parameters; A safe operating range is generated based on the rescue operation boundary.

5. The method according to claim 1, wherein The step of performing task decomposition on the rescue target information to generate a fragmented rescue task set includes: Performing complexity analysis on the rescue target information to obtain a task complexity assessment; Decomposing the rescue mission into minimum execution units based on the mission complexity assessment; Performing correlation analysis on the minimum execution unit to generate task dependency; A fragmented rescue task set is generated according to the task dependencies.

6. The method according to claim 1, characterized in that The dynamically reorganizing the fragmented rescue task set based on the firefighter status data to generate a personalized task allocation plan includes: Performing capability assessment on the firefighter status data to obtain individual capability indicators; Matching the fragmented rescue tasks based on the personal ability indicators to obtain task matching results; Perform dynamic reorganization according to the task matching results to obtain a reorganized task sequence; A personalized task allocation plan is generated based on the reorganized task sequence.

7. The method according to claim 1, characterized in that The step of adjusting the fragmented rescue task set according to the potential failure factors to generate an optimized task combination includes: Assess the impact of the potential failure factors to obtain a failure risk level; Selecting task segments that need to be adjusted based on the failure risk level; Reconfiguring the task segments that need to be adjusted to obtain an adjustment plan; The fragmented rescue tasks are reorganized according to the adjustment plan to generate an optimized task combination.

8. The method according to claim 1, characterized in that The step of converting the redefined rescue standard into a risk dimension to generate a controllable risk parameter includes: Identify risk factors for the redefined rescue standards to obtain risk constituent elements; Establish a multi-dimensional risk assessment system based on the risk components; Utilize the multi-dimensional risk assessment system to quantify risks; A controllable risk parameter is generated according to the risk quantification processing result.

9. The method according to claim 8, characterized in that Generating controllable risk parameters according to the risk quantification processing results includes: Performing risk threshold division on the risk quantification processing result to obtain the risk control boundary; Establishing a risk adjustment mechanism based on the risk control boundary to generate an adjustment strategy; Using the adjustment strategy to perform controllable conversion on the risk level to obtain a conversion coefficient; A controllable risk parameter is generated according to the conversion coefficient.

10. An intelligent fire scene fire rescue system, characterized in that: include: A data acquisition module is used to collect firefighter location information and vital sign data to generate firefighter status data, obtain temperature change information around the firefighter, perform gradient analysis on the temperature change information, and reversely track the fire source location to generate fire source distribution data; a path planning module, configured to predict the spread of fire based on the fire source distribution data to generate a dangerous area distribution, identify the boundary areas of the dangerous area distribution to generate relatively safe areas, construct an evacuation path plan from the dangerous area distribution to the relatively safe area, and formulate a rescue action boundary based on the evacuation path plan to generate a safe operation range; A task assignment module is used to obtain rescue target information, decompose the rescue target information into tasks to generate a fragmented rescue task set, and dynamically reorganize the fragmented rescue task set based on the firefighter status data to generate a personalized task assignment plan; a rescue execution module, configured to execute a rescue operation within the safe operation range according to the personalized task allocation plan, generate a rescue execution record, establish a two-way status confirmation channel between the rescuer and the rescued based on the rescue execution record, and obtain two-way confirmation data through the two-way status confirmation channel; an effect evaluation module, configured to perform an effectiveness analysis of the rescue operation based on the bidirectional confirmation data to obtain rescue effect evaluation data, perform a failure risk analysis on the rescue effect evaluation data to identify potential failure factors, and adjust the fragmented rescue task set according to the potential failure factors to generate an optimized task combination; a safety monitoring module, configured to monitor the optimized task combination to obtain rescue process data, perform abnormal pattern recognition on the rescue process data to generate abnormal warning signals, and perform safety assessment based on the evacuation path plan and the abnormal warning signals to generate safety status monitoring results; The strategy control module is used to dynamically adjust the current rescue target according to the safety status monitoring results to generate a redefined rescue standard, convert the risk dimension of the redefined rescue standard to generate a controllable risk parameter, formulate a rescue strategy based on the controllable risk parameter to generate a final control instruction, and complete the intelligent fire scene fire rescue control.

Images