Intelligent community fire-fighting big data analysis system and method based on artificial intelligence

Abstract

The invention relates to the technical field of intelligent data analysis, in particular to an intelligent community fire-fighting big data analysis system and method based on artificial intelligence, and the system comprises a data collection module, an artificial intelligence module, a screening module, a first determination module, a calculation module, a second determination module, a judgment module, an alarm module and an adjustment module. By monitoring combustible heaps, fire hydrant water levels and water tank water pressures of all grids in a community in real time, the system can quickly identify potential fire risks and give an alarm in time, the probability of fire occurrence is reduced, the dynamic adjustment function of the system flexibly optimizes grid spacing according to the number of abnormal grids and a preset standard, and the safety of the system is improved. The configuration efficiency of fire-fighting resources is improved, so that a community can accumulate and analyze fire-fighting data, and the problems of low accuracy and slow response of a fire-fighting safety analysis result caused by single monitoring means and insufficient real-time processing capability are effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of smart data analysis technology, and in particular to an artificial intelligence-based smart community fire protection big data analysis system and method. Background Art

[0002] With the acceleration of urbanization and the continuous increase in community population density, fire safety issues have become increasingly prominent. Traditional fire safety monitoring methods often rely on manual inspections and regular inspections, which cannot achieve real-time monitoring and rapid response to potential fire hazards. Therefore, an advanced intelligent system is urgently needed to effectively integrate big data analysis and artificial intelligence technology to improve the efficiency and accuracy of fire safety management.

[0003] The patent document with publication number CN117132434A discloses a building fire safety supervision system based on big data analysis, which includes: a safety supervision platform, which is communicatively connected with a channel supervision module, a pipeline monitoring module, a safety rating module and a storage module; the channel supervision module is used to monitor, manage and analyze the smoothness of the building fire passage: the fire passage of the building is recorded by a camera, the recording is decomposed into frames of images and marked as monitoring images, the monitoring images are processed and smooth grids and blocked grids are obtained; the blocked grids are clustered and analyzed and the monitoring images are marked as blocked images or smooth images; the pipeline monitoring module is used to monitor and analyze the safety of the building fire water pipe: the water pressure data SY, pressure difference data YC and pressure stability data YW of the building fire water pipe are obtained and numerical calculations are performed to obtain the pipeline coefficient GD of the fire water pipe; the pipeline threshold GDmax is obtained through the storage module, the pipeline coefficient GD is compared with the pipeline threshold GDmax, and whether the safety of the fire water pipe meets the requirements is determined by the comparison result; the safety rating module is used to perform grade assessment analysis on the building fire safety.

[0004] It can be seen that the system's delay in image processing and analysis leads to a slow response to emergencies such as fires. The process of decomposing the video into image frames and processing them takes a long time, increasing the complexity and maintenance cost of the system. Image labeling and analysis require manual intervention, increasing the possibility of human error. Summary of the invention

[0005] To this end, the present invention provides an artificial intelligence-based smart community fire big data analysis system and method to overcome the problems of low accuracy and slow response of fire safety analysis results caused by a single monitoring method and insufficient real-time processing capability in the prior art.

[0006] To achieve the above objectives, the present invention provides, on one hand, a smart community fire protection big data analysis system based on artificial intelligence, comprising: A data collection module is used to collect real-time images of each grid in the collection area based on the preset grid spacing within the community, the real-time average water level of all water tanks, and the real-time average water pressure of all fire hydrants; An artificial intelligence module, connected to the data acquisition module, for extracting the real-time pile quantity of combustibles in each of the real-time images; A screening module connected to the artificial intelligence module for screening out a number of risk grids according to the real-time number of material piles; A first determination module, which is connected to the screening module and the data acquisition module respectively, is used to determine the fluctuation consistency according to the real-time average water level and the real-time average water pressure in any two adjacent risk grids within a preset calculation time, and determine a number of first temporary grids according to the fluctuation consistency; a calculation module, which is connected to the data acquisition module and the first determination module respectively, and is used to calculate the water flow deviation according to the real-time average water level and the real-time average water pressure at adjacent moments of each of the first temporary grids; a second determination module, connected to the calculation module, for determining a plurality of second temporary grids according to the water flow deviation; A determination module, which is connected to the second determination module and the data acquisition module respectively, and is used to determine a number of abnormal grids according to the distribution degree of the second temporary grid, and record the duration; an alarm module, connected to the determination module, for sending an alarm according to the duration; An adjustment module is connected to the determination module and the data acquisition module respectively, and is used to adjust the preset grid spacing according to the grid quantity of each abnormal grid within a preset adjustment time and a preset standard quantity fluctuation value.

[0007] Furthermore, the first determining module includes: a standard deviation calculation unit, used for calculating the standard deviation of the real-time average water level to obtain the water level standard deviation, and for calculating the standard deviation of the real-time average water pressure to obtain the water pressure standard deviation; a consistency calculation unit connected to the standard deviation calculation unit, for calculating the relative deviation between the water level standard deviation and the water pressure standard deviation to form the fluctuation consistency; A first determination unit is connected to the consistency calculation unit and is used to determine a plurality of first temporary grids according to a comparison result between the fluctuation consistency and a preset standard consistency.

[0008] Furthermore, the calculation module includes: a deviation calculation unit, used for calculating the relative deviation of the real-time average water level to obtain the water level deviation, and for calculating the relative deviation of the real-time average water pressure to obtain the water pressure deviation; A water flow calculation unit is connected to the deviation calculation unit and is used to calculate the relative deviation between the water level deviation and the water pressure deviation to form the water flow deviation.

[0009] Furthermore, the second determining module includes: A water flow comparison unit, used to compare the water flow deviation with a preset standard water flow deviation to form a water flow comparison result; A second determining unit is connected to the water flow comparison unit and is used to determine a plurality of second temporary grids according to the water flow comparison result.

[0010] Furthermore, the determination module includes: a distribution degree calculation unit, configured to determine the distribution degree according to the second temporary grid and all adjacent second temporary grids within a preset radius; a determination unit connected to the distribution degree calculation unit, for determining the second temporary grid as an abnormal grid according to a comparison result between the distribution degree and a preset standard distribution degree, and forming a plurality of abnormal grids; A recording unit is connected to the determination unit and is used to record the duration of the abnormal grid.

[0011] Furthermore, the distribution degree calculation unit includes: a distance calculation subunit, used for calculating an average distance between each of the second temporary grids and all adjacent second temporary grids within the preset radius; The distribution degree calculation subunit is connected to the distribution degree confirmation unit and is used to calculate the relative deviation between the average distance and a preset standard distance to form a distribution degree.

[0012] Furthermore, the adjustment module includes: A quantity fluctuation calculation unit, used to calculate the standard deviation of the grid quantity to form a quantity fluctuation value; An adjustment unit is used to adjust the preset grid spacing according to a comparison result between the quantity fluctuation value and the preset standard quantity fluctuation value, the grid quantity, the preset standard quantity fluctuation value and a preset adjustment coefficient.

[0013] Furthermore, the alarm module comprises: An alarm determination unit, configured to determine whether an alarm needs to be sent according to a comparison result between each of the durations and a preset standard duration, and form an alarm determination result; An alarm sending unit is connected to the alarm determination unit and is used to send an alarm according to the alarm determination result.

[0014] Furthermore, the screening module includes: A material pile comparison unit, used to compare the real-time material pile quantity with a preset standard quantity to form a material pile comparison result; A screening unit is connected to the object pile comparison unit and is used to screen out a plurality of grids according to the object pile comparison result to form a plurality of risk grids.

[0015] On the other hand, the present invention also provides a smart community fire big data analysis method based on artificial intelligence, comprising: Collect real-time images of each grid in the collection area based on preset grid spacing within the community, the real-time average water level of each fire hydrant, and the real-time average water pressure of each water tank; Extracting the real-time pile quantity of combustible materials in each of the real-time images; Screening out a number of risk grids according to the real-time number of material piles; Determine the fluctuation consistency according to the real-time average water level and the real-time average water pressure in any two adjacent risk grids within a preset calculation time, and determine a number of first temporary grids according to the fluctuation consistency; Calculating the water flow deviation according to the real-time average water level and the real-time average water pressure of each of the first temporary grids at adjacent moments; Determine a plurality of second temporary grids according to the water flow deviation; Determine a number of abnormal grids according to the distribution degree of the second temporary grid, and record the duration; Sending an alert according to the duration; The preset grid spacing is adjusted according to the grid quantity of each abnormal grid within a preset adjustment time and a preset standard quantity fluctuation value.

[0016] Compared with the prior art, the beneficial effect of the present invention is that the artificial intelligence-based smart community fire big data analysis system significantly improves the efficiency and accuracy of community fire safety management. By real-time monitoring of the combustible piles, fire hydrant water levels and water tank water pressures in each grid in the community, the system can quickly identify potential fire risks and issue alarms in time to reduce the probability of fire. The system's dynamic adjustment function flexibly optimizes the grid spacing according to the number of abnormal grids and preset standards, thereby improving the allocation efficiency of fire resources. The system's continuous monitoring and data analysis functions enable the community to accumulate and analyze fire data, thereby providing a scientific basis for future safety decisions, and effectively solving the problems of low accuracy and slow response of fire safety analysis results due to single monitoring methods and insufficient real-time processing capabilities.

[0017] Furthermore, by calculating the relative deviation of the water level and water pressure standard deviation, the regional grids with abnormal fluctuations can be quickly screened out. This can effectively identify potential risk grids, improve the early warning and response efficiency of the fire protection system, and timely check abnormal water pressure and water level conditions.

[0018] Furthermore, by providing real-time feedback of water level and water pressure deviations, abnormal situations can be quickly identified.

[0019] Furthermore, by comparing with preset standards, potential fire safety hazards can be quickly identified, and the system can respond quickly after the second temporary grid is determined in time.

[0020] Furthermore, by monitoring the distribution of grids, false alarms can be effectively reduced and the accuracy of the system can be improved. In addition, recording the duration of abnormal grids provides data support for subsequent decision-making, making it easier to formulate more effective preventive measures.

[0021] Furthermore, by calculating the distribution degree, the uniformity of the grid distribution can be effectively quantified, providing data support for subsequent abnormal grid determination.

[0022] Furthermore, when the number of grids fluctuates beyond a preset range, timely adjustment of the grid spacing can ensure the comprehensiveness and accuracy of monitoring and reduce blind spots.

[0023] Furthermore, by monitoring the duration of abnormal grids, it is possible to ensure that countermeasures are taken quickly before the problem worsens.

[0024] Furthermore, by comparing real-time data with preset standards, the accuracy of fire monitoring can be effectively improved and suspicious areas can be identified in a timely manner.

[0025] Furthermore, through real-time data monitoring and intelligent analysis, potential fire risks in the community can be effectively identified, the early warning capability and response efficiency of fire safety can be improved, and the possibility of false alarms and missed alarms can be reduced by accurately screening out risk grids. At the same time, the grid spacing can be dynamically adjusted to ensure the flexibility and accuracy of the monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a schematic diagram of a smart community fire protection big data analysis system based on artificial intelligence in this embodiment; Figure 2 A decision logic diagram for determining a first temporary grid by a first determination module in this embodiment; Figure 3 A decision logic diagram for determining a second temporary grid by a second determination module in this embodiment; Figure 4 This is a flow chart of the smart community fire protection big data analysis method based on artificial intelligence in this embodiment. DETAILED DESCRIPTION

[0027] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0028] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0029] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0030] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0031] See also Figure 1 As shown, it is a schematic diagram of the smart community fire protection big data analysis system based on artificial intelligence in this embodiment; This embodiment provides a smart community fire protection big data analysis system based on artificial intelligence, including: A data collection module is used to collect real-time images of each grid in the collection area based on the preset grid spacing within the community, the real-time average water level of all water tanks, and the real-time average water pressure of all fire hydrants; An artificial intelligence module, connected to the data acquisition module, for extracting the real-time pile quantity of combustibles in each of the real-time images; A screening module connected to the artificial intelligence module for screening out a number of risk grids according to the real-time number of material piles; A first determination module, which is connected to the screening module and the data acquisition module respectively, is used to determine the fluctuation consistency according to the real-time average water level and the real-time average water pressure in any two adjacent risk grids within a preset calculation time, and determine a number of first temporary grids according to the fluctuation consistency; a calculation module, which is connected to the data acquisition module and the first determination module respectively, and is used to calculate the water flow deviation according to the real-time average water level and the real-time average water pressure at adjacent moments of each of the first temporary grids; a second determination module, connected to the calculation module, for determining a plurality of second temporary grids according to the water flow deviation; A determination module, which is connected to the second determination module and the data acquisition module respectively, and is used to determine a number of abnormal grids according to the distribution degree of the second temporary grid, and record the duration; an alarm module, connected to the determination module, for sending an alarm according to the duration; An adjustment module is connected to the determination module and the data acquisition module respectively, and is used to adjust the preset grid spacing according to the grid quantity of each abnormal grid within a preset adjustment time and a preset standard quantity fluctuation value.

[0032] The AI ​​module extracts the number of combustible piles in real-time images through its built-in YOLO model.

[0033] The preset grid spacing refers to the distance between each grid when dividing the monitoring area within the community. It depends on the layout of the community, the distribution of combustibles and the density of fire-fighting facilities. It is usually set between 5 meters and 10 meters. In this embodiment, it is set to 8 meters. It can simplify data processing while ensuring the accuracy of information collection. It is suitable for densely populated urban areas and facilitates effective monitoring of fire safety.

[0034] The preset calculation time refers to the time period used to count and analyze fluctuations in water level and water pressure data. It depends on the response speed and operation of the fire protection system. It is usually set between 1 minute and 5 minutes. In this embodiment, it is set to 3 minutes, which can effectively capture short-term fluctuations, identify equipment failures or water source problems in a timely manner, and improve response efficiency.

[0035] The preset adjustment time refers to the duration of monitoring abnormal grids to decide whether to adjust the grid spacing. It depends on the frequency of environmental changes and fire safety management requirements. It is usually set between 5 minutes and 10 minutes. In this embodiment, it is set to 7 minutes, which can effectively monitor abnormal conditions and give managers enough time to evaluate and avoid unnecessary interference caused by frequent adjustments.

[0036] The preset standard quantity fluctuation value refers to the range of quantity changes used to define when judging abnormal grids. It depends on historical data analysis and the actual situation of the community. It is usually set to between 3 and 5. In this embodiment, it is set to 4, which can increase the sensitivity to real abnormal situations, avoid false alarms caused by small fluctuations, and improve the reliability of the system.

[0037] Real-time monitoring and analysis of community safety is achieved through a series of modules. First, the data acquisition module obtains real-time images, real-time average water level and real-time average water pressure data in each grid. The artificial intelligence module processes the real-time images, extracts the number of combustible piles, and passes the results to the screening module to identify the risk grid. Next, the first determination module determines the first temporary grid based on the fluctuation consistency of the real-time average water level and real-time average water pressure of the risk grid. The calculation module then analyzes the water flow deviation of these temporary grids, and the second determination module further screens out the second temporary grid. The judgment module identifies abnormal grids by calculating the distribution degree and records their duration. Finally, the alarm module issues an alarm based on the duration, and the adjustment module adjusts the grid spacing based on the number of abnormal grids and preset standards.

[0038] This AI-based smart community fire big data analysis system has significantly improved the efficiency and accuracy of community fire safety management. By real-time monitoring of combustible piles, fire hydrant water levels and water tank water pressures in each grid in the community, the system can quickly identify potential fire risks and issue alarms in a timely manner to reduce the probability of fire. The system's dynamic adjustment function flexibly optimizes grid spacing based on the number of abnormal grids and preset standards, thereby improving the allocation efficiency of fire resources. The system's continuous monitoring and data analysis functions enable the community to accumulate and analyze fire data, thereby providing a scientific basis for future safety decisions, effectively solving the problems of low accuracy and slow response of fire safety analysis results due to single monitoring methods and insufficient real-time processing capabilities.

[0039] Please continue reading Figure 2 As shown, it is a decision logic diagram of the first determination module determining the first temporary grid in this embodiment; Specifically, the first determining module includes: a standard deviation calculation unit, used for calculating the standard deviation of the real-time average water level to obtain the water level standard deviation, and for calculating the standard deviation of the real-time average water pressure to obtain the water pressure standard deviation; a consistency calculation unit connected to the standard deviation calculation unit, for calculating the relative deviation between the water level standard deviation and the water pressure standard deviation to form the fluctuation consistency; A first determination unit is connected to the consistency calculation unit and is used to determine a plurality of first temporary grids when the fluctuation consistency is greater than a preset standard consistency.

[0040] The preset standard consistency is a benchmark value used to measure the relative fluctuation between the water level standard deviation and the water pressure standard deviation, which depends on the configuration of fire protection facilities in the community, environmental conditions, and statistical analysis of historical monitoring data. It is usually set between 0.1 and 0.5, and is set to 0.2 in this embodiment to ensure moderate sensitivity to water level and water pressure fluctuations.

[0041] First, the standard deviation calculation unit calculates the standard deviation of the real-time average water level and the real-time average water pressure respectively to obtain the standard deviation of the water level and the water pressure; then, the consistency calculation unit calculates the relative deviation of the water level standard deviation and the water pressure standard deviation to obtain the fluctuation consistency; finally, the first determination unit screens and determines a number of first temporary grids based on the comparison results of the fluctuation consistency and the preset standard consistency, and identifies areas where abnormal water level and water pressure fluctuations may exist.

[0042] By calculating the relative deviation of the water level and water pressure standard deviation, the regional grids with abnormal fluctuations can be quickly screened out. This can effectively identify potential risk grids, improve the early warning and response efficiency of the fire protection system, and timely check abnormal water pressure and water level conditions.

[0043] Specifically, the calculation module includes: a deviation calculation unit, used for calculating the relative deviation of the real-time average water level to obtain the water level deviation, and for calculating the relative deviation of the real-time average water pressure to obtain the water pressure deviation; A water flow calculation unit is connected to the deviation calculation unit and is used to calculate the relative deviation between the water level deviation and the water pressure deviation to form the water flow deviation.

[0044] Since water tanks or fire hydrants may cause water flow fluctuations due to unstable water pressure or changes in water consumption during use, the calculation module first obtains the relative deviation of the real-time average water level and water pressure through the deviation calculation unit, and obtains the water level deviation and water pressure deviation respectively. Subsequently, the water flow calculation unit combines these two deviations to calculate the water flow deviation. This process enables the system to dynamically monitor changes in water flow and identify potential problems in a timely manner.

[0045] By providing real-time feedback on water level and pressure deviations, abnormal situations can be identified quickly.

[0046] Please continue reading Figure 3 As shown, it is a decision logic diagram of the second determination module in this embodiment determining the second temporary grid; Specifically, the second determination module includes: A water flow comparison unit, used to compare the water flow deviation with a preset standard water flow deviation to form a water flow comparison result; A second determining unit is connected to the water flow comparison unit, and is used to determine a plurality of second temporary grids for the water flow deviation being greater than the preset standard water flow deviation according to the water flow comparison result.

[0047] The preset standard water flow deviation refers to the range of water flow fluctuation allowed by the system under normal operating conditions. It is used to evaluate the normality of real-time water flow and depends on the historical data of the community's water pressure and water level as well as the dynamic changes in firefighting needs to ensure that it can reflect the actual operating status. It is usually set between 1% and 5%. In this embodiment, it is set to 3%, which can effectively capture slight abnormal changes and reduce false alarms without being overly sensitive to normal fluctuations.

[0048] The second determination module compares the water flow deviation calculated in real time with the preset standard water flow deviation through the water flow comparison unit to obtain a water flow comparison result. Subsequently, the second determination unit identifies several second temporary grids based on the result to further analyze the status and risks of these grids.

[0049] By comparing with preset standards, potential fire safety hazards can be quickly identified, and the system can respond quickly after the second temporary grid is determined in time.

[0050] Specifically, the determination module includes: a distribution degree calculation unit, configured to determine the distribution degree according to the second temporary grid and all adjacent second temporary grids within a preset radius; a determination unit connected to the distribution degree calculation unit, for determining that the second temporary grid is an abnormal grid when the distribution degree is less than a preset standard distribution degree, and forming a plurality of abnormal grids; A recording unit is connected to the determination unit and is used to record the duration of the abnormal grid.

[0051] The preset radius is used to determine the range of adjacent grids around the second temporary grid in order to calculate the distribution degree. Its setting depends on the actual layout of the community, the distribution density of fire-fighting facilities and the possible fire spread speed. It is usually set between 5 meters and 10 meters. In this embodiment, it is set to 8 meters, which helps to ensure that the relationship between grids is accurately evaluated within a reasonable range, thereby improving the recognition accuracy of abnormal grids.

[0052] The preset standard distribution degree is a benchmark value used to determine whether the grid distribution is normal. It depends on the layout of fire-fighting facilities in the community and historical data analysis. It is usually set between 0.1 and 0.3. In this embodiment, it is set to 0.2, which can help the system identify grids that are obviously unevenly distributed, thereby discovering potential fire risk areas early.

[0053] The determination module analyzes the spatial distribution of the second temporary grid and all adjacent second temporary grids within a preset radius through the distribution degree calculation unit to confirm the distribution degree. Then, the determination unit compares the calculated distribution degree with the preset standard distribution degree to determine which grids are identified as abnormal grids. Finally, the recording unit is responsible for recording the duration of these abnormal grids for subsequent analysis and processing.

[0054] By monitoring the distribution of grids, false alarms can be effectively reduced and the accuracy of the system can be improved. In addition, recording the duration of abnormal grids provides data support for subsequent decision-making, making it easier to formulate more effective preventive measures.

[0055] Specifically, the distribution degree calculation unit includes: a distance calculation subunit, used for calculating an average distance between each of the second temporary grids and all adjacent second temporary grids within the preset radius; The distribution degree calculation subunit is connected to the distribution degree confirmation unit and is used to calculate the relative deviation between the average distance and a preset standard distance to form a distribution degree.

[0056] The preset standard distance refers to the ideal or reference distance value set in the process of evaluating the uniformity of distribution between the second temporary grids. It reflects the expected distribution status between the grids and helps to determine whether the actual distribution meets expectations. It depends on the needs of the specific application scenario, the structural characteristics of the community, historical data and fire safety standards. It is usually set between 5 meters and 20 meters to ensure coverage of key monitoring areas. In this embodiment, it is set to 10 meters to adapt to the distribution characteristics of the grids in the community and ensure that the status of each grid can be evaluated in a timely and effective manner.

[0057] The distribution degree calculation unit calculates the average distance between each second temporary grid and the adjacent grids within the preset radius around it through the distance calculation subunit, thereby obtaining the relative position relationship between these grids. Subsequently, the distribution degree calculation subunit compares this average distance with the preset standard distance, calculates the relative deviation, and forms the final distribution degree value.

[0058] By calculating the distribution degree, the uniformity of the grid distribution can be effectively quantified, providing data support for subsequent abnormal grid judgment.

[0059] Specifically, the adjustment module includes: A quantity fluctuation calculation unit, used to calculate the standard deviation of the number of grids to form a quantity fluctuation value; An adjustment unit is used to adjust the preset grid spacing according to the grid quantity, the preset standard quantity fluctuation value and the preset adjustment coefficient when the quantity fluctuation value is greater than the preset standard quantity fluctuation value, wherein the new preset grid spacing is equal to the preset grid spacing multiplied by an adjustment factor, and the adjustment factor is 1 plus the preset adjustment coefficient multiplied by the relative deviation between the grid quantity and the preset standard quantity fluctuation value.

[0060] The preset adjustment coefficient is a value used to adjust the grid spacing. Its function is to dynamically adjust the grid spacing according to the actual situation. It depends on the characteristics of the community and the distribution density of fire-fighting facilities. It is usually set between 0.05-0.15. In this embodiment, it is set to 0.1. When the relative deviation between the grid number and the standard number fluctuation value is small, the adjustment range will not be too large, thereby ensuring the stability of the system.

[0061] The quantity fluctuation calculation unit is responsible for calculating the standard deviation of the number of grids in real time to form a quantity fluctuation value, which reflects the change in the current number of grids. When the quantity fluctuation value exceeds the preset standard quantity fluctuation value, the adjustment unit dynamically adjusts the preset grid spacing according to the current number of grids, the preset standard quantity fluctuation value and the set adjustment coefficient. This process ensures that the system can adapt to the ever-changing community environment.

[0062] When the number of grids fluctuates beyond the preset range, timely adjustment of the grid spacing can ensure the comprehensiveness and accuracy of monitoring and reduce blind spots.

[0063] Specifically, the alarm module includes: An alarm determination unit, configured to determine that an alarm needs to be sent when the duration is longer than a preset standard duration, and to form an alarm determination result; An alarm sending unit is connected to the alarm determination unit and is used to send a maintenance alarm according to the alarm determination result.

[0064] The preset standard duration is a time period set by the system. When the monitored abnormal state continues for more than this time period, the system will consider that the state has certain risks and trigger an alarm. It depends on the requirements of fire safety management, the historical data of the community and the assessment of potential risks. It is usually set between 5 minutes and 20 minutes. In this embodiment, it is set to 10 minutes, which can effectively balance the sensitivity and false alarm rate of the alarm, ensuring that the alarm is quickly issued when it is really needed, while reducing false alarms caused by short-term fluctuations.

[0065] The alarm module receives the duration data from each abnormal grid through the alarm determination unit and compares it with the preset standard duration. When the duration exceeds the preset standard, the alarm determination unit determines that an alarm needs to be sent and generates an alarm determination result. Subsequently, the alarm sending unit performs the corresponding alarm sending operation according to the determination result to notify the relevant personnel or system to take necessary measures.

[0066] By monitoring the duration of abnormal grid conditions, we can ensure that countermeasures are taken quickly before the problem escalates.

[0067] Specifically, the screening module includes: A material pile comparison unit, used to compare the real-time material pile quantity with a preset standard quantity to form a material pile comparison result; A screening unit is connected to the object pile comparison unit, and is used to screen out a plurality of grids to form a plurality of risk grids when the object pile comparison result shows that the real-time object pile quantity is greater than the preset standard quantity.

[0068] The preset standard quantity refers to the standard threshold value of the number of combustible piles set by the system under specific environments or conditions. It is used as a benchmark for evaluating potential fire risks in the grid. It depends on the characteristics of the community environment, historical fire data, fire safety regulations, and specific needs within the community. It is usually set between 1 and 5. In this embodiment, it is set to 3, which can effectively cover risk assessments under general circumstances.

[0069] The screening module compares the number of combustible piles monitored in real time with the preset standard number through the pile comparison unit to generate a pile comparison result. Subsequently, the screening unit determines which grids have piles exceeding the standard based on the result, and screens out these grids to form several risk grids. This process ensures that the system can accurately identify areas with potential fire risks.

[0070] By comparing real-time data with preset standards, the accuracy of fire monitoring can be effectively improved and suspicious areas can be identified in a timely manner.

[0071] Please continue reading Figure 4 As shown, it is a flow chart of the smart community fire big data analysis method based on artificial intelligence in this embodiment; A method for analyzing big data of firefighting in a smart community based on artificial intelligence, based on the above-mentioned big data analysis system of firefighting in a smart community based on artificial intelligence, comprising: Collect real-time images of each grid in the collection area based on preset grid spacing within the community, the real-time average water level of all water tanks, and the real-time average water pressure of all fire hydrants; Extracting the real-time pile quantity of combustible materials in each of the real-time images; Screening out a number of risk grids according to the real-time number of material piles; Determine the fluctuation consistency according to the real-time average water level and the real-time average water pressure in any two adjacent risk grids within a preset calculation time, and determine a number of first temporary grids according to the fluctuation consistency; Calculating the water flow deviation according to the real-time average water level and the real-time average water pressure of each of the first temporary grids at adjacent moments; Determine a plurality of second temporary grids according to the water flow deviation; Determine a number of abnormal grids according to the distribution degree of the second temporary grid, and record the duration; Sending an alert according to the duration; The preset grid spacing is adjusted according to the grid quantity of each abnormal grid within a preset adjustment time and a preset standard quantity fluctuation value.

[0072] By collecting real-time images, average water level and water pressure data of each grid in the community, the number of combustible piles is extracted and risk grids are screened out. Then, the fluctuation consistency is determined using the changes in water level and water pressure of adjacent risk grids, and the first temporary grid is formed based on this consistency. Subsequently, the water flow deviation is calculated to determine the second temporary grid, and the abnormal grids are determined based on the distribution of these grids, and their duration is recorded. When the duration of the abnormality exceeds the preset standard, the system will automatically send an alarm. At the same time, the preset grid spacing is dynamically adjusted based on the number of abnormal grids and the standard fluctuation value within the adjustment period to optimize the monitoring and response mechanism.

[0073] Through real-time data monitoring and intelligent analysis, it can effectively identify potential fire risks in the community, improve the early warning capability and response efficiency of fire safety, reduce the possibility of false alarms and missed alarms by accurately screening out risk grids, and dynamically adjust the grid spacing to ensure the flexibility and accuracy of the monitoring system.

[0074] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0075] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A smart community fire big data analysis system based on artificial intelligence, characterized in that: include: A data collection module is used to collect real-time images of each grid in the collection area based on the preset grid spacing within the community, the real-time average water level of all water tanks, and the real-time average water pressure of all fire hydrants; An artificial intelligence module, connected to the data acquisition module, for extracting the real-time pile quantity of combustibles in each of the real-time images; A screening module connected to the artificial intelligence module for screening out a number of risk grids according to the real-time number of material piles; A first determination module, which is connected to the screening module and the data acquisition module respectively, is used to determine the fluctuation consistency according to the real-time average water level and the real-time average water pressure in any two adjacent risk grids within a preset calculation time, and determine a number of first temporary grids according to the fluctuation consistency; a calculation module, which is connected to the data acquisition module and the first determination module respectively, and is used to calculate the water flow deviation according to the real-time average water level and the real-time average water pressure at adjacent moments of each of the first temporary grids; a second determination module, connected to the calculation module, for determining a plurality of second temporary grids according to the water flow deviation; A determination module, which is connected to the second determination module and the data acquisition module respectively, and is used to determine a number of abnormal grids according to the distribution degree of the second temporary grid, and record the duration; an alarm module, connected to the determination module, for sending an alarm according to the duration; An adjustment module is connected to the determination module and the data acquisition module respectively, and is used to adjust the preset grid spacing according to the grid quantity of each abnormal grid within a preset adjustment time and a preset standard quantity fluctuation value.

2. According to the artificial intelligence-based smart community fire big data analysis system of claim 1, it is characterized in that: The first determining module comprises: a standard deviation calculation unit, used for calculating the standard deviation of the real-time average water level to obtain the water level standard deviation, and for calculating the standard deviation of the real-time average water pressure to obtain the water pressure standard deviation; a consistency calculation unit connected to the standard deviation calculation unit, for calculating the relative deviation between the water level standard deviation and the water pressure standard deviation to form the fluctuation consistency; A first determination unit is connected to the consistency calculation unit and is used to determine a plurality of first temporary grids according to a comparison result between the fluctuation consistency and a preset standard consistency.

3. The smart community fire protection big data analysis system based on artificial intelligence according to claim 2 is characterized in that: The calculation module comprises: a deviation calculation unit, used for calculating the relative deviation of the real-time average water level to obtain the water level deviation, and for calculating the relative deviation of the real-time average water pressure to obtain the water pressure deviation; A water flow calculation unit is connected to the deviation calculation unit and is used to calculate the relative deviation between the water level deviation and the water pressure deviation to form the water flow deviation.

4. The smart community fire protection big data analysis system based on artificial intelligence according to claim 3 is characterized in that: The second determining module comprises: A water flow comparison unit, used to compare the water flow deviation with a preset standard water flow deviation to form a water flow comparison result; A second determining unit is connected to the water flow comparison unit and is used to determine a plurality of second temporary grids according to the water flow comparison result.

5. The artificial intelligence-based smart community fire big data analysis system according to claim 4 is characterized in that: The determination module comprises: a distribution degree calculation unit, configured to determine the distribution degree according to the second temporary grid and all adjacent second temporary grids within a preset radius; a determination unit connected to the distribution degree calculation unit, for determining the second temporary grid as an abnormal grid according to a comparison result between the distribution degree and a preset standard distribution degree, and forming a plurality of abnormal grids; A recording unit is connected to the determination unit and is used to record the duration of the abnormal grid.

6. The smart community fire protection big data analysis system based on artificial intelligence according to claim 5 is characterized in that: The distribution degree calculation unit comprises: a distance calculation subunit, used for calculating an average distance between each of the second temporary grids and all adjacent second temporary grids within the preset radius; The distribution degree calculation subunit is connected to the distribution degree confirmation unit and is used to calculate the relative deviation between the average distance and a preset standard distance to form a distribution degree.

7. The smart community fire protection big data analysis system based on artificial intelligence according to claim 6 is characterized in that: The adjustment module comprises: A quantity fluctuation calculation unit, used to calculate the standard deviation of the grid quantity to form a quantity fluctuation value; An adjustment unit is used to adjust the preset grid spacing according to a comparison result between the quantity fluctuation value and the preset standard quantity fluctuation value, the grid quantity, the preset standard quantity fluctuation value and a preset adjustment coefficient.

8. The smart community fire protection big data analysis system based on artificial intelligence according to claim 7 is characterized in that: The alarm module comprises: An alarm determination unit, configured to determine whether an alarm needs to be sent according to a comparison result between each of the durations and a preset standard duration, and form an alarm determination result; An alarm sending unit is connected to the alarm determination unit and is used to send an alarm according to the alarm determination result.

9. The smart community fire protection big data analysis system based on artificial intelligence according to claim 8 is characterized in that: The screening module comprises: A material pile comparison unit, used to compare the real-time material pile quantity with a preset standard quantity to form a material pile comparison result; A screening unit is connected to the object pile comparison unit and is used to screen out a plurality of grids according to the object pile comparison result to form a plurality of risk grids.

10. A method for analyzing big data of firefighting in a smart community based on artificial intelligence, based on the big data analysis system of firefighting in a smart community based on artificial intelligence according to any one of claims 1 to 9, characterized in that: include: Collect real-time images of each grid in the collection area based on the preset grid spacing within the community, the real-time average water level of each fire hydrant, and the real-time average water pressure of each water tank; Extracting the real-time pile quantity of combustible materials in each of the real-time images; Screening out a number of risk grids according to the real-time number of material piles; Determine the fluctuation consistency according to the real-time average water level and the real-time average water pressure in any two adjacent risk grids within a preset calculation time, and determine a number of first temporary grids according to the fluctuation consistency; Calculating the water flow deviation according to the real-time average water level and the real-time average water pressure of each of the first temporary grids at adjacent moments; Determine a plurality of second temporary grids according to the water flow deviation; Determine a number of abnormal grids according to the distribution degree of the second temporary grid, and record the duration; Sending an alert according to the duration; The preset grid spacing is adjusted according to the grid quantity of each abnormal grid within a preset adjustment time and a preset standard quantity fluctuation value.

Images