Intelligent venue security system fire risk assessment method

Abstract

The invention discloses an intelligent venue security system fire risk assessment method, and relates to the technical field of risk assessment. The method comprises the following steps: S1, data acquisition; step S2, data processing; s3, constructing a risk assessment index system; s4, constructing a risk assessment model; and S5, carrying out risk response. According to the method, the risk assessment model is constructed, the fire risk level and the risk level color of the fire compartment are determined according to the assessment score of the risk assessment index system, and the physical model of the smart venue building is identified, so that potential safety hazards can be found in time, and effective prevention and response measures are taken; and safe operation of the venue and life and property safety of personnel are guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of risk assessment, and particularly relates to a method for fire risk assessment of a security system in a smart venue. Background Art

[0002] In recent years, with the continuous and rapid development of the social economy and the continuous expansion of the urban scale, a large number of various large-scale smart venues such as stadiums, exhibition halls, and conference centers have emerged. These venues often have a large number of people, numerous devices, and complex functions. Once a fire occurs, it is likely to cause significant casualties and property losses, with a huge social impact.

[0003] Meanwhile, the potential safety hazards are increasing day by day, and various disaster accidents are characterized by high risks and great harms. The social public security needs are increasing exponentially. People have put forward higher requirements for the fire safety guarantee of public places such as smart venues, and a more scientific and accurate fire risk assessment method is needed to ensure the safe operation of the venues.

[0004] With the rapid development of technologies such as the Internet of Things, big data, and artificial intelligence, the security system of smart venues has been continuously upgraded and improved, and can collect a large amount of data related to fire risks in real time, such as environmental temperature, smoke concentration, and the operating status of electrical equipment. However, how to effectively utilize these massive data for accurate fire risk assessment is an urgent problem to be solved.

[0005] Most traditional fire risk assessment methods are based on historical data and experience, lack the effective utilization of real-time data, and are difficult to dynamically and accurately reflect the current fire risk situation of smart venues.

[0006] Some assessment methods based on the Analytic Hierarchy Process (AHP) can build a relatively systematic index system to a certain extent, but there are problems such as strong subjectivity in determining index weights and insufficient consideration of the dynamic relationships between indexes in complex systems.

[0007] When dealing with the diverse and intelligent security devices and complex network environments in smart venues, the existing assessment methods often seem powerless and cannot comprehensively and accurately assess the fire risk. For example, for the fire risk caused by potential security vulnerabilities in a large number of Internet of Things devices in smart venues, traditional assessment methods are difficult to effectively cover. Summary of the Invention

[0008] The purpose of the present invention is to provide a method for fire risk assessment of a security system in a smart venue. By constructing a risk assessment model and determining the fire risk level and risk level color of the fire compartment according to the assessment scores of the risk assessment index system, and marking them on the physical model of the smart venue building, the problems of untimely discovery of existing potential safety hazards and the inability to take effective preventive and response measures are solved.

[0009] To solve the above technical problems, the present invention is implemented through the following technical solutions: The present invention relates to a method for evaluating the fire risk of a security system in an intelligent venue, comprising the following steps: Step S1, data collection: The data center collects the building drawings of the intelligent venue, the data of fire-fighting facilities in the intelligent venue, the data of the electrical system, and the data of personnel activities; Step S2, data processing: Preprocess the collected data; Step S3, construction of the risk assessment index system: Divide the risk assessment index system into five categories, specifically including building structure and layout, fire-fighting facilities and systems, electrical systems, human factors, and management factors; Step S4, construction of the risk assessment model: Construct a risk assessment model, and determine the fire risk level and the color of the risk level of this fire compartment according to the evaluation scores of the risk assessment index system, and mark it in the physical model of the intelligent venue building; Step S5, risk response: Obtain the risk response plan through the color of the risk level in the physical model of the intelligent venue building.

[0010] As a preferred technical solution, in step S1, collect the building drawings of the intelligent venue and obtain the building material types, fire compartment divisions, and evacuation passage layouts of the intelligent venue to construct the physical model of the intelligent venue building. The specific construction process is as follows: Step S11: Obtain the basic information of the building drawings of the intelligent venue building; Step S12: Mark the building drawings through 3D modeling software; Step S13: Use the software drawing tool to draw the basic outline of the building according to the dimensions on the drawings, and convert the two-dimensional plane graph into a three-dimensional solid model; Step S14: Add doors, windows, stairs, elevators, and the internal structure of the building to the three-dimensional solid model; Step S15: Select the corresponding materials in the material library of the 3D modeling software according to the obtained building material information.

[0011] As a preferred technical solution, in step S12, before importing the basic information of the building drawings of the intelligent venue building into the 3D modeling software, it is necessary to process the sectional drawings of the actually measured intelligent venue by layers to generate a complete CAD actually measured intelligent venue fire-fighting facilities drawing; determine the connection positions of the lines according to the fire-fighting facilities completion drawings, connect the lines with the same row as the same number to complete the line connection between the fire-fighting facilities; and save them one by one according to the fire-fighting equipment numbers, and determine the base point of the model according to the geographical coordinates of the fire-fighting equipment.

[0012] As a preferred technical solution, in the step S13, the specific process of converting the two-dimensional planar graph into a three-dimensional solid model is as follows: Step S131: In the software drawing tool, create all the building components, fire protection facilities, and electrical systems of the intelligent venue, and assign names and descriptions; Step S132: Define the starting insertion point of the fire protection facilities, and define the subordinate relationship between the building components and the fire protection facilities and the connection relationship between the fire protection facilities; Step S133: Select basic primitives to establish the shape of the fire protection facilities, and place them according to the geographical coordinates of the fire equipment; Step S134: When the addition of the fire protection facilities is completed, add basic information and GIM parameter attributes to the fire protection facilities.

[0013] As a preferred technical solution, in the step S2, the preprocessing of the collected data includes: data cleaning, data denoising, data normalization, data smoothing, feature selection, and data dimensionality reduction; When performing data cleaning, deal with the noise, missing values, and outliers in the data. For missing value processing, such as the formula: , which is used for mean filling; where is the valid data, is the number of valid data; or use the linear interpolation algorithm: , where and are the data at adjacent time points and ; when dealing with outliers, if or , then is an outlier, and are the first quartile and the third quartile respectively, .

[0014] When performing data normalization, scale the data to a unified range to eliminate the influence of dimensions, that is: ; When performing data smoothing, eliminate the short-term fluctuations in the data and highlight the long-term trend; achieve smoothing through local polynomial fitting: ; Where is the filtering coefficient, is the window size; When performing feature selection, it is necessary to calculate the correlation coefficient between the feature and the target variable based on the correlation of the data. The specific calculation formula is as follows: ; In the formula, represents the Pearson correlation coefficient, represents the number of samples, represents the - th eigenvalue of the sample, represents the - th target value of the sample, represents the mean value of the feature ; represents the mean value of the variable ; When performing data dimensionality reduction processing, dimensionality reduction is achieved by optimizing the KL divergence: ; In the formula, and respectively represent the similarities in high - dimensional and low - dimensional spaces.

[0015] As a preferred technical solution, in step S3, the building structure and layout, fire protection facilities and systems, electrical systems, human factors, and management factors are classified as first - level indicators. Each first - level indicator is further divided into multiple second - level indicators. A risk calculation expression is constructed by multiplying the weight of the risk event by the occurrence of the risk event. The specific calculation formula is as follows: ; In the formula, is the final score of the risk calculation, are the weights of the five first - level risk events of the building structure and layout, fire protection facilities and systems, electrical systems, human factors, and management factors respectively, is the weight of the second - level risk event under this first - level risk, is the occurrence of this second - level risk event.

[0016] As a preferred technical solution, the final score of the risk calculation is divided into 5 grade scales of extremely low, low, medium, high, and extremely high according to the probability of risk occurrence, corresponding to the numerical levels 1 - 5; the severity of the risk is divided into 5 grade scales according to the serious consequences of the risk, namely extremely small, small, medium, large, and extremely large, corresponding to the numerical levels 1 - 5.

[0017] As a preferred technical solution, in step S4, the specific process of constructing the risk assessment model is as follows: Step S41: Determine the evaluation factor set and the index set ; Step S42: According to each factor for the index Membership degree constitutes a fuzzy relation matrix ; Step S43: Determine the weight vector ; Step S44: Calculate the comprehensive evaluation result ; Step S45: Obtain the rescue plan according to the comprehensive evaluation result and evaluation factors.

[0018] As a preferred technical solution, in the step S42, let the factor set and the index set , then the membership degree of each factor to the index constitutes a fuzzy relation matrix , and the specific formula is as follows:

[0019] In the formula, is obtained by expert scoring or historical data statistics.

[0020] As a preferred technical solution, in the step S43, the normalized value of each column in the fuzzy relation matrix is calculated as: , and then the weight vector is calculated.

[0021] As a preferred technical solution, after the weight vector is calculated, a consistency test is also required; the consistency test process is as follows: Calculate the consistency index , and then calculate the consistency ratio ; In the formula, represents the maximum eigenvalue of the judgment matrix, represents the random consistency index.

[0022] As a preferred technical solution, in the step S44, the evaluation result ; Among them, is a fuzzy composition operator: , .

[0023] The present invention has the following beneficial effects: (1) The present invention constructs a risk assessment model, determines the fire risk level and risk level color of the fire compartment according to the evaluation scores of the risk assessment index system, and marks them in the physical model of the intelligent venue building, so as to timely discover potential safety hazards, take effective preventive and response measures, and ensure the safe operation of the venue and the safety of the lives and property of personnel. (2) The present invention comprehensively utilizes multi-source information such as environmental data, equipment data, and personnel data, monitors and analyzes the data in real time, realizes the dynamic assessment and early warning of fire risks, timely discovers and eliminates safety hazards, and improves the comprehensiveness and accuracy of fire risk assessment. (3) The present invention automatically triggers corresponding early warning and disposal measures according to different risk levels, improves the efficiency and effect of fire prevention and control, and at the same time uses machine learning algorithms to enable the model to continuously learn and improve, and improve the intelligent level of fire risk assessment.

[0024] Of course, any product implementing the present invention does not necessarily need to achieve all the above-mentioned advantages simultaneously. Description of the Drawings

[0025] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0026] Figure 1 It is a flowchart of a method for fire risk assessment of an intelligent venue security system of the present invention. Detailed Embodiments

[0027] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0028] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0029] In order to make the purpose, technical solutions and advantages of the present application clearer, the following Figure 1 and embodiments are used to further describe the present application in detail. It should be understood that the specific embodiments described here are only used to explain the present application and are not used to limit the present application.

[0030] Please refer toFigure 1 As shown in the figure, the present invention is a method for fire risk assessment of a smart venue security system, including the following steps: Step S1, data collection: The data center collects the building drawings of the smart venue, the data of fire protection facilities in the smart venue, the data of the electrical system, and the data of personnel activities; Step S2, data processing: Preprocess the collected data; Step S3, construction of the risk assessment index system: Divide the risk assessment index system into five categories, specifically including building structure and layout, fire protection facilities and systems, electrical systems, personnel factors, and management factors; Step S4, construction of the risk assessment model: Construct a risk assessment model, and determine the fire risk level and the color of the risk level of this fire compartment according to the assessment scores of the risk assessment index system, and mark them on the physical model of the smart venue building; Step S5, risk response: Obtain the risk response plan through the color of the risk level in the physical model of the smart venue building.

[0031] In step S1, collect the building drawings of the smart venue and obtain the building material types, fire compartment divisions, and evacuation passage layouts of the smart venue to construct the physical model of the smart venue building. The specific construction process is as follows: Step S11: Obtain the basic information of the building drawings of the smart venue, including floor plans, elevation views, sectional views, details, etc., understand the overall structure, spatial layout, dimensional scale, connection relationships between various parts, etc. of the building, and clarify key information such as the functional partitions, door and window positions, wall thicknesses, floor heights, etc. of the building; In addition to the building drawings, collect other materials related to the building, such as information on the specifications, colors, textures of building materials, and materials on the surrounding environment, topography, etc., to provide reference for subsequent model construction and improvement; Step S12: Mark the building drawings through 3D modeling software; Step S13: Use the software drawing tool to draw the basic outline of the building according to the dimensions on the drawings, and convert the two-dimensional plane graph into a three-dimensional solid model; Step S14: Add doors, windows, stairs, elevators, and internal structures of the building to the three-dimensional solid model; Step S15: Select the corresponding materials in the material library of the 3D modeling software according to the obtained building material information.

[0032] In step S12, before importing the basic information of the intelligent venue building drawings into the 3D modeling software, it is necessary to process the cross-sectional drawings of the actual measured intelligent venue by layers to generate a complete CAD drawing of the fire protection facilities of the actual measured intelligent venue; determine the connection positions of the lines according to the fire protection facilities completion drawings, connect the lines with the same row numbered the same, and complete the line connection between the fire protection facilities; and save them one by one according to the fire protection equipment numbers, and determine the base points of the model according to the geographical coordinates of the fire protection equipment.

[0033] In step S13, the specific process of converting the 2D planar graph into a 3D solid model is as follows: Step S131: Create all the building components, fire protection facilities, and electrical systems of the intelligent venue in the software drawing tool and assign names and descriptions to them; Step S132: Define the starting insertion points of the fire protection facilities, and define the subordinate relationship between the building components and the fire protection facilities as well as the connection relationship between the fire protection facilities; Step S133: Select the basic primitives to establish the shapes of the fire protection facilities and place them according to the geographical coordinates of the fire protection equipment; Step S134: When the addition of the fire protection facilities is completed, add basic information and GIM parameter attributes to the fire protection facilities.

[0034] In step S2, the preprocessing of the collected data includes: data cleaning, data denoising, data normalization, data smoothing, feature selection, and data dimensionality reduction; When performing data cleaning, deal with the noise, missing values, and outliers in the data. For missing value processing, such as the formula: , which is used for mean filling; where is the valid data, is the number of valid data; or use the linear interpolation algorithm: , where and are the data at adjacent time points and ; when dealing with outliers, if or , then is an outlier, and are the first quartile and the third quartile respectively, .

[0035] When performing data normalization, scale the data to a unified range to eliminate the influence of the dimension, that is: ; When performing data smoothing, eliminate the short-term fluctuations in the data and highlight the long-term trend; achieve smoothing through local polynomial fitting: ; In the formula, is the filtering coefficient, is the window size; When performing feature selection, it is necessary to calculate the correlation coefficient between the feature and the target variable based on the correlation of the data. The specific calculation formula is as follows: ; In the formula, represents the Pearson correlation coefficient, represents the number of samples, represents the -th eigenvalue of the sample, represents the -th target value of the sample, represents the mean value of the feature ; represents the mean value of the variable ; When performing data dimensionality reduction processing, dimensionality reduction is achieved by optimizing the KL divergence: ; In the formula, and respectively represent the similarities in the high - dimensional and low - dimensional spaces.

[0036] In step S3, the building structure and layout, fire protection facilities and systems, electrical systems, human factors, and management factors are classified as first - level indicators. Each first - level indicator is further divided into multiple second - level indicators. For example, under the building structure and layout, the building fire resistance rating, fire compartment area, evacuation passage width, etc. can be set; under the fire protection facilities and systems, the integrity rate of the fire alarm system, coverage rate of the fire extinguishing system, etc. can be set; under the electrical system, the safe operation rate of electrical equipment, integrity rate of lines, etc. can be set; under human factors, the personnel density, fire safety training rate, etc. can be set; under management factors, the perfection degree of fire safety systems, frequency of emergency plan drills, etc. are used. The calculation method of multiplying the weight of the risk event by the occurrence situation of the risk event is used to construct the risk calculation expression. The specific calculation formula is as follows: ; In the formula, is the final score of the risk calculation, are the weights of the five first - level risk events of the building structure and layout, fire protection facilities and systems, electrical systems, human factors, and management factors respectively, is the weight of the second - level risk event under this first - level risk, is the occurrence situation of this second - level risk event.

[0037] It is also possible to further refine the tertiary risk indicators under secondary risks. For example, under the secondary indicator of evacuation passage width, it can be specific to the actual width measurement values of evacuation passages in different areas; under the integrity rate of the fire alarm system, it can include the integrity of specific devices such as detectors and alarms, etc.

[0038] Risk analysis is a process that considers the likelihood of risk occurrence and the severity of consequences. Its core goal is to deeply explore the potential threats of each risk type on the basis of risk identification, so as to comprehensively understand the possible impacts. The final score of risk calculation is divided into 5 grade scales of extremely low, low, medium, high, and extremely high according to the probability of risk occurrence, corresponding to digital levels 1 to 5 respectively; the severity of risk is divided into 5 grade scales according to the serious consequences caused by the risk, namely extremely small, small, medium, large, and extremely large, corresponding to digital levels 1 to 5.

[0039] Among them, the risk matrix formed by the final score of risk calculation and the severity of risk is shown in the following table, and the result of risk assessment is obtained by the product of the two.

[0040]

[0041] In step S4, the specific process of constructing the risk assessment model is as follows: Step S41: Determine the evaluation factor set and the index set ; Step S42: According to each factor for the index of the membership degree to form a fuzzy relation matrix ; Step S43: Determine the weight vector ; Step S44: Calculate the comprehensive evaluation result ; Step S45: Obtain the rescue plan according to the comprehensive evaluation result and the evaluation factors.

[0042] Use the analytic hierarchy process to construct a judgment matrix and calculate the weights of each index; the constructed structural hierarchy includes: Goal layer: Fire risk level.

[0043] Criterion layer: Environmental factor, equipment factor, personnel factor.

[0044] Scheme layer: Specific indicators (such as temperature, smoke concentration, personnel density, etc.) In step S42, let the factor set and the index set , then each factor for the index Membership degree constitutes a fuzzy relation matrix The specific formula is as follows:

[0045] In the formula, is obtained by expert scoring or historical data statistics.

[0046] In step S43, calculate the fuzzy relation matrix The normalization value of each column in is: , and then calculate the weight vector .

[0047] After the weight vector calculation is completed, a consistency check is also required; the consistency check process is as follows: Calculate the consistency index , and then calculate the consistency ratio ; In the formula, represents the maximum eigenvalue of the judgment matrix, represents the random consistency index. Generally, the consistency ratio , and the judgment matrix passes the consistency check.

[0048] In step S44, the evaluation result ; Among them, is a fuzzy composition operator: , .

[0049] It should be noted that in the above system embodiments, the included units are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0050] In addition, those of ordinary skill in the art can understand that all or part of the steps in implementing the above method embodiments can be completed by instructing relevant hardware through a program, and the corresponding program can be stored in a computer-readable storage medium.

[0051] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and changes can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and utilize the present invention well. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A fire risk assessment method for a smart venue security system, characterized in that: The steps include: Step S1, data collection: the data center collects architectural drawings of the smart venue, fire protection facility data, electrical system data and personnel activity data in the smart venue; Step S2, data processing: preprocessing the collected data; Step S3, constructing a risk assessment indicator system: the risk assessment indicator system is divided into five categories, including building structure and layout, fire protection facilities and systems, electrical systems, personnel factors, and management factors; Step S4, risk assessment model construction: construct a risk assessment model, and determine the fire risk level and risk level color of the fire zone according to the assessment score of the risk assessment indicator system, and mark it on the physical model of the smart venue building; Step S5, risk response: obtain the risk response plan through the risk level color in the physical model of the smart venue building.

2. According to claim 1, a fire risk assessment method for a smart venue security system is characterized in that: In step S1, the smart venue architectural drawings are collected and the building material types, fire protection area divisions, and evacuation channel layouts of the smart venue are obtained to construct a physical model of the smart venue building. The specific construction process is as follows: Step S11: Obtain basic information of the smart venue building drawings; Step S12: annotating the building drawings using 3D modeling software; Step S13: using software drawing tools to draw the basic outline of the building according to the dimensions on the drawing, and converting the two-dimensional plane figure into a three-dimensional model; Step S14: adding doors, windows, stairs, elevators and internal structures of the building to the three-dimensional model; Step S15: According to the acquired building material information, select a corresponding material in the material library of the 3D modeling software.

3. According to claim 2, a fire risk assessment method for a smart venue security system is characterized in that: In step S12, before the basic information of the smart venue building drawings is imported into the 3D modeling software, the cross-sectional drawings of the measured smart venue need to be processed layer by layer to generate a complete CAD measured smart venue fire protection facility drawing; the connection position of the line is determined according to the fire protection facility completion drawing, and the lines are connected with the same row as the same number to complete the line connection between the fire protection facilities; and they are saved one by one according to the fire protection equipment number, and the base point of the model is determined according to the geographical coordinates of the fire protection equipment.

4. According to claim 2, a fire risk assessment method for a smart venue security system is characterized in that: In step S13, the specific process of converting the two-dimensional plane figure into a three-dimensional stereoscopic model is as follows: Step S131: In the software drawing tool, create the building components, fire protection facilities, and electrical systems of all smart venues and give them names and descriptions; Step S132: defining the starting insertion point of the fire-fighting facility, and defining the subordinate relationship between the building components and the fire-fighting facilities and the connection relationship between the fire-fighting facilities; Step S133: Select basic graphic elements to establish the appearance of fire-fighting facilities, and place them according to the geographical coordinates of the fire-fighting equipment; Step S134: When the fire-fighting facilities are added, basic information and GIM parameter attributes are added to the fire-fighting facilities.

5. According to claim 1, a fire risk assessment method for a smart venue security system is characterized in that: In step S2, the preprocessing of the collected data includes: data cleaning, data denoising, data normalization, data smoothing, feature selection and data dimension reduction; When performing feature selection, it is necessary to calculate the correlation coefficient between the feature and the target variable based on the correlation of the data. The specific calculation formula is as follows: ； In the formula, represents the Pearson correlation coefficient, represents the number of samples, Indicates The characteristic value of the sample, Indicates The target value of samples, Representation characteristics The mean of Representation variables The mean of .

6. According to claim 1, a fire risk assessment method for a smart venue security system is characterized in that: In step S3, the building structure and layout, fire protection facilities and systems, electrical systems, personnel factors, and management factors are divided into primary indicators, and each primary indicator is subdivided into multiple secondary indicators. The risk calculation expression is constructed by multiplying the weight of the risk event by the occurrence of the risk event. The specific calculation formula is as follows: ； In the formula, The final score for risk calculation is They are the weights of five first-level risk events: building structure and layout, fire protection facilities and systems, electrical systems, human factors, and management factors. is the weight of the second-level risk event under the first-level risk, The occurrence of the secondary risk event.

7. According to claim 6, a fire risk assessment method for a smart venue security system is characterized in that: The final score of the risk calculation is divided into five levels according to the probability of risk occurrence, namely very low, low, medium, high, and extremely high, corresponding to numbers 1 to 5 respectively; the risk severity is divided into five levels according to the serious consequences of the risk, namely very small, small, medium, large, and extremely large, corresponding to numbers 1 to 5 respectively.

8. According to claim 1, a fire risk assessment method for a smart venue security system is characterized in that: In step S4, the specific process of constructing the risk assessment model is as follows: Step S41: Determine the evaluation factor set And the indicator set ; Step S42: Based on each factor For indicators Membership Constructing the fuzzy relationship matrix ; Step S43: Determine the weight vector ; Step S44: Calculate comprehensive evaluation results ; Step S45: Obtain a rescue plan based on the comprehensive evaluation results and evaluation factors.

9. The fire risk assessment method for a smart venue security system according to claim 8 is characterized in that: In step S42, it is assumed that the factor set and indicator set , then each factor For indicators Membership Constructing the fuzzy relationship matrix The specific formula is as follows: , In the formula, Obtained through expert scoring or historical data statistics.

10. The method for fire risk assessment of a smart venue security system according to claim 8, characterized in that: In step S43, the fuzzy relationship matrix is ​​calculated. The normalized value of each column in is: , and then calculate the weight vector .

11. The method for fire risk assessment of a smart venue security system according to claim 10, characterized in that: After the weight vector is calculated, a consistency check is required; the consistency check process is as follows: Calculate consistency index , and then calculate the consistency ratio ; In the formula, represents the maximum eigenvalue of the judgment matrix, Represents a random consistency indicator.

12. A fire risk assessment method for a smart venue security system according to claim 8, characterized in that: In step S44, the evaluation result ;in, is the fuzzy synthesis operator: , .

Images