Intelligent building fire prevention and control management system and method

Abstract

The invention discloses an intelligent building fire protection management system and method, and particularly relates to the technical field of building fire protection. A building fire prevention system is divided into a plurality of monitoring links, delay accumulation of each monitoring link in different time periods is collected, a server calculates load and network congestion fluctuation data, the weight of delay accumulation data of each monitoring link is determined, and an overall delay accumulation interference index is calculated; according to an index result, the delay condition is divided into a high level, a middle level and a low level, corresponding management measures are taken for different levels, for the high delay level, the timeliness of fire detection and alarm notification links is preferentially guaranteed, and for the middle delay level, load and bandwidth resources are dynamically adjusted and calculated through analysis. The response speed and safety of the building fire prevention system at the initial stage of a fire disaster are improved, and the risk that people stay in a high-rise or closed space is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of building fire prevention, and particularly to an intelligent building fire prevention and fire fighting management system and method. Background Art

[0002] Intelligent building fire prevention and fire fighting management refers to a systematic method of using modern intelligent technologies to monitor, manage, and control the fire safety inside buildings in real time. By deploying various sensors, monitoring devices, and intelligent management platforms, such a system can achieve early detection of fire hazards, automatic alarm, intelligent linkage of fire fighting equipment, and data analysis. Its purpose is to improve the efficiency and accuracy of fire prevention and control, minimize the losses caused by fires, and ensure the safety of personnel.

[0003] In an intelligent building fire prevention management system, technologies such as the Internet of Things (IoT), big data analysis, and artificial intelligence (AI) are applied to monitor and evaluate various parameters of the fire fighting system, such as temperature, smoke concentration, flame recognition, etc. When the system detects an abnormal situation, it will trigger an early warning mechanism, automatically notify relevant personnel or the fire department, and at the same time link relevant fire fighting facilities, such as sprinkler devices, smoke exhaust systems, and evacuation indicator lights, to achieve an automated fire emergency response.

[0004] The existing technologies have the following deficiencies:

[0005] Since the building fire prevention system usually involves multi-level feedback and instruction transmission processes, abnormal data from sensors need to be first analyzed and classified by the processor, and then trigger early warning and linkage actions. Any delay at any level in the building fire prevention system (such as excessive server computing load, network data congestion) will cause delay accumulation and form feedback delay. In this case, when the system detects a fire, the triggered linkage devices and notification system start late, and relevant personnel and the fire department may not receive the alarm in time. At the same time, due to the lack of real-time performance of the building fire prevention system, the alarm signal may reach the evacuation system and the fire department late, making it impossible for personnel evacuation to start in time at the initial stage of the fire. People in the building, especially those in high-rise or enclosed spaces, may not receive the alarm and evacuation guidance within the delay time and are at risk of being trapped by thick smoke and flames. Summary of the Invention

[0006] The purpose of the present invention is to provide an intelligent building fire prevention and fire fighting management system and method to solve the deficiencies in the background art.

[0007] To achieve the above purpose, the present invention provides the following technical solution: An intelligent building fire prevention and fire fighting management method, including the following steps:

[0008] S1: Divide the building fire protection system into several monitoring links, and collect the server computing load data and network data congestion fluctuation state data of each monitoring link in different time periods;

[0009] S2: Determine the weight assignment of the delay accumulation data of each monitoring link in different time periods according to the obtained server computing load data and network data congestion fluctuation state data, and perform weighted average calculation on the weight assignment of the delay accumulation data of each monitoring link in different time periods to obtain the overall delay accumulation interference index of the building fire protection system;

[0010] S3: Compare and analyze the overall delay accumulation interference index of the calculated building fire protection system with the gradient delay threshold set according to the pre-obtained historical data, and divide the delay accumulation interference situation of the building fire protection system into different levels according to the analysis results;

[0011] S4: Further analyze the delay accumulation interference situation of the building fire protection system within a fixed time period, and dynamically adjust the allocation of the computing load of the building fire protection system and the use of bandwidth resources according to the analysis results.

[0012] Preferably, in S2, after analyzing the saturation situation of the memory usage rate in the obtained server computing load data, generate a memory usage rate saturation anomaly index. The method for obtaining the memory usage rate saturation anomaly index is as follows:

[0013] Collect and define the historical data of the memory usage rate, and construct a first time series data set , where represents the memory usage rate at the nth time point. Use the first time series data set D to train the model, and set the memory usage rate to conform to the normal distribution , that is: ; where: is the mean value of the memory usage rate under normal conditions, is the variance of the memory usage rate under normal conditions; according to the historical distribution of the memory usage rate, set the prior probability P(normal); , representing the prior probability of the abnormal state. For the memory usage rate x at the current time point, calculate the probability under normal conditions and the probability under abnormal conditions. Set the memory usage rate in the abnormal state to a uniform distribution U(a,b), and the calculation expression is: ; where [a,b] is the memory usage rate interval in the abnormal situation. Calculate the posterior probability according to Bayes' theorem, and the expression is: ; where, represents the normal probability weight when the memory usage rate is x, It represents the abnormal probability weight when the memory usage rate is x. LK is the posterior probability, and the posterior probability is used as the memory usage saturation abnormal index.

[0014] Preferably, in S2, after analyzing the fluctuation of the network bandwidth occupancy data in the obtained network data congestion fluctuation state data, a network bandwidth occupancy fluctuation index is generated. The method for obtaining the network bandwidth occupancy fluctuation index is as follows:

[0015] Collect the network bandwidth occupancy data within the W time period to form a second time series data set , where represents the network bandwidth occupancy data at time m. Based on the characteristics of the time series, the autoregressive order p, the differencing order d, and the moving average order q are selected. The network bandwidth occupancy data is input into the ARIMA(p,d,q) model and trained. The model formula is: ; where: is the actual network bandwidth occupancy data at time t, is the autoregressive coefficient, is the moving average coefficient, is the random error term at time t. The model parameters ϕ and θ are solved by the maximum likelihood estimation method to obtain the fitted ARIMA model;

[0016] Using the fitted ARIMA model, predict the predicted network bandwidth occupancy data for the current time period t The prediction is expressed as: ; In the formula, represents time 's random error term. Compare the predicted value with the actual observed value and calculate the residual: ; The residual reflects the deviation between the current network bandwidth occupancy data and the predicted value. Standardize the residual to calculate the network bandwidth occupancy fluctuation index, that is, calculate the absolute value of the standardized residual.

[0017] Preferably, in S2, the memory usage saturation anomaly index and the network bandwidth occupancy fluctuation index are converted into a comprehensive feature vector, and the comprehensive feature vector is used as the input of the machine learning model. The machine learning model takes the weight assignment label of the delay cumulative data of each monitoring link in different time periods predicted by each group of comprehensive feature vectors as the prediction target, and takes minimizing the sum of the prediction errors of the weight assignment labels of the delay cumulative data of each monitoring link in all different time periods as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence and then the model training is stopped. The weight assignment of the delay cumulative data of each monitoring link in different time periods is determined according to the model output result. Among them, the machine learning model is a polynomial regression model, and the overall delay cumulative interference index of the building fire protection system is obtained after weighted average calculation of the weight assignments of the delay cumulative data of each monitoring link in different time periods.

[0018] Preferably, in S3, the overall delay cumulative interference index of the building fire protection system calculated is compared and analyzed with the gradient delay threshold set according to the previously obtained historical data. Specifically:

[0019] The overall delay cumulative interference index of the obtained building fire protection system is compared with the gradient delay threshold. The gradient delay threshold includes a first delay threshold and a second delay threshold, and the first delay threshold is less than the second delay threshold. The overall delay cumulative interference index of the building fire protection system is compared with the first delay threshold and the second delay threshold respectively;

[0020] If the overall delay cumulative interference index of the building fire protection system is greater than the second delay threshold, it indicates that the overall delay cumulative interference degree of the building fire protection system is high, and the delay cumulative interference situation of the building fire protection system is classified as a high delay cumulative interference level; if the overall delay cumulative interference index of the building fire protection system is greater than or equal to the first delay threshold and less than or equal to the second delay threshold, it indicates that the overall delay cumulative interference degree of the building fire protection system is at a medium level, and the delay cumulative interference situation of the building fire protection system is classified as a medium delay cumulative interference level; if the overall delay cumulative interference index of the building fire protection system is less than the first delay threshold, it indicates that the overall delay cumulative interference degree of the building fire protection system is low, and the delay cumulative interference situation of the building fire protection system is classified as a low delay cumulative interference level.

[0021] Preferably, in S4, for the medium-delay cumulative interference level, that is, the overall delay cumulative interference index of the building fire protection system generated within a fixed time period is greater than or equal to the first delay threshold and less than or equal to the second delay threshold, collect the overall delay cumulative interference index of the building fire protection system generated within the subsequent fixed time period that is greater than or equal to the first delay threshold and less than or equal to the second delay threshold, and establish a corresponding data set, calculate the mean and standard deviation of the data set, analyze the abnormal degree of the overall delay cumulative interference of the building fire protection system within the fixed time period, and dynamically adjust the allocation of the calculation load and the use of bandwidth resources of the building fire protection system according to the analysis results.

[0022] Preferably, if the mean of the overall delay cumulative interference index in the data set is greater than or equal to the reference threshold of the mean of the overall delay cumulative interference index, and the standard deviation of the overall delay cumulative interference index is less than the reference threshold of the standard deviation of the overall delay cumulative interference index, it indicates that the delay cumulative abnormal situation is stable and continuous, with small fluctuations. At this time, generate a secondary warning signal, and it is necessary to optimize the current calculation load allocation and bandwidth resource configuration, concentrate on improving resources, and focus on alleviating the bottleneck part;

[0023] If the mean of the overall delay cumulative interference index is greater than or equal to the reference threshold of the mean of the overall delay cumulative interference index, and the standard deviation of the overall delay cumulative interference index is greater than or equal to the reference threshold of the standard deviation of the overall delay cumulative interference index, it indicates that the delay cumulative abnormal situation is unstable and has large fluctuations. At this time, generate a primary warning signal and introduce a load balancing mechanism and dynamic bandwidth management;

[0024] If the mean of the overall delay cumulative interference index is less than the reference threshold of the mean of the overall delay cumulative interference index, and the standard deviation of the overall delay cumulative interference index is greater than or equal to the reference threshold of the standard deviation of the overall delay cumulative interference index, it indicates that the delay cumulative abnormal situation has large fluctuations, but generally the abnormality is light. At this time, generate a tertiary warning signal, monitor the load change, automatically allocate more bandwidth resources when the load is high, and maintain overall monitoring to avoid further exacerbation of delay fluctuations;

[0025] If the mean of the overall delay cumulative interference index is less than the reference threshold of the mean of the overall delay cumulative interference index, and the standard deviation of the overall delay cumulative interference index is less than the reference threshold of the standard deviation of the overall delay cumulative interference index, it indicates that the delay cumulative abnormal situation is low and stable. At this time, no warning signal is generated, the existing configuration is maintained, and the resource allocation is monitored and maintained regularly to keep the system running smoothly.

[0026] The present invention also provides an intelligent building fire protection and management system, including a data collection module, a calculation module, a delay interference level division module, and a dynamic adjustment module;

[0027] Data collection module: Divide the building fire protection system into several monitoring links, collect the delay cumulative data of each monitoring link in different time periods, and obtain the server computing load data and network data congestion fluctuation state data in each monitoring link in different time periods;

[0028] Calculation module: Determine the weight assignment of the delay cumulative data of each monitoring link in different time periods according to the obtained server computing load data and network data congestion fluctuation state data, and perform weighted average calculation on the weight assignment of the delay cumulative data of each monitoring link in different time periods to obtain the overall delay cumulative interference index of the building fire protection system;

[0029] Low-delay and high-delay processing module: If the delay cumulative interference situation of the building fire protection system is classified as the low-delay cumulative interference level, no additional measures need to be taken at this time, and the system is monitored and maintained regularly; if the delay cumulative interference situation of the building fire protection system is classified as the high-delay cumulative interference level, the system process is immediately adjusted at this time to give priority to the delay in the fire detection and alarm notification links;

[0030] Dynamic adjustment module: Further analyze the delay cumulative interference situation of the building fire protection system within a fixed time period, and dynamically adjust the distribution of the computing load and the use of bandwidth resources of the building fire protection system according to the analysis results.

[0031] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0032] 1. By collecting and analyzing the delay cumulative data, server load, and network congestion data of each monitoring link of the building fire protection system in real time, the present invention dynamically determines the weight of delay accumulation and the overall delay cumulative interference index in different time periods, and performs delay level division and real-time response based on the threshold of historical data. This method can quickly identify different levels (high, medium, low) of system delay accumulation, immediately optimize the process for high-delay situations to give priority to the real-time performance of the fire detection and alarm notification links; for medium-delay levels, use the adaptive adjustment of computing load and bandwidth resources to ensure that the system delay is maintained within a controllable range, improving the overall response ability of the system.

[0033] 2. By generating the memory usage saturation anomaly index and the network bandwidth occupancy fluctuation index, and performing delay weight assignment based on the machine learning model, the present invention can accurately identify the key influencing factors of delay accumulation in each time period. In addition, through the three-level warning signals (level one, level two, level three), the system can timely adjust the load distribution and bandwidth resources to cope with unstable or minor delay fluctuations, ultimately ensuring the real-time response and operation stability of the building fire protection system in case of emergency, effectively reducing the response delay in the initial stage of the fire, and improving the fire safety and emergency evacuation efficiency of the building. Brief Description of the Drawings

[0034] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0035] Figure 1 It is a flowchart of the method of the present invention.

[0036] Figure 2 It is a system module diagram of the present invention. Detailed Embodiments

[0037] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0038] Embodiment 1, please refer to Figure 1 As shown, a method for intelligent building fire prevention and fire fighting management in this embodiment includes the following steps:

[0039] S1: Divide the building fire prevention system into several monitoring links, and collect the server computing load data and network data congestion fluctuation state data of each monitoring link in different time periods;

[0040] S2: Determine the weight assignment of the delay cumulative data of each monitoring link in different time periods according to the obtained server computing load data and network data congestion fluctuation state data, and perform a weighted average calculation on the weight assignment of the delay cumulative data of each monitoring link in different time periods to obtain the overall delay cumulative interference index of the building fire prevention system;

[0041] S3: Compare and analyze the overall delay cumulative interference index of the calculated building fire prevention system with the gradient delay threshold set according to the previously obtained historical data, and divide the delay cumulative interference situation of the building fire prevention system into different levels according to the analysis results;

[0042] S4: Further analyze the delay cumulative interference situation of the building fire prevention system within a fixed time period, and dynamically adjust the distribution of the computing load of the building fire prevention system and the use of bandwidth resources according to the analysis results.

[0043] In S1, the building fire protection system is divided into several monitoring links, and the delay cumulative data of each monitoring link in different time periods is collected, and the server computing load data and network data congestion fluctuation state data in each monitoring link in different time periods are obtained. Specifically:

[0044] The working process of the building fire protection system can be divided into the following five main monitoring links, and each link represents a key node for the system to achieve the fire protection function:

[0045] Monitoring link 1: Fire detection and data collection function: It includes sensors such as smoke, temperature, and flame, which are used to monitor the potential signals of fire in the environment in real time. Delay source: The time for sensor data collection and preliminary transmission to the central processor.

[0046] Monitoring link 2: Data processing and analysis function: After the system server receives the sensor data, it performs analysis, classification, and anomaly identification to determine whether the alarm condition is reached. Delay source: The computing time consumed during the data processing by the server, which may be affected by the server load.

[0047] Monitoring link 3: Communication and transmission function: Transmit the analysis results and instructions from the server to the linkage devices and the alarm system, and notify relevant personnel and the fire department. Delay source: The transmission time of data in the building internal communication network, which is affected by network congestion or bandwidth limitation.

[0048] Monitoring link 4: Linkage control function: Control the activation of linkage devices such as sprinklers, smoke exhaust, and emergency lighting to ensure that the devices can respond in a timely manner during a fire. Delay source: The response time for the instruction to reach the control system from the server and activate the linkage device, which may be delayed due to the complexity of the device control program or the hardware response time.

[0049] Monitoring link 5: Alarm and notification function: Convey the fire information to the building management personnel and the fire department, including information such as the location and severity of the fire. Delay source: The time for the information to be sent to external recipients, including the fire department and the building management party, which may be affected by network connection or external communication systems.

[0050] Analyze the latency situation of each monitoring link in different time periods, specifically including: divide a day into multiple time periods (such as morning rush hour, lunchtime, evening rush hour, night, etc.) to capture the impact of different load conditions on system latency. Deploy a latency monitoring program or a timestamp recording module at key nodes of each monitoring link. Timestamp recording: Record timestamps at the start and end of each link to calculate the latency. For example, record timestamps at nodes such as from fire detection to data processing completion, and from data processing to communication transmission start. Set the frequency of latency collection, such as collecting once per minute or per hour, and record the latency data into the database. Calculate the latency time of each link through the difference between the start and end timestamps, and accumulate to obtain the average latency of different time periods.

[0051] The server computing load data reflects the pressure on the server to process tasks in each monitoring link. Install load monitoring software (such as Prometheus, Nagios, Zabbix, etc.) on the system server to record the CPU, memory, and hard disk usage rates in real time. According to the time periods of the aforementioned latency collection, collect the server load data within the corresponding time periods to ensure the matching of load data and latency data. Collect key metrics: CPU usage rate: Reflects the execution of server computing tasks. A high CPU usage rate may lead to computing latency. Memory usage rate: When the memory is close to saturation, operations such as paging will occur in the system, resulting in a decrease in data processing speed. Storage read and write speed: The read and write speed during the data processing process directly affects the analysis and classification speed. Summarize and store the load data according to the collection time periods into the database for subsequent analysis.

[0052] Network data congestion will affect data transmission and system response speed. Deploy network monitoring tools (such as Wireshark, SolarWinds, NetFlow Analyzer, etc.) to record the network status in real time. Select key network metrics: Network bandwidth usage rate: Monitor the network bandwidth occupancy of each monitoring link. When the bandwidth is close to saturation, the transmission speed decreases. Data packet loss rate: A high packet loss rate indicates an unstable network connection, affecting the success rate of data transmission. Network latency (Ping or RTT): Regularly Ping network nodes or measure the round-trip time (RTT) to obtain the network latency fluctuation. Set network collection for different time periods: According to the collection time periods of the latency data, record the network status within the corresponding time periods to ensure data consistency. Store the congestion status data according to the time periods, and regularly calculate the average value and peak value to capture the network status fluctuation.

[0053] Store the delay accumulation data, server computing load data, and network congestion status data for different time periods in a unified database. Use data analysis tools or scripts to associate the delay data with the load and network status data to identify the reasons for delay accumulation in different time periods. Generate a delay report based on the data summary for different time periods to provide data support for delay cause analysis and real-time improvement.

[0054] S2: Determine the weight assignment of the delay accumulation data for each monitoring link in different time periods based on the obtained server computing load data and network data congestion fluctuation status data, and perform a weighted average calculation on the weight assignment of the delay accumulation data for each monitoring link in different time periods to obtain the overall delay accumulation interference index of the building fire protection system.

[0055] Analyze the saturation situation of the memory usage rate in the obtained server computing load data to generate a memory usage rate saturation anomaly index. The method for obtaining the memory usage rate saturation anomaly index is as follows:

[0056] Collect and define the historical data of the memory usage rate and construct a first time series data set , where represents the memory usage rate at the nth time point. Use the first time series data set D to train the model, assuming that the memory usage rate follows a normal distribution , that is: ; where: is the mean of the memory usage rate under normal conditions, is the variance of the memory usage rate under normal conditions; according to the historical distribution of the memory usage rate, set the prior probability P(normal): for example, assume it is 0.95 (or 95%), indicating that most memory usage rates should be normal values under normal circumstances; , representing the prior probability of the abnormal state. The prior probability is used for the initial hypothesis and represents the subjective belief about normal and abnormal situations before observing the data. For the memory usage rate x at the current time point, calculate the probability under normal conditions and the probability under abnormal conditions. The memory usage rate in the abnormal situation shows a wide distribution (which can be a uniform distribution or a wide normal distribution). Set the memory usage rate in the abnormal state to a uniform distribution U(a,b), and the calculation expression is: ; where [a,b] is the memory usage rate interval in the abnormal situation. Calculate the posterior probability according to Bayes' theorem (that is, the probability of belonging to the abnormal state after observing the memory usage rate x), and the expression is: ; where, represents the normal probability weight when the memory usage rate is x, It represents the abnormal probability weight when the memory usage rate is x. LK is the posterior probability, and the posterior probability is used as the memory usage saturation abnormal index.

[0057] The larger the memory usage saturation abnormal index, the closer or exceeding the normal saturation value of the server memory usage in the current time period, indicating that the server is under high load pressure in data processing or computing tasks. The saturation of memory resources will lead to a decrease in data processing efficiency, thus increasing the delay accumulation in each monitoring link. Especially in the fire detection and data analysis links, this delay may lead to a decrease in the response speed of alarm and linkage control. Therefore, a high memory saturation abnormal index indicates poor system real-time performance and serious delay accumulation in each monitoring link, and it is necessary to immediately optimize memory resources or take load balancing measures to reduce the delay impact.

[0058] On the contrary, the smaller the memory usage saturation abnormal index, the lower the memory usage rate is at a normal or low load level, indicating that the computing resources of the server are relatively sufficient in the current time period, and the data processing and task execution efficiency are high. In this case, the delay accumulation in each monitoring link is relatively light, the real-time response of the system is good, and the alarm and linkage control can be started in a timely manner. A low memory saturation abnormal index usually indicates that the system is running in a stable state, and the delay abnormality is not significant. The memory usage situation can be monitored regularly to ensure the continuous and efficient operation of the system.

[0059] After analyzing the fluctuation of the network bandwidth occupancy data in the obtained network data congestion fluctuation state data, a network bandwidth occupancy fluctuation index is generated. The method for obtaining the network bandwidth occupancy fluctuation index is as follows:

[0060] Collect the network bandwidth occupancy data within the W time period to form a second time series data set , where represents the network bandwidth occupancy data at time m. Based on the characteristics of the time series, select the autoregressive order p, the differencing order d, and the moving average order q, which can be assisted by the ACF (Autocorrelation Function) and PACF (Partial Autocorrelation Function) graphs, or use the Akaike Information Criterion (AIC) for model optimization.

[0061] Input the network bandwidth occupancy data into the ARIMA(p,d,q) model and train it. The model formula is: ; where: is the actual network bandwidth occupancy data at time t, is the autoregressive coefficient (used to explain the historical dependence of bandwidth occupancy). is the moving average coefficient (used to explain the historical dependence of errors), is the random error term at time t. The model parameters φ and θ are solved by the maximum likelihood estimation method to obtain the fitted ARIMA model.

[0062] Using the fitted ARIMA model, the network bandwidth usage data for the current time period t is predicted To make a prediction, the expression is: ; In the formula, Indicates time The random error term will predict the value The actual observed value For comparison, calculate the residual: ; Residual It reflects the deviation between the current network bandwidth usage data and the predicted value. A larger residual indicates that the bandwidth usage has experienced abnormal fluctuations. In order to quantify the degree of fluctuation, the residual is standardized so that anomalies can be identified more clearly. The network bandwidth usage fluctuation index is calculated by calculating the absolute value of the standardized residual.

[0063] The larger the network bandwidth usage fluctuation index is, the more drastic the fluctuation of network bandwidth usage is in the current time period, which is beyond the normal range. This abnormal fluctuation may cause the cumulative increase of data delay in the network transmission process, especially for key links that rely on real-time data transmission (such as fire detection and alarm notification). A high fluctuation index indicates that the system has serious network congestion in this time period, and the data transmission delay in each monitoring link increases, thereby delaying the response speed of operations such as alarm, linkage and notification, and increasing security risks. Therefore, in the case of a high fluctuation index, network optimization measures need to be taken immediately to reduce the impact of delays.

[0064] On the contrary, the smaller the network bandwidth occupancy fluctuation index is, the more stable the network bandwidth usage is and within the normal fluctuation range. Bandwidth stability results in lower data transmission delays in each monitoring link, and less significant delay accumulation, which helps ensure the real-time responsiveness of each monitoring link in the building fire protection system. During the period of low fluctuation index, alarm and linkage control can operate efficiently, with less delay, and the system operates in an efficient state without taking additional network adjustment measures.

[0065] Convert the memory usage saturation anomaly index and the network bandwidth occupancy fluctuation index into a comprehensive feature vector, and use the comprehensive feature vector as the input of the machine learning model. The machine learning model takes the weight assignment label of the cumulative delay data of each monitoring link in different time periods predicted by each group of comprehensive feature vectors as the prediction target, and takes minimizing the sum of the prediction errors of the weight assignment labels of the cumulative delay data of each monitoring link in all different time periods as the training target, and trains the machine learning model until the sum of the prediction errors reaches convergence and then stops the model training. Determine the weight assignment of the cumulative delay data of each monitoring link in different time periods according to the model output result. Among them, the machine learning model is a polynomial regression model, and the overall cumulative delay interference index of the building fire protection system is obtained by weighted average calculation of the weight assignment of the cumulative delay data of each monitoring link in different time periods.

[0066] The method for obtaining the weight assignment of the cumulative delay data of each monitoring link in different time periods is as follows: obtain the corresponding function expression from the comprehensive feature vector training data of the trained machine learning model: ; In the formula, is the output function of the model, LK is the memory usage saturation anomaly index, GH is the network bandwidth occupancy fluctuation index, is the weight assignment of the cumulative delay data of each monitoring link in different time periods.

[0067] S3: Compare and analyze the overall cumulative delay interference index of the building fire protection system calculated with the gradient delay threshold set according to the pre-obtained historical data, and divide the cumulative delay interference situation of the building fire protection system into different levels according to the analysis result. Among them, the levels include high cumulative delay interference level, medium cumulative delay interference level and low cumulative delay interference level.

[0068] Compare the overall cumulative delay interference index of the obtained building fire protection system with the gradient delay threshold. The gradient delay threshold includes a first delay threshold and a second delay threshold, and the first delay threshold is less than the second delay threshold. Compare the overall cumulative delay interference index of the building fire protection system with the first delay threshold and the second delay threshold respectively;

[0069] If the overall cumulative delay interference index of the building fire protection system is greater than the second delay threshold, it indicates that the overall cumulative delay interference degree of the building fire protection system is high, and the cumulative delay interference situation of the building fire protection system is divided into a high cumulative delay interference level. In this case, the system delay problem is relatively serious, indicating that the cumulative delay caused by abnormal fluctuations in memory usage and network bandwidth occupancy is relatively large. In this state, it may have a significant impact on fire alarm, evacuation and linkage response, and it is necessary to immediately optimize resources or adjust strategies to reduce the delay.

[0070] If the overall delay cumulative interference index of the building fire protection system is greater than or equal to the first delay threshold and less than or equal to the second delay threshold, it indicates that the overall delay cumulative interference degree of the building fire protection system is at a medium level, and the delay cumulative interference situation of the building fire protection system is classified as the medium delay cumulative interference level. At this time, the delay cumulative situation of the system is relatively obvious, but within a certain range. Monitoring and optimization measures can be taken, such as load balancing and bandwidth adjustment, to ensure that the delay accumulation will not deteriorate further.

[0071] If the overall delay cumulative interference index of the building fire protection system is less than the first delay threshold, it indicates that the overall delay cumulative interference degree of the building fire protection system is low, and the delay cumulative interference situation of the building fire protection system is classified as the low delay cumulative interference level. In this case, the system delay accumulation is small, indicating that the memory and network resources are relatively sufficient, the data transmission and response of each monitoring link are timely, and the system is in a stable and efficient state. At this time, no additional measures are required, and normal monitoring and maintenance are sufficient.

[0072] If the delay cumulative interference situation of the building fire protection system is classified as the low delay cumulative interference level, no additional measures are required at this time, and the system is monitored and maintained regularly; if the delay cumulative interference situation of the building fire protection system is classified as the high delay cumulative interference level, the system process is immediately adjusted to prioritize the delay in the fire detection and alarm notification links.

[0073] When the delay cumulative interference situation of the building fire protection system is classified as the low delay cumulative interference level, it indicates that the current system delay situation is within the normal and stable range, the delay accumulation is small, and the data processing and transmission of each monitoring link are smooth, meeting the real-time requirements of the building fire protection system. In this state, the system runs smoothly, the resource load and network bandwidth are sufficient, and key links such as fire detection, alarm notification, and linkage control can respond in a timely manner. Therefore, no additional intervention measures are required, and the system only needs to be monitored and maintained regularly to ensure that the delay situation continues to remain at a low level and prevent potential hardware aging or increased load from affecting the delay.

[0074] When the delay cumulative interference situation of the building fire protection system is classified as the high delay cumulative interference level, it means that the system delay accumulation has exceeded the safety threshold, seriously affecting the timeliness of fire detection and alarm notification. At this time, the delay accumulation will cause the transmission speed of fire detection signals and alarm information to slow down significantly, possibly delaying the response to fire alarms, making it impossible for building occupants, management personnel, and the fire department to be notified quickly in the initial stage of a fire, thus increasing the risk of fire spread and personnel entrapment. To ensure the real-time performance of the fire detection and alarm notification links, the system must immediately adjust the process and raise the priority of these two links to the highest level to ensure that resources are concentrated on these key tasks.

[0075] Specific adjustments include preferentially allocating memory, CPU, and network bandwidth resources to the fire detection and alarm notification modules, while enabling dedicated data transmission channels to ensure that these critical data can be quickly processed and transmitted in the case of high latency. In addition, non-critical tasks can be paused or postponed to release system resources and avoid interference from secondary tasks to fire detection and alarm notification. If the latency situation persists severely, the system can also switch to an alternative communication link or enable edge computing nodes to process fire signals locally as much as possible, reducing the dependence on the main server, thereby further ensuring the reliability and response speed of the system under high latency.

[0076] S4: Further analyze the cumulative latency interference situation of the building fire protection system within a fixed time period, and dynamically adjust the allocation of the computing load and the use of bandwidth resources of the building fire protection system according to the analysis results.

[0077] For the medium cumulative latency interference level, that is, the overall cumulative latency interference index of the building fire protection system generated within a fixed time period is greater than or equal to the first latency threshold and less than or equal to the second latency threshold, collect the overall cumulative latency interference indices of the building fire protection system that are greater than or equal to the first latency threshold and less than or equal to the second latency threshold generated in subsequent fixed time periods, and establish a corresponding data set. Calculate the mean and standard deviation of the data set, analyze the abnormal degree of the overall cumulative latency interference of the building fire protection system within the fixed time period, and dynamically adjust the allocation of the computing load and the use of bandwidth resources of the building fire protection system according to the analysis results.

[0078] If the mean of the overall cumulative latency interference indices in the data set is greater than or equal to the reference threshold of the mean of the overall cumulative latency interference indices, and the standard deviation of the overall cumulative latency interference indices is less than the reference threshold of the standard deviation of the overall cumulative latency interference indices, it indicates that the cumulative latency anomaly is stable and continuous, with small fluctuations, and there are bottlenecks in the system load and network resources at a fixed level. At this time, a secondary warning signal is generated, and it is necessary to optimize the current computing load allocation and bandwidth resource configuration, concentrate on improving resources, and focus on alleviating the bottleneck part to improve the cumulative latency situation.

[0079] If the mean of the overall cumulative latency interference indices is greater than or equal to the reference threshold of the mean of the overall cumulative latency interference indices, and the standard deviation of the overall cumulative latency interference indices is greater than or equal to the reference threshold of the standard deviation of the overall cumulative latency interference indices, it indicates that the cumulative latency anomaly is unstable, with large fluctuations, and the system load and bandwidth resources vary greatly at different times. At this time, a primary warning signal is generated, and a load balancing mechanism and dynamic bandwidth management are introduced to flexibly allocate resources, adapt to latency fluctuations, and ensure that the system has sufficient resources to handle latency during peak and off-peak periods.

[0080] If the mean value of the overall delay cumulative interference index is less than the reference threshold of the mean value of the overall delay cumulative interference index, and the standard deviation of the overall delay cumulative interference index is greater than or equal to the reference threshold of the standard deviation of the overall delay cumulative interference index, it indicates that the delay cumulative anomaly fluctuates greatly, but the overall anomaly is light. System resources are under pressure during certain periods. At this time, a third-level warning signal is generated, the load change is monitored, more bandwidth resources are automatically allocated at high load, and overall monitoring is maintained to avoid further exacerbation of delay fluctuations.

[0081] If the mean value of the overall delay cumulative interference index is less than the reference threshold of the mean value of the overall delay cumulative interference index, and the standard deviation of the overall delay cumulative interference index is less than the reference threshold of the standard deviation of the overall delay cumulative interference index, it indicates that the delay cumulative anomaly is low and stable, and the system resource configuration basically meets the requirements. At this time, no warning signal is generated, the existing configuration is maintained, and the resource allocation is monitored and maintained regularly to keep the system running smoothly.

[0082] It should be noted here that the importance of the first-level warning signal is greater than that of the second-level warning signal, and the importance of the second-level warning signal is greater than that of the third-level warning signal. Relevant personnel can take corresponding management measures according to different warning signal levels.

[0083] When the delay cumulative anomaly of the building fire protection system is unstable and fluctuates greatly, the system generates a first-level warning signal, indicating that the delay situation changes significantly with time periods and is difficult to predict and control. This situation usually indicates that the server computing load and network bandwidth fluctuate violently at different time periods, and there may be phenomena such as peak period delay accumulation or increased network congestion, resulting in unstable response times for critical tasks (such as fire detection, alarm, and evacuation guidance). Therefore, to ensure that the system can still respond in a timely manner under various load conditions, a load balancing mechanism and dynamic bandwidth management need to be introduced to stabilize the system performance.

[0084] The load balancing mechanism specifically includes: The system dynamically allocates computing tasks to server nodes with lighter loads according to the current load conditions of the servers, avoiding single-node overloading and causing delay accumulation. This can effectively disperse the pressure and ensure the load balance of each node. In the first-level warning state, the system can give priority to processing fire detection and alarm notification tasks, postpone or transfer non-urgent tasks to low priorities to ensure the real-time nature of critical tasks. If a node with too high a load is detected, the system automatically enables standby servers or computing resources to share high-load tasks, thereby reducing the delay fluctuations brought by peak periods.

[0085] Dynamic bandwidth management specifically includes: setting bandwidth priorities for key processes (such as alarm transmission and fire signal processing) to ensure that important data can be preferentially transmitted during network congestion, reducing the impact of latency. The system monitors the bandwidth usage of the network and dynamically allocates bandwidth resources when the network fluctuates significantly, avoiding data transmission being affected by instantaneous congestion. In the case of severe network fluctuations, multi-path transmission can be enabled to distribute critical data across multiple network paths for transmission, ensuring that at least one path can transmit important information in a timely manner.

[0086] In this embodiment, the building fire protection system is divided into multiple monitoring processes. The delay accumulation, server computing load, and network congestion fluctuation data of each monitoring process in different time periods are collected and analyzed to determine the delay accumulation weight of each monitoring process and calculate the overall delay accumulation interference index of the system. By comparing this index with the gradient threshold set based on historical data, the delay situation of the system is divided into three levels: high, medium, and low. If it is low delay, regular monitoring and maintenance are sufficient; if it is high delay, the process is immediately adjusted to prioritize the real-time performance of the fire detection and alarm notification processes; if it is medium delay, the delay anomaly situation is further analyzed, and the system computing load and bandwidth resource allocation are dynamically adjusted to optimize the system response ability.

[0087] Embodiment 2, please refer to Figure 2 As shown in the figure, an intelligent building fire protection and management system in this embodiment includes a data collection module, a calculation module, a delay interference level division module, and a dynamic adjustment module;

[0088] Data collection module: divides the building fire protection system into several monitoring processes, collects the delay accumulation data of each monitoring process in different time periods, and obtains the server computing load data and network data congestion fluctuation state data of each monitoring process in different time periods;

[0089] Calculation module: determines the weight assignment of the delay accumulation data of each monitoring process in different time periods based on the obtained server computing load data and network data congestion fluctuation state data, and performs a weighted average calculation on the weight assignments of the delay accumulation data of each monitoring process in different time periods to obtain the overall delay accumulation interference index of the building fire protection system;

[0090] Delay interference level division module: compares and analyzes the overall delay accumulation interference index of the building fire protection system calculated with the gradient delay threshold set according to the previously obtained historical data, and divides the delay accumulation interference situation of the building fire protection system into different levels according to the analysis results. Among them, the levels include high delay accumulation interference level, medium delay accumulation interference level, and low delay accumulation interference level;

[0091] Dynamic adjustment module: Further analyze the delay cumulative interference situation of the building fire protection system within a fixed time period, and dynamically adjust the distribution of the computing load and the use of bandwidth resources of the building fire protection system according to the analysis results.

[0092] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0093] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. These three situations, where A and B can be singular or plural. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0094] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0095] As described above, it is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application.

Claims

1. An intelligent building fire prevention and firefighting management method, characterized in that: The following steps are involved: S1: Divide the building fire protection system into several monitoring links, and collect the server computing load data and network data congestion fluctuation status data of each monitoring link in different time periods; S2: Determine the weight assignment of the accumulated delay data of each monitoring link in different time periods according to the obtained server computing load data and network data congestion fluctuation status data, and obtain the overall delay cumulative interference index of the building fire protection system by weighted average calculation of the accumulated delay data of each monitoring link in different time periods; S3: Compare and analyze the calculated overall delay cumulative interference index of the building fire protection system with the gradient delay threshold set according to the historical data obtained in advance, and divide the delay cumulative interference of the building fire protection system into different levels according to the analysis results; S4: Further analyze the delay cumulative interference of the building fire protection system within a fixed time period, and dynamically adjust the distribution of the building fire protection system computing load and the use of bandwidth resources according to the analysis results.

2. The intelligent building fire prevention and firefighting management method according to claim 1 is characterized by: In S2, the saturation of memory usage in the acquired server computing load data is analyzed to generate a memory usage saturation abnormality index. The method for obtaining the memory usage saturation abnormality index is as follows: Collect and define historical data on memory usage and build a first time series dataset ,in Represents the memory usage at the nth time point. The model is trained using the first time series dataset D, and the memory usage is set to conform to the normal distribution. ,Right now: ;in: is the average memory usage under normal circumstances, is the variance of memory usage under normal conditions; according to the historical distribution of memory usage, set the prior probability P(normal); , represents the prior probability of abnormal state, for the memory usage x at the current time point, calculate the probability under normal conditions and the probability under abnormal conditions , assuming that the memory usage rate under abnormal conditions is uniformly distributed U(a,b), the calculation expression is: ; where [a,b] is the memory usage interval under abnormal conditions. The posterior probability is calculated according to Bayes' theorem, and the expression is: ;in, represents the normal probability weight when the memory usage rate is x, It represents the abnormal probability weight when the memory usage rate is x, LK is the posterior probability, and the posterior probability is used as the memory usage saturation abnormality index.

3. The intelligent building fire prevention and firefighting management method according to claim 2 is characterized in that: In S2, a network bandwidth occupancy fluctuation index is generated after analyzing the fluctuation of the network bandwidth occupancy data in the acquired network data congestion fluctuation status data. The method for obtaining the network bandwidth occupancy fluctuation index is: Collect network bandwidth usage data within the W time period to form the second time series data set ,in Represents the network bandwidth usage data at time m. Based on the characteristics of time series, the autoregressive order p, the difference order d, and the moving average order q are selected. The network bandwidth usage data is input into the ARIMA (p, d, q) model and trained. The model formula is: ;in: The actual network bandwidth usage data at time t, is the autoregression coefficient, is the moving average coefficient, is the random error term at time t, and the model parameters ϕ and θ are solved by the maximum likelihood estimation method to obtain the fitted ARIMA model; Using the fitted ARIMA model, the network bandwidth usage data for the current time period t is predicted To make a prediction, the expression is: ; In the formula, Indicates time The random error term will predict the value The actual observed value For comparison, calculate the residual: ; Residual It reflects the deviation between the current network bandwidth occupancy data and the predicted value. The residual is standardized and the network bandwidth occupancy fluctuation index is calculated, that is, the absolute value of the standardized residual is calculated.

4. The intelligent building fire prevention and firefighting management method according to claim 3 is characterized by: In S2, the memory usage saturation anomaly index and the network bandwidth occupancy fluctuation index are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the weighted assignment labels of the delayed cumulative data of each monitoring link in different time periods as the prediction target, and takes minimizing the sum of the prediction errors of the weighted assignment labels of the delayed cumulative data of each monitoring link in all different time periods as the training target. The machine learning model is trained until the sum of the prediction errors converges and the model training is stopped. The weight assignment of the delayed cumulative data of each monitoring link in different time periods is determined according to the model output results. Among them, the machine learning model is a polynomial regression model, and the weighted average calculation of the weight assignment of the delayed cumulative data of each monitoring link in different time periods is performed to obtain the overall delay cumulative interference index of the building fire protection system.

5. The intelligent building fire prevention and firefighting management method according to claim 4 is characterized in that: In S3, the calculated overall delay cumulative interference index of the building fire protection system is compared and analyzed with the gradient delay threshold set according to the historical data obtained in advance, specifically: The obtained overall delay cumulative interference index of the building fire protection system is compared with the gradient delay threshold, the gradient delay threshold includes a first delay threshold and a second delay threshold, and the first delay threshold is less than the second delay threshold, and the overall delay cumulative interference index of the building fire protection system is compared with the first delay threshold and the second delay threshold respectively; If the overall delay cumulative interference index of the building fire protection system is greater than the second delay threshold, it means that the overall delay cumulative interference level of the building fire protection system is high, and the delay cumulative interference situation of the building fire protection system is classified as a high delay cumulative interference level; if the overall delay cumulative interference index of the building fire protection system is greater than or equal to the first delay threshold and less than or equal to the second delay threshold, it means that the overall delay cumulative interference level of the building fire protection system is at a medium level, and the delay cumulative interference situation of the building fire protection system is classified as a medium delay cumulative interference level; if the overall delay cumulative interference index of the building fire protection system is less than the first delay threshold, it means that the overall delay cumulative interference level of the building fire protection system is low, and the delay cumulative interference situation of the building fire protection system is classified as a low delay cumulative interference level.

6. The intelligent building fire prevention and firefighting management method according to claim 5 is characterized by: In S4, for the medium delay cumulative interference level, that is, the overall delay cumulative interference index of the building fire protection system generated within a fixed time period is greater than or equal to the first delay threshold and less than or equal to the second delay threshold, the overall delay cumulative interference index of the building fire protection system generated in a subsequent fixed time period that is greater than or equal to the first delay threshold and less than or equal to the second delay threshold is collected, and a corresponding data set is established, the mean and standard deviation of the data set are calculated, the degree of abnormality of the overall delay cumulative interference of the building fire protection system within the fixed time period is analyzed, and the distribution of the computing load of the building fire protection system and the use of bandwidth resources are dynamically adjusted according to the analysis results.

7. The intelligent building fire prevention and firefighting management method according to claim 6 is characterized by: If the mean value of the overall delay cumulative interference index in the data set is greater than or equal to the reference threshold value of the overall delay cumulative interference index mean value, and the standard deviation of the overall delay cumulative interference index is less than the reference threshold value of the standard deviation of the overall delay cumulative interference index, it means that the delay accumulation anomaly is stable and continuous with small fluctuations. At this time, a secondary warning signal is generated, and it is necessary to optimize the current computing load distribution and bandwidth resource configuration, concentrate on improving resources, and focus on alleviating bottlenecks; If the mean value of the overall delay cumulative interference index is greater than or equal to the reference threshold value of the mean value of the overall delay cumulative interference index, and the standard deviation of the overall delay cumulative interference index is greater than or equal to the reference threshold value of the standard deviation of the overall delay cumulative interference index, it means that the delay accumulation abnormality is unstable and fluctuates greatly. At this time, a first-level warning signal is generated, and a load balancing mechanism and dynamic bandwidth management are introduced; If the mean value of the overall delay cumulative interference index is less than the reference threshold value of the mean value of the overall delay cumulative interference index, and the standard deviation of the overall delay cumulative interference index is greater than or equal to the reference threshold value of the standard deviation of the overall delay cumulative interference index, it means that the delay accumulation abnormality fluctuates greatly, but the overall abnormality is mild. At this time, a third-level warning signal is generated to monitor load changes, automatically allocate more bandwidth resources when the load is high, and maintain overall monitoring to avoid further aggravation of delay fluctuations; If the mean of the overall delay cumulative interference index is less than the reference threshold of the mean of the overall delay cumulative interference index, and the standard deviation of the overall delay cumulative interference index is less than the reference threshold of the standard deviation of the overall delay cumulative interference index, it means that the delay accumulation abnormality is low and stable. At this time, no warning signal is generated. The existing configuration is maintained, and resource allocation is monitored and maintained regularly to maintain smooth operation of the system.

8. An intelligent building fire prevention and fire management system, used to implement an intelligent building fire prevention and fire management method according to any one of claims 1 to 7, characterized in that: It includes a data collection module, a calculation module, a delay interference level classification module and a dynamic adjustment module; Data collection module: divides the building fire protection system into several monitoring links, collects the accumulated delay data of each monitoring link in different time periods, and obtains the server computing load data and network data congestion fluctuation status data in each monitoring link in different time periods; Calculation module: Determine the weight assignment of the accumulated delay data of each monitoring link in different time periods according to the acquired server calculation load data and network data congestion fluctuation status data, and perform weighted average calculation on the accumulated delay data of each monitoring link in different time periods to obtain the overall accumulated delay interference index of the building fire protection system; Delay interference level classification module: compares and analyzes the calculated overall delay cumulative interference index of the building fire protection system with the gradient delay threshold set according to the historical data obtained in advance, and divides the delay cumulative interference of the building fire protection system into different levels according to the analysis results, wherein the levels include high delay cumulative interference level, medium delay cumulative interference level and low delay cumulative interference level; Dynamic adjustment module: further analyzes the cumulative interference of the delay of the building fire protection system within a fixed time period, and dynamically adjusts the distribution of the building fire protection system computing load and the use of bandwidth resources based on the analysis results.

Images