Fire safety intelligent evaluation method and system, storage medium and program product

Abstract

The invention discloses a fire safety intelligent evaluation method and system, a storage medium and a program product, and the method comprises the steps: building a reference safety capacity index of a building according to the static parameters of the building, and calculating a real-time safety load index based on the dynamic parameters of the building; calculating the safety capacity-load ratio of the safety load index relative to the safety capacity index; building a safety buffer area room of the building; establishing an elastic threshold band in the safety buffer zone; calculating a normalized pressure index of the dynamic parameter according to the pressure index calculation function, and projecting the normalized pressure index to an elastic threshold band to obtain a parameter evolution track; determining an intersection point of the parameter evolution track and the elastic threshold band as a safety critical point; calculating a safety toughness index of the building according to the distribution characteristics and the occurrence frequency of the safety critical points; and determining a fire safety level evaluation result of the building according to the position of the safety toughness index in the preset safety level mapping set. According to the invention, the accuracy of building fire safety assessment is improved.

Description

Technical Field

[0001] The present application relates to the field of fire safety assessment, and in particular to a fire safety intelligent assessment method, system, storage medium and program product. Background Art

[0002] With the acceleration of urbanization and the continuous expansion of building scale, the fire safety problem of buildings has become increasingly prominent. Traditional fire safety assessment methods mainly rely on manual on-site inspections and empirical judgments, which have defects such as low assessment efficiency and strong subjectivity, and are difficult to meet the fire safety management needs in the current complex building environment.

[0003] In the relevant technology, relevant data can be collected from multiple channels such as the building's design documents, on-site inspections and equipment operation records, including information on the building's structure, fire-fighting equipment, fire passages and fire alarm systems; the collected data is analyzed to evaluate the fire safety status of buildings and facilities, including the number and performance of fire-fighting equipment, the smoothness of fire passages and the fire resistance of the building's structure; an indicator system for evaluating fire safety levels is determined, including fire safety level classification standards and evaluation indicators; buildings and facilities are evaluated based on the determined evaluation indicators, and their fire safety levels are determined using quantitative evaluation methods; fire safety levels are adjusted and updated based on the use of buildings and facilities and environmental changes; and a fire safety level confirmation report is prepared based on the evaluation results, including the fire safety level of buildings and facilities, the evaluation basis, evaluation results and recommended improvement measures.

[0004] The above technical solutions mainly focus on the evaluation of static properties of buildings and facilities, such as building structure, fire equipment configuration, etc. However, buildings are in a dynamic state of use, and only the evaluation of static properties of buildings and facilities leads to incomplete evaluation data, which makes it difficult to accurately reflect the actual fire safety situation, thereby reducing the accuracy of building fire safety evaluation. Summary of the invention

[0005] The present application provides a fire safety intelligent assessment method, system, storage medium and program product for improving the accuracy of building fire safety assessment.

[0006] In the first aspect, the present application provides a fire safety intelligent assessment method, which constructs a benchmark safety capacity index of a building based on the static parameters of the building, and calculates a real-time safety load index based on the dynamic parameters of the building. The safety capacity index represents the inherent safety bearing capacity of the building, and the safety load index represents the real-time safety pressure of the building. The static parameters include building structure parameters and fire protection facility parameters, and the dynamic parameters include personnel density time series data, equipment operation status data, and environmental monitoring data. Calculate the occupancy ratio of the safety load index compared to the safety capacity index to obtain the safety capacity ratio. The larger the safety capacity ratio, the lower the current safety redundancy of the building. The safety buffer of the building is constructed based on the safety capacity ratio. The upper limit of the safety buffer is determined by the safety capacity index, and the lower limit is determined by the historical maximum safety load index. Establish elastic threshold bands within the safety buffer zone according to the safety capacity ratio; The normalized pressure index of the dynamic parameter is calculated according to the pressure index calculation function, and the normalized pressure index is projected onto the elastic threshold band to obtain the parameter evolution trajectory; The intersection of the parameter evolution trajectory and the elastic threshold band is determined as the safety critical point; According to the distribution characteristics and occurrence frequency of safety critical points, the safety resilience index of the building is calculated; The fire safety level assessment result of the building is determined according to the position of the safety resilience index in the preset safety level mapping set.

[0007] By adopting the above technical scheme, the benchmark safety capacity index and real-time safety load index of the building are established, the inherent safety bearing capacity and real-time safety pressure of the building are quantified, and a computable index is provided for evaluating the fire safety status of the building. The ratio of the two indicators is defined as the safety capacity ratio, which intuitively reflects the current safety redundancy of the building. The safety buffer zone of the building is constructed, the capacity ratio is limited to a reasonable range, and the elastic threshold band is established according to the change of the capacity ratio in the buffer zone, so as to realize the dynamic evaluation and early warning of the fire safety status of the building. The pressure index calculation function is introduced to quantitatively analyze the influence of personnel density, equipment operation and environmental factors on the safety of the building, and the normalized pressure index is obtained and projected onto the threshold band. The safety critical state of the building is judged by the relationship between the parameter trajectory and the threshold band. The safety resilience index of the building is calculated by comprehensively considering the distribution characteristics and occurrence frequency of the safety critical point and other multi-dimensional information, and mapped to the preset grade system, giving an intuitive fire safety grade evaluation result. This method characterizes the fire safety characteristics of the building from both static and dynamic perspectives, realizes a comprehensive evaluation of fire safety through quantitative indicators, threshold comparison, trajectory analysis and other technical means, and improves the accuracy of the fire safety evaluation of the building.

[0008] In conjunction with some embodiments of the first aspect, in some embodiments, constructing a baseline safety capacity index of a building according to static parameters of the building specifically includes: Establishing a multi-dimensional parameter space of a building, mapping the building structure parameters into a structure feature vector of a preset first number dimension, and mapping the fire protection facility parameters into a facility feature vector of a preset second number dimension; A fuzzy inference rule set is constructed based on the preset expert knowledge base, and the fuzzy inference rule set is used to perform fuzzy comprehensive evaluation on the structural feature vector and the facility feature vector to obtain the inherent safety bearing capacity score of the building; A nonlinear mapping function is constructed according to the inherent safety bearing capacity score, and the output value of the nonlinear mapping function is the benchmark safety capacity index of the building.

[0009] By adopting the above technical solution, static parameters are extracted from the two aspects of building structure and fire protection facilities, and mapped to the feature space of corresponding dimensions, thus achieving quantitative characterization of key factors affecting the inherent safety attributes of buildings. When constructing the benchmark safety capacity index, the fuzzy comprehensive evaluation mechanism of structural characteristic vectors and facility characteristic vectors is established by using the empirical rules in the preset expert knowledge base, which can objectively evaluate the inherent safety bearing capacity of the building and reduce the influence of subjective judgment. The comprehensive evaluation results are associated with the benchmark capacity index through a nonlinear mapping function, which gives the capacity index a clear physical meaning, improves the rationality of subsequent calculations and comparisons, and more comprehensively considers the correlation between the characteristic parameters, thereby improving the accuracy of the evaluation results.

[0010] In conjunction with some embodiments of the first aspect, in some embodiments, the pressure index calculation function is: In the function, P is the normalized pressure index, α, β and γ are weight coefficients, D is the time series data of personnel density, T is the equipment operation status data, and H is the environmental monitoring data. is the change rate of population density, is the device temperature change rate, is the rate of change of hazardous source concentration.

[0011] By adopting the above technical solution, the pressure index calculation function comprehensively considers the change rate of dynamic parameters such as personnel density, equipment operation and environmental monitoring, and reflects the contribution of different factors to the safety pressure of the building through the weight coefficient, which can quantitatively evaluate the real-time safety risks faced by the building.

[0012] In combination with some embodiments of the first aspect, in some embodiments, after calculating the occupancy rate of the safety load index compared to the safety capacity index to obtain the safety capacity ratio, the method further includes: Construct a time series capacity-to-load ratio sequence, and calculate the first-order difference and second-order difference of the capacity-to-load ratio according to the time series capacity-to-load ratio sequence; A load situation curve is obtained according to the first-order difference and the second-order difference, and a set of characteristic points are extracted on the load situation curve, wherein the characteristic points include local extreme value points, inflection points and jump points; A state transition graph is constructed based on a set of feature points, and topological characteristic parameters of the state transition graph are calculated. The topological characteristic parameters include node degree distribution, clustering coefficient and path length.

[0013] By adopting the above technical solution, after obtaining the capacity ratio that reflects the safety redundancy of the building, the time dimension is further introduced to construct the time series data of the capacity ratio for analysis. By calculating the first-order and second-order differences of the capacity ratio, a capacity situation curve that directly reflects the change speed and change trend of the capacity ratio is obtained, making the dynamic evolution of the building's safety status more intuitive. Feature points such as local extreme points, inflection points and jump points are extracted on the situation curve to depict the key turning points in the process of capacity ratio changes, making the safety status transfer of the building clearer and providing more comprehensive data information for safety management.

[0014] In conjunction with some embodiments of the first aspect, in some embodiments, constructing a state transition diagram based on a feature point set specifically includes: Establish a feature point space coordinate system, the horizontal coordinate of which represents the time position of the local extreme point, inflection point and jump point, and the vertical coordinate represents the change trend of the load situation curve; The local extreme value points are marked with a preset first shape, the inflection points are marked with a preset second shape, and the jump points are marked with a preset third shape; the preset first shape, the preset second shape, and the preset third shape are sequentially connected in chronological order to obtain a state transition diagram.

[0015] By adopting the above technical solution, using the time position as the horizontal coordinate, not only the order of local extreme points, inflection points, and jump points in the time dimension is characterized, but also the time interval characteristics between feature points are analyzed. Using the change trend of the capacity situation as the vertical coordinate, the change direction and magnitude of the capacity situation when the feature point appears are intuitively shown, making the dynamic evolution of the capacity ratio clearer. Different shapes are used to distinguish different types of feature points, and they are connected in chronological order, which more intuitively shows the structural changes in the fire safety status of the building over time.

[0016] In conjunction with some embodiments of the first aspect, in some embodiments, before calculating the topological characteristic parameters of the state transition diagram, the method further includes: Establish a state transition intensity matrix, the rows and columns of which correspond to local extreme points, inflection points and jump points respectively, and the matrix element values ​​represent the state transition frequency between the corresponding feature points; A Markov chain model is constructed based on the state transition intensity matrix to calculate the steady-state transition probability distribution between each feature point; the number of times each feature point participates in the state transition as the starting point and the end point is counted to obtain the state transition activity of the feature point; Based on the steady-state transition probability distribution and the state transition activity, the state transition graph is optimized and reconstructed to obtain an updated state transition graph.

[0017] By adopting the above technical solution, the state transition intensity matrix is ​​introduced to quantitatively describe the transfer frequency between feature points, and the Markov chain model is used to solve the steady-state transfer probability distribution, which characterizes the state distribution characteristics of the building after the long-term evolution reaches equilibrium, and reveals the inherent law of the transfer between states. The state transfer activity is obtained by counting the frequency of feature points participating in the transfer, which characterizes the importance of each feature point in the state transfer process. The steady-state transfer probability distribution is combined with the state transfer activity to optimize and reconstruct the state transfer diagram, highlighting the key state nodes and core transfer paths that play a leading role, making the state transfer relationship clearer and more compact, and achieving a more accurate and efficient evaluation of the evolution law of the building's fire safety state.

[0018] In combination with some embodiments of the first aspect, in some embodiments, based on the steady-state transition probability distribution and the state transition activity, the state transition diagram is optimized and reconstructed to obtain an updated state transition diagram, specifically including: Using steady-state transition probability distribution and state transition activity to identify key state nodes, the state transition activity of the key state node exceeds a preset first threshold, and the transition probability with the adjacent feature point exceeds a preset second threshold; Determine a dominant transfer path according to the transfer probability between key state nodes, where the dominant transfer path satisfies that the transfer probability between adjacent key state nodes on the path is greater than a preset third threshold, and the cumulative transfer probability is the maximum value among all paths; The state transition graph is reconstructed with the dominant transfer path as the trunk path and other transfer paths as branches to obtain an updated state transition graph.

[0019] By adopting the above technical solution, in the identification stage, by setting the judgment conditions of key state nodes, the activity of the node itself and the transfer probability with adjacent nodes are considered at the same time, and the key nodes are screened from the two perspectives of node importance and node connection strength, which improves the comprehensiveness of the identification results. The state transition graph is reconstructed in a trunk-branch manner, which simplifies the topological structure of the graph and highlights the transfer context with the dominant path as the core, so that users can quickly grasp the key evolution mode of the building's fire safety status. At the same time, the retention of branch paths also avoids the loss of important information, reserves space for in-depth analysis of local state fluctuations, and improves the effectiveness and practicality of safety assessment.

[0020] In the second aspect, an embodiment of the present application provides a fire safety intelligent assessment system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and one or more processors call the computer instructions to enable the system to execute the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions, which, when executed on a system, causes the system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer program product, characterized in that when the computer program product runs on a system, the system executes the method described in any possible implementation manner in the first aspect.

[0023] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. This application provides a fire safety intelligent assessment method, establishes a baseline safety capacity index and a real-time safety load index for a building, quantifies the inherent safety bearing capacity and real-time safety pressure of the building, and provides a computable indicator for assessing the fire safety status of the building. The ratio of the two indicators is defined as the safety capacity ratio, which intuitively reflects the current safety redundancy of the building. A safety buffer zone is constructed for the building, the capacity ratio is limited to a reasonable range, and an elastic threshold band is established according to the change of the capacity ratio in the buffer zone, so as to realize the dynamic assessment and early warning of the fire safety status of the building. The pressure index calculation function is introduced to quantitatively analyze the impact of personnel density, equipment operation and environmental factors on the safety of the building, and the normalized pressure index is obtained and projected onto the threshold band. The critical safety state of the building is judged by the relationship between the parameter trajectory and the threshold band. Taking into account the distribution characteristics and frequency of occurrence of the critical safety points and other multi-dimensional information, the safety resilience index of the building is calculated and mapped to the preset grade system to give an intuitive fire safety grade assessment result. This method characterizes the fire safety characteristics of buildings from both static and dynamic perspectives, and achieves a comprehensive assessment of fire safety through a variety of technical means such as quantitative indicators, threshold comparison, and trajectory analysis, thereby improving the accuracy of fire safety assessments on buildings.

[0024] 2. This application provides a fire safety intelligent assessment method. After obtaining the capacity ratio that reflects the safety redundancy of the building, the time dimension is further introduced to construct the capacity ratio time series data for analysis. By calculating the first-order and second-order differences of the capacity ratio, a capacity situation curve that directly reflects the change speed and change trend of the capacity ratio is obtained, making the dynamic evolution of the building's safety status more intuitive. Feature points such as local extreme points, inflection points, and jump points are extracted from the situation curve to characterize the key turning points in the process of capacity ratio changes, making the building's safety status transition clearer and providing more comprehensive data information for safety management.

[0025] 3. This application provides a fire safety intelligent assessment method, which introduces a state transition intensity matrix to quantitatively describe the frequency of transitions between feature points, uses a Markov chain model to solve the steady-state transition probability distribution, characterizes the state distribution characteristics of the building after the long-term evolution reaches equilibrium, and reveals the inherent laws of transitions between states. The state transition activity is obtained by counting the frequency of feature points participating in the transition, which characterizes the importance of each feature point in the state transition process. The steady-state transition probability distribution is combined with the state transition activity to optimize and reconstruct the state transition diagram, highlighting the key state nodes and core transfer paths that play a leading role, making the state transition relationship clearer and more compact, and achieving a more accurate and efficient assessment of the evolution law of the building's fire safety state. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 It is a flow chart of a fire safety intelligent assessment method in an embodiment of the present application.

[0027] Figure 2 It is another flow chart of a fire safety intelligent assessment method in an embodiment of the present application.

[0028] Figure 3 It is a schematic diagram of the physical device structure of a fire safety intelligent assessment system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification and appended claims of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more listed items.

[0030] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0031] The following uses an embodiment and combines Figure 1 , a fire safety intelligent assessment method in an embodiment of the present application is described: See also Figure 1 , which is a flow chart of a fire safety intelligent assessment method in an embodiment of the present application.

[0032] S101, constructing a benchmark safety capacity index of a building according to static parameters of the building, and calculating a real-time safety load index based on dynamic parameters of the building; The system constructs a benchmark safety capacity index of the building based on the static parameters of the building. Specifically: a multi-dimensional parameter space of the building is established, and the building structure parameters are mapped into a structure feature vector of a preset first quantity dimension, and the fire protection facility parameters are mapped into a facility feature vector of a preset second quantity dimension; a fuzzy reasoning rule set is constructed based on a preset expert knowledge base, and the fuzzy reasoning rule set is used to perform a fuzzy comprehensive evaluation on the structure feature vector and the facility feature vector to obtain the inherent safety bearing capacity score of the building; a nonlinear mapping function is constructed based on the inherent safety bearing capacity score, and the output value of the nonlinear mapping function is the benchmark safety capacity index of the building.

[0033] Likewise, the system calculates real-time safe load indicators based on the dynamic parameters of the building.

[0034] Among them, the safety capacity index represents the inherent safety bearing capacity of the building, the safety load index represents the real-time safety pressure of the building, the static parameters include building structure parameters and fire-fighting facility parameters, and the dynamic parameters include personnel density time series data, equipment operation status data and environmental monitoring data.

[0035] This step evaluates the inherent safety bearing capacity and real-time safety pressure of the building through the static and dynamic parameters of the building. Static parameters include building structure parameters and fire protection facility parameters, which reflect the safety characteristics of the building itself; dynamic parameters include personnel density time series data, equipment operation status data and environmental monitoring data, which reflect the real-time safety status of the building.

[0036] To construct the baseline safety capacity index, the system can establish a multi-dimensional parameter space of the building, map the building structure parameters into the structure feature vector, and map the fire protection facility parameters into the facility feature vector. Then, the system can build a fuzzy reasoning rule set based on the expert knowledge base, and use fuzzy reasoning to comprehensively judge the structure feature vector and the facility feature vector to obtain the inherent safety bearing capacity score. Finally, the system constructs a nonlinear mapping function based on the score and outputs the baseline safety capacity index of the building. Similarly, the system can also calculate the real-time safety load index based on dynamic parameters.

[0037] In this step, the system can also consider dividing the building into regions and evaluating the safety capacity index and safety load index for different regions to improve the precision of the evaluation. In addition, when constructing the fuzzy inference rule set, the system can introduce machine learning methods to optimize the rule set through historical data training to improve the accuracy and adaptability of the evaluation.

[0038] S102, calculating the occupancy rate of the safety load index compared to the safety capacity index to obtain a safety capacity ratio; The system calculates the occupancy rate of the safety load index compared to the safety capacity index to obtain the safety capacity ratio. The larger the safety capacity ratio, the lower the current safety redundancy of the building.

[0039] This step calculates the occupancy rate of the safety load index compared to the safety capacity index to obtain the safety capacity ratio that reflects the current safety redundancy of the building. The larger the safety capacity ratio, the lower the safety redundancy of the building and the higher the safety risk.

[0040] The system can directly calculate the safety load ratio by dividing the safety load index by the safety capacity index. In order to more accurately reflect the degree of safety redundancy, the system can also introduce a nonlinear calculation method for the safety load ratio, such as considering the weights of different parameters, or setting upper and lower limits for the safety load ratio.

[0041] S103. Construct a safe buffer zone of the building based on the safe capacity ratio; The system constructs a safety buffer zone for the building based on the safety capacity ratio. The upper limit of the safety buffer zone is determined by the safety capacity index, and the lower limit is determined by the historical maximum safety load index.

[0042] After obtaining the safety capacity ratio, the system further constructs the safety buffer zone of the building. The safety buffer zone reflects the range of changes and adjustment capabilities of the building's safety status. Its upper limit is determined by the benchmark safety capacity index, indicating the maximum safety load capacity of the building; the lower limit is determined by the historical maximum safety load index, indicating the highest safety load level that the building has ever experienced in the past period of time. The size of the safety buffer zone reflects the building's buffering capacity to cope with safety pressure fluctuations. The larger the interval, the stronger the building's safety resilience.

[0043] When constructing a safety buffer zone, the system can use a sliding time window method to dynamically update the upper and lower limits of the interval. For example, the system can set a fixed-length time window, only consider historical data within the window, and adjust the safety buffer zone in real time according to the changes in the data to adapt to the dynamic changes in the building's safety status. In addition, the system can also introduce an adaptive threshold mechanism to set different safety capacity ratio thresholds based on the importance level and risk preference of the building. When the actual safety capacity ratio exceeds the threshold, early warning and adjustment measures are triggered in a timely manner.

[0044] S104, establishing an elastic threshold band within the safety buffer zone according to the safety capacity ratio; After determining the safe buffer zone of the building, the system further establishes an elastic threshold zone within the zone. The elastic threshold zone divides the safe buffer zone into multiple sub-zones, each of which corresponds to a different safety risk level and adjustment strategy. When the safe load ratio falls within different sub-zones, the system will take corresponding measures to maintain the safe state of the building. The setting of the elastic threshold zone reflects the dynamic and flexibility of building safety management, and can be adaptively adjusted according to actual conditions.

[0045] In the process of establishing elastic threshold zones, the system can comprehensively consider multiple factors, such as the structural characteristics, usage functions, and population density of buildings, and adopt technical means such as layered settings and dynamic updates to improve the rationality and operability of threshold zones. For example, for densely populated public buildings, the system can set stricter threshold standards to strengthen safety monitoring and early warning; while for general residential buildings, the threshold requirements can be appropriately relaxed to reduce excessive intervention.

[0046] S105, calculating the normalized pressure index of the dynamic parameter according to the pressure index calculation function, and projecting the normalized pressure index onto the elastic threshold band to obtain a parameter evolution trajectory; The system calculates the normalized pressure index of the dynamic parameter according to the pressure index calculation function, and projects the normalized pressure index onto the elastic threshold band to obtain the parameter evolution trajectory, where the pressure index calculation function is: In the function, P is the normalized pressure index, α, β and γ are weight coefficients, D is the time series data of personnel density, T is the equipment operation status data, and H is the environmental monitoring data. is the change rate of population density, is the device temperature change rate, is the rate of change of hazardous source concentration.

[0047] In this step, the system first quantifies the changes in dynamic parameters (including personnel density, equipment operating status, environmental monitoring data, etc.) into a normalized pressure index according to the preset pressure index calculation function. The pressure index function adopts the form of weighted summation, comprehensively considers the change rate of different dynamic parameters, and reflects the importance of each parameter by setting the weight coefficient. The normalization process fixes the value range of the pressure index in the interval [0, 1], which is convenient for subsequent analysis and comparison.

[0048] After obtaining the normalized pressure index, the system projects it onto the elastic threshold band to form a parameter evolution trajectory that changes over time. The parameter evolution trajectory intuitively shows the changing trend of the building's safety pressure level over a period of time, and can reflect the dynamic characteristics of the building's safety status. By observing the relative position relationship between the parameter evolution trajectory and the elastic threshold band, the system can determine whether the building is in a safe state and whether corresponding adjustment measures need to be taken.

[0049] In the process of implementing this step, the system can use a variety of data processing and visualization technologies to improve the effect of pressure index calculation and trajectory display. For example, the system can introduce a data smoothing algorithm to remove noise and outliers from the original data of dynamic parameters to improve the stability of pressure index calculation; in terms of displaying parameter evolution trajectories, the system can use three-dimensional visualization technology to integrate information of multiple dimensions such as time, pressure index, threshold band, etc. into a three-dimensional visualization model to enhance the intuitiveness and interactivity of data analysis and decision support.

[0050] At the same time, this step may also cause some new technical problems. For example, in practical applications, there may be certain problems with the data quality and integrity of dynamic parameters, resulting in deviations or distortions in the pressure index calculation results. To address this problem, the system can establish a data quality assessment and repair mechanism, and improve the reliability and continuity of the data through technical means such as anomaly detection and data filling to ensure the accuracy of the pressure index calculation. In addition, the system can also introduce an incremental learning algorithm to adjust and optimize the weight coefficient of the pressure index function online based on new data samples, so that it can adapt to the long-term changing trend of the building's safety status.

[0051] S106, determining the intersection of the parameter evolution trajectory and the elastic threshold band as a safety critical point; After obtaining the parameter evolution trajectory, the system further determines the intersection of the trajectory and the elastic threshold band as the safety critical point. The safety critical point indicates the critical moment when the building's safety status undergoes a qualitative change, that is, the safety pressure level breaks through a certain threshold interval and enters a new safety risk level. By identifying and tracking the safety critical point, the system can promptly detect abnormal changes in the building's safety status and provide a basis for taking targeted adjustment measures.

[0052] S107. Calculate the building's safety resilience index based on the distribution characteristics and occurrence frequency of safety critical points; After identifying the critical points, the system calculates the building's safety resilience index based on the distribution characteristics and frequency of occurrence of the critical points. The safety resilience index is a comprehensive evaluation indicator that reflects the building's resistance and recovery capabilities when facing safety pressure shocks. Generally speaking, the more dispersed the distribution of critical points on the elastic threshold band and the lower the frequency of occurrence, the stronger the building's safety resilience is, and it can effectively respond to and absorb safety risks. On the contrary, if the critical points are too concentrated or appear frequently, it means that the building's safety redundancy is poor and it is extremely susceptible to safety incidents.

[0053] In the process of calculating the safety resilience index, the system can use a variety of quantitative analysis methods, such as statistical inference, time series analysis, etc., to evaluate the distribution pattern and evolution trend of critical points from multiple perspectives. At the same time, the system can also introduce a benchmark comparison mechanism to judge whether the safety status of the building is at a reasonable level by comparing it horizontally with the safety resilience index of buildings of the same type. In addition, the system can also establish a safety resilience assessment model, comprehensively consider the structural characteristics, usage functions, environmental factors and other aspects of the building, and revise and calibrate the safety resilience index to improve the pertinence and interpretability of the assessment results.

[0054] In practical applications, the identification of critical safety points and the calculation of the safety resilience index may face some technical challenges. For example, due to the complexity and dynamics of buildings, there may be certain uncertainties and ambiguities in the determination of critical safety points. To address this problem, the system can introduce uncertainty processing methods such as fuzzy logic and evidence theory, and quantify the uncertainty of critical points by establishing fuzzy membership functions and trust functions, thereby improving the reliability of identification results. In addition, the system can also use incremental learning and online updates to dynamically adjust the safety resilience index based on new safety event data, so that it can reflect the latest changes in the safety status of the building.

[0055] S108. Determine a fire safety level assessment result of the building according to the position of the safety resilience index in a preset safety level mapping set.

[0056] This step is the key to the final assessment of the building's fire safety level. The system first establishes a preset safety level mapping set to establish a correspondence between the safety resilience index values ​​in different intervals and the corresponding fire safety levels. For example, the safety resilience index can be divided into several level intervals (such as excellent, good, general, poor, extremely poor, etc.), and each interval corresponds to a specific fire safety level (such as level one, level two, level three, etc.). Then, the system maps the actual safety resilience index value of the building to the safety level mapping set, and determines the final fire safety level assessment result based on its interval position.

[0057] In the process of implementing this step, the system can comprehensively use a variety of knowledge representation and reasoning technologies to improve the intelligence level of safety level mapping and evaluation. For example, the system can use a rule-based expert system method to encode fire safety standards and empirical knowledge into a series of IF-THEN form of reasoning rules, and determine the safety level through rule matching and chain reasoning; in addition, the system can also introduce case reasoning technology, through similarity retrieval and comparative analysis of existing building safety assessment cases, and use empirical knowledge to assist in the determination of safety levels. At the same time, the system can also establish a safety level interpretation mechanism, generate an interpretable description of the safety level assessment results based on the specific components and influencing factors of the safety resilience index, and provide a reference for subsequent safety management decisions.

[0058] In the above embodiment, the benchmark safety capacity index and real-time safety load index of the building are established, the inherent safety bearing capacity and real-time safety pressure of the building are quantified, and a computable index is provided for evaluating the fire safety status of the building. The ratio of the two indicators is defined as the safety capacity ratio, which intuitively reflects the current safety redundancy of the building. A safety buffer zone of the building is constructed, the capacity ratio is limited to a reasonable range, and an elastic threshold band is established according to the change of the capacity ratio in the buffer zone, so as to realize the dynamic evaluation and early warning of the fire safety status of the building. The pressure index calculation function is introduced to quantitatively analyze the influence of personnel density, equipment operation and environmental factors on the safety of the building, and the normalized pressure index is obtained and projected onto the threshold band. The safety critical state of the building is judged by the relationship between the parameter trajectory and the threshold band. The safety resilience index of the building is calculated by comprehensively considering the distribution characteristics and occurrence frequency of the safety critical point and other multi-dimensional information, and is mapped to the preset grade system to give an intuitive fire safety grade evaluation result. This method describes the fire safety characteristics of the building from both static and dynamic perspectives, realizes a comprehensive evaluation of fire safety through quantitative indicators, threshold comparison, trajectory analysis and other technical means, and improves the accuracy of the fire safety evaluation of the building.

[0059] The above embodiment realizes dynamic evaluation of building fire safety status by establishing a baseline safety capacity index and a real-time safety load index, combining concepts such as safety capacity ratio and elastic threshold band. Figure 2 , another fire safety intelligence assessment method in the embodiment of the present application is described: See also Figure 2 , is another flow chart of a fire safety intelligent assessment method in an embodiment of the present application.

[0060] S201, constructing a time series capacity-to-load ratio sequence, and calculating the first-order difference and the second-order difference of the capacity-to-load ratio according to the time series capacity-to-load ratio sequence; In this step, the system first constructs a time series capacity ratio sequence in chronological order based on the safety capacity ratio data obtained in the previous step. This sequence reflects the dynamic change process of the building's safety status over a period of time. In order to further explore the inherent laws of the change of the safety status, the system calculates the first-order difference and second-order difference of the capacity ratio based on the time series capacity ratio sequence. The first-order difference represents the rate of change of the capacity ratio between two adjacent moments, reflecting the instantaneous change speed of the safety status; the second-order difference represents the rate of change of the first-order difference, reflecting the acceleration characteristics of the speed of change of the safety status. Through the calculation of the first-order difference and the second-order difference, the dynamic evolution trajectory of the building's safety status can be more carefully portrayed.

[0061] In the process of implementing this step, the system can use a variety of time series analysis techniques, such as moving average method, exponential smoothing method, etc., to pre-process the original capacity ratio data, remove random fluctuations and outliers, and improve the stability of first-order difference and second-order difference calculations. At the same time, in order to adapt to the changing characteristics of the safety status of different buildings, the system can introduce an adaptive time window mechanism to dynamically adjust the time scale of the difference calculation according to the stability and periodicity of the capacity ratio sequence, so as to capture the long-term trend of the safety status and reflect the local fluctuation details. In addition, the system can also use the recursive relationship of the difference order and use incremental calculation to improve the calculation efficiency and reduce the cost of data storage and transmission.

[0062] In practical applications, due to the frequency and accuracy limitations of data acquisition, the load-to-capacity ratio sequence may have certain discreteness and incompleteness, resulting in deviations or distortions in the calculation results of the first-order and second-order differences. To address this problem, the system can introduce interpolation and smoothing algorithms to improve the continuity and smoothness of the load-to-capacity ratio sequence by estimating missing data and filtering noise. At the same time, the system can also use mathematical tools such as generalized state space models to convert discrete load-to-capacity ratio sequences into continuous state variables, while ensuring calculation accuracy and enhancing the physical explanatory power of first-order and second-order differences.

[0063] S202, obtaining a capacity situation curve according to the first-order difference and the second-order difference, and extracting a set of characteristic points on the capacity situation curve; The system obtains the capacity situation curve according to the first-order difference and the second-order difference, and extracts a set of characteristic points on the capacity situation curve. The characteristic points include local extreme points, inflection points and jump points.

[0064] In this step, the system uses the first-order difference and second-order difference data calculated in the previous step to draw the load situation curve. The load situation curve is a two-dimensional plane curve. The horizontal axis represents time, and the vertical axis represents the change rate (first-order difference) and change acceleration (second-order difference) of the load ratio. By observing the shape characteristics of the load situation curve, the changing trend of the building's safety status in different periods can be intuitively judged, and the occurrence time and impact degree of safety incidents can be identified. On the basis of drawing the load situation curve, the system further extracts a set of characteristic points on the curve, mainly including local extreme points, inflection points and jump points. These characteristic points represent the key change positions of the load situation curve, corresponding to the sudden change moments and turning points of the building's safety status.

[0065] In the process of implementing this step, the system can comprehensively use a variety of numerical analysis and image processing technologies. For example, when drawing the capacity situation curve, the system can use the difference algorithm to calculate the interpolation points on the curve, and use smoothing techniques such as spline curves to fit the curve to improve the visual effect and numerical accuracy of the curve. When extracting feature points, the system can automatically detect local extreme points by setting threshold conditions for first-order differences and second-order differences; determine the location of the inflection point by analyzing the changes in the positive and negative signs of the first-order differences and second-order differences; and identify the time coordinates of the jump point by calculating the slope and curvature of the capacity situation curve. At the same time, in order to ensure the accuracy and robustness of feature point extraction, the system can also introduce pattern recognition and machine learning algorithms to automatically optimize the judgment rules and parameter settings of feature points through training and learning of a large amount of historical data.

[0066] S203, constructing a state transition diagram based on the feature point set; The system constructs a state transition diagram based on a set of feature points. Specifically: a feature point space coordinate system is established, the horizontal coordinate of the feature point space coordinate system represents the time position of local extreme points, inflection points and jump points, and the vertical coordinate represents the change trend of the load situation curve; local extreme points are marked with a preset first shape, inflection points are marked with a preset second shape, and jump points are marked with a preset third shape; the preset first shape, the preset second shape and the preset third shape are connected in chronological order to obtain a state transition diagram.

[0067] After extracting the characteristic point set of the capacity situation curve, the system further constructs a state transition diagram based on the characteristic point set. The state transition diagram is a directed graph model used to describe the transition relationship between different characteristic points of the building's safety status. The nodes in the graph represent characteristic points, and the types of nodes include local extreme points, inflection points, and jump points; the directed edges in the graph represent the transfer direction and strength between adjacent characteristic points, and the weight of the edge can be measured by the transfer frequency or transfer probability. Through the state transition diagram, the topological structure and dynamic mechanism of the evolution of the building's safety status can be vividly portrayed, providing support for causal analysis and predictive warning of the safety situation.

[0068] In the process of constructing the state transition diagram, the system first establishes a feature point reference system. The reference system consists of two coordinate axes: the horizontal axis represents the time position of the feature point on the capacity situation curve, and the vertical axis represents the capacity ratio change trend (increasing, decreasing or stable) corresponding to the feature point. In the reference system, the system uses geometric marks of different shapes to represent different types of feature points: for example, circular marks represent local maximum points, triangular marks represent local minimum points, diamond marks represent inflection points, and five-pointed star marks represent jump points. Then, the system connects these geometric marks in sequence according to the time sequence of the feature points to obtain a directed graph, which is the initial state transition diagram.

[0069] In the process of implementing this step, the system can make full use of the relevant theories and methods of graph theory and network science. For example, the system can use adjacency matrix or adjacency list to store the structural information of the state transition graph, use graph traversal algorithms such as depth-first search and breadth-first search to analyze the connectivity and accessibility of the graph, use Dijkstra algorithm, Floyd algorithm, etc. to solve the shortest path of the graph, and use PageRank, HITS and other algorithms to calculate the centrality and influence of nodes in the graph. At the same time, the system can also introduce complex network community discovery, central node identification and other technologies to explore the hierarchical module structure and key feature points of the state transition graph, and enhance the depth and breadth of security situation analysis.

[0070] S204, establishing a state transfer intensity matrix; The system establishes a state transition intensity matrix, the rows and columns of which correspond to local extreme points, inflection points and jump points respectively, and the matrix element values ​​represent the state transition frequency between the corresponding feature points.

[0071] On the basis of constructing the state transition diagram, the system further establishes the state transition strength matrix. The state transition strength matrix is ​​an N*N square matrix (N is the number of feature points). The rows and columns of the matrix correspond to the feature points in the state transition diagram, and the matrix element a_ij represents the strength of the transfer from feature point i to feature point j. The transfer strength can be measured by absolute frequency or relative probability: the absolute frequency represents the number of direct transfers between feature points i and j in historical data; the relative probability represents the proportion of the number of transfers from feature point i to j in all the transfers of i. The state transition strength matrix accurately describes the structural characteristics of the state transition diagram in numerical form, and is an important basis for conducting subsequent intelligent analysis of security situation.

[0072] In the process of establishing the state transition intensity matrix, the system needs to conduct in-depth statistical analysis of the state transition diagram. First, the system traverses all directed edges in the state transition diagram, counts the starting point, end point, and frequency of occurrence of each edge, and generates a list of triples. Then, the system scans the triple list and accumulates the frequency at the corresponding position of the state transition intensity matrix according to the number of the starting point and end point. After obtaining the frequency matrix, the system can also convert the frequency into transition probability through operations such as row normalization, so that the sum of the elements in each row of the matrix is ​​equal to 1. In this way, the state transition intensity matrix fully reflects the mutual transfer relationship between feature points from the perspective of frequency and probability.

[0073] S205, constructing a Markov chain model based on the state transition intensity matrix, and calculating the steady-state transition probability distribution between each feature point; After obtaining the state transition intensity matrix, the system constructs a Markov chain model based on the matrix, and then calculates the steady-state transition probability distribution between each feature point. Markov chain is a classic random process model, which assumes that the state at the next moment is only related to the state at the current moment, and has nothing to do with the past state. In this system, the state transition intensity matrix can be regarded as a transition probability matrix of a discrete-time, finite-state Markov chain. Through the Markov chain model, the system can predict the future evolution trend of the building's safety status, measure the importance of different feature points, and discover implicit safety risk factors.

[0074] The core step of building a Markov chain model is to solve the steady-state distribution vector of the state transition intensity matrix. The steady-state distribution represents the probability of each feature point appearing in the equilibrium state finally reached by the system after a long period of operation. The common method for calculating the steady-state distribution is the power method iteration: first select an initial probability vector, and then repeatedly multiply the state transition intensity matrix on the left until the vector converges to a fixed point. The converged vector is the steady-state distribution of the Markov chain, where each component π_i represents the probability that the system is at feature point i after a sufficiently long time starting from any state. Using the steady-state distribution, the system can quantitatively evaluate the long-term impact of each feature point on the entire safety state.

[0075] S206, counting the number of times each feature point participates in state transition as a starting point and an end point, and obtaining the state transition activity of the feature point; On the basis of the Markov chain model, the system further counts the frequency of each feature point as the starting point and end point of the transfer to obtain the state transfer activity of the feature point. Activity is an important indicator that reflects the centrality and influence of the feature point in the state transfer diagram. Specifically, the starting point activity a_i of feature point i is defined as the sum of the frequencies of all transfers starting from i, and the end point activity b_i is defined as the sum of the frequencies of all transfers with i as the end point. The starting point activity reflects the ability of the feature point to trigger state transfer, and the end point activity reflects the ability of the feature point to converge state transfer. The ratio of the two, a_i / b_i, reflects the net outflow effect of the feature point in the transfer process. The activity index measures the importance of feature points from the perspective of frequency, which is an important supplement to the steady-state transfer probability.

[0076] As the data scale increases, the performance overhead of activity calculation will also increase significantly. To this end, the system can adopt an incremental update strategy, that is, whenever new transfer data is added, only the activity of the feature points directly related to the transfer is updated without rescanning the entire intensity matrix. This local update method can greatly reduce the computational complexity. For massive state transition graphs, the system can also use technical means such as graph databases and parallel graph computing frameworks to achieve efficient storage, retrieval and calculation of activity analysis. At the same time, in the face of the skewness of the activity distribution, the system can perform pre-processing operations such as normalization and logarithmic transformation on the activity vector to improve the effect of subsequent statistical analysis and pattern mining.

[0077] S207, optimizing and reconstructing the state transition graph based on the steady-state transition probability distribution and the state transition activity to obtain an updated state transition graph; After calculating the steady-state transition probability distribution and state transition activity of the feature points, the system further optimizes and reconstructs the state transition graph based on these two indicators. The reconstruction of the graph mainly includes two tasks: one is to adjust the topological structure of the graph, remove redundant or noisy connections, and highlight the main transfer paths; the other is to update the edge weights of the graph so that it can comprehensively reflect the joint influence of probability distribution and activity. The reconstructed state transition graph can express the evolution law of the building's safety status in a more concise and accurate form, providing a more targeted reference for subsequent safety situation analysis and early warning decisions.

[0078] In the process of implementing this step, the system can use a variety of classic graph optimization algorithms and strategies. In terms of topological structure optimization, the system can set probability thresholds and activity thresholds to prune edges with probabilities or activities less than the thresholds; it can also use algorithms such as maximum spanning trees and skeleton extraction to retain the backbone structure of the graph and remove edges with smaller weights; when updating edge weights, the system can define a weighted combination of transition probability and activity, such as the geometric mean or harmonic mean, or map the two to the same scale and add them together as a combined weight. To avoid information loss, the system can also try to divide the original graph into several subgraphs with higher density based on algorithms such as hierarchical clustering and spectral clustering, and then perform edge pruning and weight adjustment within the subgraphs.

[0079] S208. Calculate the topological characteristic parameters of the state transition graph.

[0080] The system uses the updated state transition graph obtained in step S207 to calculate its topological characteristic parameters, which include node degree distribution, clustering coefficient and path length.

[0081] After obtaining the optimized and reconstructed state transition graph, the system finally calculates a series of topological characteristic parameters of the graph. Topological characteristic parameters are quantitative characterizations of the graph structure, which can reveal the organizational patterns and evolutionary characteristics of the graph at different scales. In this system, the topological characteristic parameters that are focused on include: node degree distribution, average path length, clustering coefficient, etc. Node degree distribution reflects the distribution law of the number of node connections in the graph, and intuitively reflects the heterogeneity of transfer behavior; the average path length measures the average shortest distance between any two points in the graph, and describes the speed and efficiency of the transition between states; the clustering coefficient measures the clustering tendency of nodes in the graph, and reflects the stability of the local state group. By systematically analyzing these topological parameters, we can gain insight into the vulnerability and key influencing factors of buildings under different safety states, and guide the formulation of targeted safety protection measures.

[0082] In the above embodiment, after obtaining the capacity ratio that reflects the safety redundancy of the building, the time dimension is further introduced to construct the time series data of the capacity ratio for analysis. By calculating the first-order and second-order differences of the capacity ratio, a capacity situation curve that directly reflects the change speed and change trend of the capacity ratio is obtained, making the dynamic evolution of the building's safety status more intuitive. Feature points such as local extreme points, inflection points and jump points are extracted from the situation curve to depict the key turning points in the process of capacity ratio change, making the safety status transfer of the building clearer and providing more comprehensive data information for safety management.

[0083] The following describes the system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the physical device structure of a fire safety intelligent assessment system provided in an embodiment of the present application.

[0084] It should be noted that Figure 3 The structure of the system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0085] like Figure 3 As shown, the system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through a bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0086] The following components are connected to the I / O interface 305: an input section 306 including a camera, an infrared sensor, etc.; an output section 307 including a liquid crystal display (LCD) and a speaker, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0087] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 309, and / or installed from a removable medium 311. When the computer program is executed by a central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0088] It should be noted that the computer-readable medium shown in the embodiment of the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.

[0089] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Among them, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0090] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the system described in the above embodiment; or may exist independently without being assembled into the system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of a system, the system implements the method provided in the above embodiment.

[0091] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0092] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0093] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media integration. The available medium can be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk), etc.

[0094] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A fire safety intelligence assessment method, characterized in that: include: A benchmark safety capacity index of the building is constructed according to the static parameters of the building, and a real-time safety load index is calculated based on the dynamic parameters of the building, wherein the safety capacity index represents the inherent safety bearing capacity of the building, and the safety load index represents the real-time safety pressure of the building, wherein the static parameters include building structure parameters and fire protection facility parameters, and the dynamic parameters include personnel density time series data, equipment operation status data, and environmental monitoring data; Calculate the occupancy rate of the safety load index compared to the safety capacity index to obtain a safety capacity ratio, wherein a larger safety capacity ratio indicates a lower current safety redundancy level of the building; Constructing a safety buffer zone of the building based on the safety capacity ratio, wherein the upper limit of the safety buffer zone is determined by the safety capacity index, and the lower limit is determined by the historical maximum safety load index; Establishing an elastic threshold band within the safety buffer zone according to the safety capacity ratio; Calculating the normalized pressure index of the dynamic parameter according to the pressure index calculation function, and projecting the normalized pressure index onto the elastic threshold band to obtain a parameter evolution trajectory; Determine the intersection of the parameter evolution trajectory and the elastic threshold band as a safety critical point; Calculating the safety resilience index of the building according to the distribution characteristics and occurrence frequency of the safety critical points; The fire safety level assessment result of the building is determined according to the position of the safety resilience index in the preset safety level mapping set.

2. The method according to claim 1, characterized in that The step of constructing the benchmark safety capacity index of the building according to the static parameters of the building specifically includes: Establishing a multidimensional parameter space of the building, mapping the building structure parameters into a structure feature vector of a preset first number dimension, and mapping the firefighting facility parameters into a facility feature vector of a preset second number dimension; Constructing a fuzzy inference rule set based on a preset expert knowledge base, and using the fuzzy inference rule set to perform fuzzy comprehensive evaluation on the structural feature vector and the facility feature vector to obtain an inherent safety bearing capacity score of the building; A nonlinear mapping function is constructed according to the inherent safety bearing capacity score, and an output value of the nonlinear mapping function is a benchmark safety capacity index of the building.

3. The method according to claim 1, characterized in that The pressure index calculation function is: In the function, P is the normalized pressure index, α, β and γ are weight coefficients, D is the personnel density time series data, T is the equipment operation status data, H is the environmental monitoring data, is the change rate of personnel density, is the device temperature change rate, is the rate of change of hazardous source concentration.

4. The method according to claim 1, characterized in that: After calculating the occupancy rate of the safety load index compared to the safety capacity index to obtain the safety capacity ratio, the method further includes: Constructing a time series capacity-to-load ratio sequence, and calculating the first-order difference and the second-order difference of the capacity-to-load ratio according to the time series capacity-to-load ratio sequence; obtaining a capacity-to-load situation curve according to the first-order difference and the second-order difference, and extracting a set of characteristic points on the capacity-to-load situation curve, wherein the characteristic points include local extreme value points, inflection points, and jump points; A state transition graph is constructed based on the feature point set, and topological feature parameters of the state transition graph are calculated. The topological feature parameters include node degree distribution, clustering coefficient and path length.

5. The method according to claim 4, characterized in that The constructing of the state transition diagram based on the feature point set specifically includes: Establishing a feature point spatial coordinate system, wherein the horizontal coordinate of the feature point spatial coordinate system represents the time position of the local extreme point, the inflection point and the jump point, and the vertical coordinate represents the change trend of the capacity situation curve; Marking the local extreme point with a preset first shape, marking the inflection point with a preset second shape, and marking the jump point with a preset third shape; The preset first shape, the preset second shape and the preset third shape are connected in chronological order to obtain a state transition diagram.

6. The method according to claim 4, characterized in that Before calculating the topological characteristic parameters of the state transition diagram, the method further includes: Establishing a state transition intensity matrix, wherein the rows and columns of the state transition intensity matrix correspond to the local extreme value points, the inflection points and the jump points respectively, and the matrix element values ​​represent the state transition frequencies between the corresponding feature points; Constructing a Markov chain model based on the state transition intensity matrix, and calculating the steady-state transition probability distribution between each of the feature points; Counting the number of times each of the feature points participates in state transition as a starting point and an end point, and obtaining the state transition activity of the feature point; Based on the steady-state transition probability distribution and the state transition activity, the state transition diagram is optimized and reconstructed to obtain an updated state transition diagram.

7. The method according to claim 6, characterized in that The optimizing and reconstructing the state transition diagram based on the steady-state transition probability distribution and the state transition activity to obtain an updated state transition diagram specifically includes: Identify a key state node using the steady-state transition probability distribution and the state transition activity, wherein the state transition activity of the key state node exceeds a preset first threshold, and the transition probability with an adjacent feature point exceeds a preset second threshold; A dominant transfer path is determined according to the transfer probability between the key state nodes, and the dominant transfer path satisfies that the transfer probability between adjacent key state nodes on the path is greater than a preset third threshold, and the cumulative transfer probability is the maximum value among all paths; the state transition diagram is reconstructed with the dominant transfer path as the trunk path and other transfer paths as branches to obtain an updated state transition diagram.

8. A fire safety intelligent assessment system, characterized in that: The system comprises: One or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a system, the system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a system, the system is caused to execute the method according to any one of claims 1 to 7.

Images