Fire safety inspection and evaluation method, system, computer equipment and storage medium

Abstract

The present invention relates to the technical field of inspection effect rating, and discloses a fire safety inspection evaluation method, system, computer equipment and storage medium, and constructs a fire safety inspection evaluation index system, wherein the index system includes multiple independent indicators and multiple related indicators; historical inspection data and actual inspection results are obtained; based on the historical inspection data, the comprehensive weights of each independent indicator and each related indicator in the index system are calculated respectively; based on the historical inspection data and the actual inspection results, the index scores of each independent indicator and each related indicator in the index system are calculated respectively; based on the actual inspection results, the related indicator coefficients of each related indicator are calculated; based on the comprehensive weights, the index scores and the related indicator coefficients, the total scores of all indicators in the index system are calculated; and the fire safety inspection effect is rated based on the total score. The present invention effectively reduces the workload of inspection effect evaluation and improves the efficiency of inspection effect evaluation.

Description

Technical Field

[0001] The present invention relates to the technical field of inspection effect rating, and in particular to a fire safety inspection evaluation method, system, computer equipment and storage medium. Background Art

[0002] At present, the size of key firefighting units is large, and fire safety issues are becoming increasingly complex and diverse. Inspectors help key firefighting units to promptly discover and eliminate safety issues through regular inspections and supervision. They are the key force to ensure that key firefighting units comply with production safety regulations and prevent accidents. In order to improve the effectiveness of fire safety inspections, it is necessary to reasonably evaluate the inspection results of inspectors, promote the standardization of the inspection team, and improve the inspection capabilities of inspectors.

[0003] At present, the evaluation of the inspection effect of fire safety inspectors in key fire-fighting units is mainly for the evaluation units to set evaluation indicators and scores. The evaluated objects, i.e. the inspectors, need to conduct self-inspections item by item according to the assessment indicators, and the evaluation units will score them item by item based on the inspectors' self-inspection materials. The setting of the indicator system is highly subjective and difficult to apply to the inspection and evaluation of fire safety inspectors. In addition, when the number of evaluation objects is large and the evaluation content is complex, the lagging method of manual evaluation will greatly increase the workload of fire safety inspection and evaluation of personnel. It is necessary to explore the setting of indicator systems and evaluation methods suitable for the evaluation of inspection effects of fire safety inspectors. Summary of the invention

[0004] In view of this, the present invention provides a fire safety inspection and evaluation method, system, computer device and storage medium to solve the problem of strong subjectivity and low evaluation efficiency in setting fire safety inspection and evaluation indicators by fire safety inspectors.

[0005] In a first aspect, the present invention provides a fire safety inspection and evaluation method, the method comprising:

[0006] Construct a fire safety inspection and evaluation index system, which includes multiple independent indicators and multiple related indicators;

[0007] Obtain historical inspection data and actual inspection results;

[0008] Calculate the comprehensive weight of each independent indicator and each related indicator in the indicator system based on historical inspection data;

[0009] Calculate the indicator scores of each independent indicator and each related indicator in the indicator system based on historical inspection data and actual inspection results;

[0010] Calculate the correlation index coefficient of each correlation index based on the actual inspection results;

[0011] Calculate the total score of all indicators in the indicator system based on comprehensive weights, indicator scores and related indicator coefficients;

[0012] Rating of fire safety inspection effectiveness is based on the total score.

[0013] The fire safety inspection and evaluation method provided by the present invention constructs a fire safety inspection and evaluation index system, and divides the index system into multiple independent indicators and multiple related indicators, makes full use of historical inspection data and actual inspection results, calculates the comprehensive weight, index score and related index coefficient of each indicator, and then obtains the total score of all indicators, and rates the fire safety inspection effect based on the total score, effectively reducing the workload of inspection effect evaluation, improving the efficiency of inspection effect evaluation, and realizing standardized, dynamic and precise evaluation of fire safety inspection effects, which can reduce the workload of inspection effect evaluation, reduce the subjectivity in evaluation work, and promote transparency and fairness of inspection evaluation, which is helpful to standardize the safety inspection team and improve the overall safety inspection level of inspectors for fire protection key units. The problem of strong subjectivity and low evaluation efficiency of fire safety inspection and evaluation effect index setting of fire safety inspectors is solved.

[0014] In an optional implementation, constructing a fire safety inspection evaluation index system includes:

[0015] Obtain inspection type, inspection standard and inspection content;

[0016] The Delphi method and analytic hierarchy process are used to construct a fire safety inspection effect evaluation index system consisting of primary, secondary and tertiary indicators based on inspection type, inspection standard and inspection content;

[0017] The explanatory structural model is used to divide the three-level indicators into multiple independent indicators and multiple related indicators.

[0018] The fire safety inspection and evaluation method provided by the present invention adopts the Delphi method and the hierarchical analysis method to construct a fire safety inspection effect evaluation index system including primary indicators, secondary indicators and tertiary indicators based on the inspection type, inspection standard and inspection content, and adopts the explanatory structure model to divide the tertiary indicators into multiple independent indicators and multiple related indicators, thereby achieving the purpose of constructing a multi-dimensional fire safety inspection evaluation index system in combination with the actual inspection situation, making the constructed index system more standardized, and providing an index basis for the subsequent calculation of the comprehensive weight of the index and the index score.

[0019] In an optional implementation, calculating the comprehensive weight of each independent indicator and each associated indicator in the indicator system based on the historical inspection data includes:

[0020] Get the historical weight time series in the historical check data for each independent indicator and each associated indicator;

[0021] The unit root test algorithm is used to check whether the distribution of the historical weighted time series is stable, and the difference operation is performed on the non-stationary time series until the time series distribution is in a stable state, and the difference order is obtained;

[0022] Determine the autoregressive order model and the moving average order model in the time series under the stationary state;

[0023] Based on the autoregressive order model, the difference order and the moving average order model, the autoregressive integrated moving average model is used to fit the time series under the steady state, and the comprehensive weight of each independent indicator and each related indicator is calculated.

[0024] The fire safety inspection and evaluation method provided by the present invention calculates the autoregressive order, differential order and moving average order based on historical inspection data, and uses the autoregressive integral sliding average model to fit the time series in a stable state, and calculates the comprehensive weight of each independent indicator and each related indicator, thereby reducing the calculation error of the comprehensive weight and making the calculation of the comprehensive weight more scientific and reasonable, thereby providing a data basis for the subsequent calculation of the total score of the indicator.

[0025] In an optional implementation, the independent indicator and the associated indicator have linear characteristics or nonlinear characteristics;

[0026] When the independent indicators and the related indicators have linear characteristics, the indicator scores of each independent indicator and each related indicator in the indicator system are calculated based on the historical inspection data and the actual inspection results, including:

[0027] When the independent indicator and the associated indicator have linear characteristics, the historical inspection data and the actual inspection results corresponding to each independent indicator and each associated indicator are obtained;

[0028] Filter the highest inspection sample data and the lowest inspection sample data for each independent indicator and each associated indicator from the historical inspection data;

[0029] Based on the highest inspection sample data and the lowest inspection sample data, the autoregressive integrated moving average model is used to determine the highest inspection standard and the lowest inspection standard for each independent indicator and each associated indicator; the highest inspection standard corresponds to the preset full score value, and the lowest inspection standard corresponds to zero score;

[0030] Calculate the indicator unit score based on the highest inspection standard and the lowest inspection standard;

[0031] Calculate the indicator score of each independent indicator and each associated indicator based on the indicator unit score and the actual inspection results of the corresponding indicator;

[0032] When independent indicators and related indicators have nonlinear characteristics, the indicator scores of each independent indicator and each related indicator in the indicator system are calculated based on historical inspection data and actual inspection results, including:

[0033] When independent indicators and related indicators have nonlinear characteristics, the highest inspection standard and the lowest inspection standard for each independent indicator and each related indicator are determined by using the expert scoring method and the Delphi method based on historical inspection data and actual inspection results;

[0034] Calculate the indicator unit score based on the highest inspection standard and the lowest inspection standard;

[0035] The indicator scores of each independent indicator and each associated indicator are calculated based on the indicator unit scores and the actual inspection results of the corresponding indicators.

[0036] The fire safety inspection and evaluation method provided by the present invention analyzes and refines historical inspection data and actual inspection results, and scientifically determines the zero score and full score standards for each independent indicator and each related indicator through the linear or nonlinear characteristics of the indicators, thereby improving the calculation accuracy of each indicator score, achieving the purpose of scientifically and reasonably calculating each indicator score, fitting the actual inspection work, and providing objective and fair indicator scores for subsequent fire safety inspection and evaluation.

[0037] In an optional implementation, calculating the correlation index coefficient of each correlation index based on the actual inspection result includes:

[0038] Get the actual inspection results corresponding to each associated indicator;

[0039] The piecewise function is used to determine the reasonable interval division result of each correlation index and the corresponding correlation index coefficient;

[0040] Based on the reasonable interval division results and the corresponding correlation index coefficients, the corresponding correlation index coefficients are determined according to the reasonable intervals where the actual inspection results are located.

[0041] In the fire safety inspection and evaluation method provided by the present invention, the correlation index plays a relatively important role in the evaluation of the fire safety inspection effect. Based on the reasonable interval division result and the corresponding correlation index coefficient, the corresponding correlation index coefficient is determined according to the reasonable interval where the actual inspection result is located. The calculated correlation index coefficient reflects the important influence of the correlation index on the overall fire safety inspection effect, fits the actual fire safety inspection situation, makes the calculated correlation index coefficient more scientific and reasonable, and provides a coefficient basis for the subsequent calculation of the total score of all indicators.

[0042] In an optional implementation, rating the fire safety inspection effect based on the total score includes:

[0043] Use estimation method to set the passing score;

[0044] The inspection results are ranked from high to low according to the total score;

[0045] Based on the passing score and the ranking of inspection results, a piecewise function is used to determine the inspection effect level;

[0046] Fire safety inspections are rated based on the inspection effectiveness level to obtain evaluation results.

[0047] The fire safety inspection and evaluation method provided by the present invention adopts an estimation method to set a passing score line; ranks the inspection effects from high to low according to the total score; determines the inspection effect level by adopting a piecewise function based on the passing score line and the inspection effect ranking; and rates the fire safety inspection based on the inspection effect level to obtain an evaluation result, thereby promoting the transparency of the fire safety inspection and evaluation and improving the objectivity, fairness and accuracy of the fire safety inspection and evaluation.

[0048] In an optional implementation, the fire safety inspection and evaluation method further includes:

[0049] Conduct behavioral risk warnings and formulate reward and punishment measures based on the evaluation results.

[0050] The fire safety inspection and evaluation method provided by the present invention carries out behavioral risk warning and formulates reward and punishment measures according to the evaluation results, which helps to standardize the safety inspection team and improve the overall safety inspection level.

[0051] In a second aspect, the present invention provides a fire safety inspection and evaluation system, which includes: an emergency management data platform, a data call module, a rule setting module, an inspection and evaluation module, and a behavior risk warning module;

[0052] The data calling module is used to obtain historical inspection data and actual inspection results from the emergency management data platform;

[0053] The rule setting module communicates with the data calling module. The rule setting module is used to construct a fire safety inspection evaluation index system, which includes multiple independent indicators and multiple related indicators; based on historical inspection data, the comprehensive weight of each independent indicator and each related indicator in the index system is calculated respectively;

[0054] The inspection and evaluation module communicates with the rule setting module. The inspection and evaluation module is used to calculate the index scores of each independent index and each associated index in the index system based on the historical inspection data and the actual inspection results; calculate the associated index coefficient of each associated index based on the actual inspection results, and calculate the total score of all indicators in the index system based on the comprehensive weight, the index score and the associated index coefficient, and rate the fire safety inspection effect based on the total score;

[0055] The behavior risk warning module communicates with the inspection and evaluation module, and the behavior risk warning module is used to carry out behavior risk warning.

[0056] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the fire safety inspection and evaluation method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0057] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the fire safety inspection and evaluation method of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1 is a flow chart of a fire safety inspection and evaluation method according to an embodiment of the present invention;

[0060] Figure 2 is a flow chart of another fire safety inspection and evaluation method according to an embodiment of the present invention;

[0061] Figure 3 is a flow chart of another fire safety inspection and evaluation method according to an embodiment of the present invention;

[0062] Figure 4 is a structural block diagram of a fire safety inspection and evaluation system according to an embodiment of the present invention;

[0063] Figure 5 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0064] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0065] According to an embodiment of the present invention, an embodiment of a fire safety inspection and evaluation method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0066] In this embodiment, a fire safety inspection and evaluation method is provided. Figure 1 is a flow chart of a fire safety inspection and evaluation method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0067] Step S101, constructing a fire safety inspection and evaluation index system, the index system includes multiple independent indicators and multiple related indicators.

[0068] For example, taking the inspection work of fire safety inspectors as an example, when constructing a fire safety inspection evaluation index system, multiple dimensions of indicators can be selected based on safety inspection laws and regulations, departmental regulations, standard requirements, and actual needs of safety inspection work. According to the inspection content, inspection standards, and inspection types in the actual work of fire safety inspectors, a fire safety inspection index system suitable for fire safety inspectors can be constructed in a hierarchical manner. For example: the fire safety inspection index system for fire safety inspectors can include three-level indicators. The first-level indicators can include indicators such as inspection process, inspection quality, and professional skills. The second-level indicators are determined on the basis of the first-level indicators. The inspection quality indicators in the first-level indicators can be divided into second-level indicators such as the safety status of key fire units and personal inspection effects. The third-level indicators are determined on the basis of the second-level indicators. The safety status of key fire units in the second-level indicators is divided into three-level indicators such as the self-inspection status of key fire units, the occurrence of work-related injuries in key fire units, the occurrence of accidents in key fire units, and the actual risk reduction of key fire units according to the inspection standards.

[0069] According to the importance of the indicators, the last-level indicators are divided into related indicators and independent indicators. Related indicators refer to indicators that are highly correlated with other indicators. A single related indicator can preliminarily determine the difficulty of the inspection and the tone of the inspection quality, and have a greater impact on the overall fire safety inspection. For example, the two indicators "Real Risk Degradation of Key Fire Units" and "Accidents in Key Fire Units" in the three-level indicator example are used as related indicators. The larger the actual risk degradation of the key fire units, the more in-place the inspection work is. The fire safety inspector should judge the overall fire safety inspection to be relatively good under the condition that the inspection performance of other indicators is equivalent. The more serious the accident in the key fire unit, the fire safety inspector should judge the overall fire safety inspection to be relatively poor under the condition that the inspection performance of other indicators is equivalent. Independent indicators refer to indicators that are relatively independent. A single independent indicator cannot determine the difficulty of the inspection and the tone of the inspection quality, and have a relatively small impact on other indicators and the overall fire safety inspection, such as the "Self-inspection of Key Fire Units" indicator in the three-level indicator example.

[0070] Step S102, obtaining historical inspection data and actual inspection results.

[0071] Specifically, historical inspection data includes historical inspection indicators and the inspection work content and inspection standards corresponding to each indicator, historical indicator weights and corresponding historical indicator weight time series, historical indicator scores, historical inspection results and other data, and actual inspection results include the actual inspection task status, inspection work completion status, inspection behavior records and other data based on the current indicator evaluation system. Both historical inspection data and actual inspection results are stored in the emergency management data platform. When it is necessary to obtain historical inspection data and actual inspection results for inspectors, they can be obtained directly from the emergency management data platform.

[0072] Step S103, calculating the comprehensive weight of each independent indicator and each associated indicator in the indicator system based on the historical inspection data.

[0073] Specifically, the comprehensive weight refers to the quantitative value of the value and relative importance of each indicator of a measured object in the overall indicator system, as well as the size of the proportion.

[0074] Exemplarily, historical inspection data of fire safety inspectors over the past 10 years are collected, and historical indicator weights ω′ that are consistent with the indicators in the indicator system are screened, that is, the proportion of the full score of a single item to the full score of all items. Further, the comprehensive weight ω of each independent indicator and each related indicator can be determined based on the historical indicator weights.

[0075] Step S104, calculating the indicator scores of each independent indicator and each associated indicator in the indicator system based on the historical inspection data and the actual inspection results.

[0076] For example, the index score is calculated by the index scoring method, where the full score is 100 and the lowest score is zero. A certain score is assigned to each index within the range of less than or equal to the full score and greater than or equal to zero. Each index is scored separately to obtain the index score of each independent index and each related index. For example, for the index "total number of fire safety problems found", the maximum number of p1, p2, ..., p that each person can find in the historical inspection data is obtained. n fire safety issues, the result with the most fire safety issues found is taken as the optimal result p, and the score corresponding to the optimal result p is set to the full score. The score obtained if no fire safety issues are found is zero. Based on the actual inspection results, the "total number of fire safety issues found" indicator is scored within the range of less than or equal to the full score and greater than or equal to zero, and the indicator score corresponding to the actual inspection results of the "total number of fire safety issues found" indicator is obtained.

[0077] Step S105, calculating the correlation index coefficient of each correlation index based on the actual inspection result.

[0078] Specifically, the correlation index coefficient is used to reflect the impact of the correlation index on the overall fire safety inspection, such as giving a "veto power" to the actual inspection results that exceed the reasonable range. The correlation index coefficient of each correlation index is calculated according to the impact of the actual inspection results of each correlation index on the safety production management of key fire units. For example, for the correlation index of "accidents in key fire units", the corresponding actual inspection results include five levels: major and above accidents in key fire units, deaths of less than 3 people, serious injuries of less than 10 people, accidents with other impacts, and no casualties. For major and above accidents in key fire units, the economic and social impacts on key fire units are huge, which is something that every key fire unit does not want to see. Therefore, the correlation index coefficient corresponding to this level can be determined as 0. No casualties are the most ideal inspection result for the correlation index of "accidents in key fire units", so the correlation index coefficient corresponding to this level can be determined as 1. For the three levels of deaths of less than 3 people, serious injuries of less than 10 people, and accidents with other impacts, the corresponding correlation index coefficients can be determined between 0 and 1.

[0079] Step S106, calculating the total score of all indicators in the indicator system based on the comprehensive weight, indicator score and related indicator coefficient.

[0080] Specifically, the impact of related indicators on fire safety inspections is very significant. When calculating the total score of all indicators, we first obtain the number of related indicators in the indicator system, and then use the inspection effect comprehensive scoring method to calculate the sum of the scores of all indicators based on the comprehensive weights and indicator scores. Finally, we calculate the total score of all indicators based on the sum of the scores of all indicators, the number of related indicators, and the related indicator coefficients.

[0081] Step S107, rating the fire safety inspection based on the total score.

[0082] Specifically, the fire safety inspections are sorted based on the total scores to obtain the total score ranking results, and then the fire safety inspection levels are set according to the total score rankings. For example, the fire safety inspections of fire safety inspectors are ranked from high to low according to the total scores and the inspection effect levels are distinguished. The inspection effect levels include excellent, good, competent, and incompetent. In order to achieve fairness and rationality in fire safety inspections, a passing score can be set first, and then the inspection effect level of fire safety inspectors can be determined according to the passing score and the inspection effect ranking according to the percentage threshold.

[0083] The fire safety inspection and evaluation method provided in this embodiment constructs a fire safety inspection and evaluation index system, and divides the index system into multiple independent indicators and multiple related indicators, fully utilizes historical inspection data and actual inspection results, calculates the comprehensive weight of each indicator, the index score and the related index coefficient, and then obtains the total score of all indicators, and rates the fire safety inspection based on the total score, effectively improving the efficiency of the inspection effect evaluation, realizing the standardized, dynamic and precise evaluation of fire safety inspection, which can reduce the workload of inspection and evaluation, reduce the subjectivity in the evaluation work, and promote the transparency and fairness of inspection and evaluation, which is helpful to standardize the safety inspection team and improve the overall safety inspection level of inspectors for key units of production safety and fire protection. The problem of strong subjectivity in setting fire safety inspection evaluation indicators and low evaluation efficiency for fire safety inspectors is solved.

[0084] In this embodiment, a fire safety inspection and evaluation method is provided. Figure 2 is a flow chart of a fire safety inspection and evaluation method according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0085] Step S201, constructing a fire safety inspection and evaluation index system, the index system includes multiple independent indicators and multiple related indicators.

[0086] Specifically, the above step S201 includes:

[0087] Step S2011, obtaining the inspection type, inspection standard and inspection content.

[0088] Specifically, taking the actual inspection work of fire safety inspectors as an example, the inspection types include inspection process, inspection quality, and professional skills. The inspection standards are set based on the inspection types. For example, inspection quality indicators can include the safety status of key fire units and personal inspection results according to the inspection standards. The inspection content is set based on the inspection standards. For example, the safety status of key fire units includes the self-inspection of key fire units, work-related injuries in key fire units, accidents in key fire units, and actual risk degradation of key fire units according to the inspection content.

[0089] Step S2012, using the Delphi method and the analytic hierarchy process to construct a fire safety inspection evaluation index system including primary indicators, secondary indicators and tertiary indicators based on the inspection type, inspection standard and inspection content.

[0090] Specifically, the Delphi method, also known as the expert survey method, is a decision-making method that uses the form of communication to send the problems to be solved to each expert separately. Experts are not allowed to discuss with each other. After obtaining the opinions of the experts, they are sorted, summarized, and counted, and then anonymously fed back to the experts, and opinions are again solicited, concentrated, and fed back again until a consensus is reached. The hierarchical analysis method refers to decomposing the problem into different components according to the nature of the problem and the overall goal to be achieved, and the factors are clustered and combined at different levels according to the mutual correlation and affiliation between the factors, and compared two by two, forming a multi-level analysis structure model, so that the problem is ultimately reduced to the determination of the relative importance of the lowest level (schemes, measures, etc. for decision-making) relative to the highest level (overall goal) or the ranking of the relative order of superiority and inferiority.

[0091] For example, taking the actual inspection work of fire safety inspectors as an example, the fire safety inspection index system of fire safety inspectors may include three-level indicators. The first-level indicator may be the inspection type, which may include indicators such as inspection process, inspection quality, and professional skills. The second-level indicators are determined based on the first-level indicators according to the inspection content. The inspection quality indicators in the first-level indicators can be divided into second-level indicators such as the safety status of key fire units and personal inspection results. The third-level indicators are determined based on the second-level indicators according to the inspection standards. The safety status of key fire units in the second-level indicators is divided into three-level indicators such as self-inspection of key fire units, work-related injuries in key fire units, accidents in key fire units, and actual risk degradation of key fire units according to the inspection standards.

[0092] Step S2013, using the explanatory structure model to divide the third-level indicators into multiple independent indicators and multiple related indicators.

[0093] Specifically, the explanatory structural model is a systematic analysis method used to obtain the complex interrelationships and levels between elements. The idea is to first find out the components or influencing factors of the problem through investigation or technical means, and then analyze the relationship between the elements through the matrix model to obtain a multi-level hierarchical structural model. The explanatory structural model is used to divide the three-level indicators into multiple independent indicators and multiple related indicators, including:

[0094] Step a1, calculate the adjacency matrix of the correlation between the two indicators, and judge the causal relationship between the two indicators. The judgment of the causal relationship is determined by expert discussion. The calculation of the adjacency matrix of the correlation between the two indicators can be implemented by using relevant technologies, which will not be described in detail here.

[0095] Step a2, calculate the multiplication matrix of the adjacency matrix, and then obtain the reachability matrix by continuously multiplying the matrix by itself until the matrix no longer changes. The reachability matrix refers to the degree to which each node of the directed graph can be reached after a path of a certain length is described in matrix form.

[0096] Step a3, hierarchical decomposition of the matrix model is performed through the reachable matrix, and finally the correlation of the matrix model is obtained, and the correlation index and the independent index are determined according to the relative importance of the correlation. The hierarchical decomposition of the matrix model through the reachable matrix can be implemented by using relevant technologies, which will not be described in detail here.

[0097] After calculations in steps a1 to a3, the third-level indicators are divided into multiple independent indicators and multiple related indicators according to their importance.

[0098] It should be noted that multiple independent indicators and multiple related indicators are divided into linear indicators and nonlinear indicators according to whether the indicator values ​​are continuous.

[0099] The fire safety inspection evaluation index system for fire safety inspectors is shown in Table 1 below:

[0100] Table 1 Fire safety inspection evaluation index system for fire safety inspectors

[0101]

[0102]

[0103] Step S202: Obtain historical inspection data and actual inspection results. Figure 1 Step S102 of the illustrated embodiment will not be described in detail here.

[0104] Step S203, calculating the comprehensive weight of each independent indicator and each associated indicator in the indicator system based on the historical inspection data.

[0105] Specifically, in the above step S203, the comprehensive weight of each independent indicator and each associated indicator in the indicator system is calculated based on the historical inspection data, including:

[0106] Step S2031, obtaining the historical weight time series in the historical inspection data of each independent indicator and each associated indicator.

[0107] Specifically, obtain the historical weight time series in the historical inspection data, and define the historical weight time series as {Y t}, taking the “total number of fire safety problems found” as an example, obtain the historical weight ω′ of the “total number of fire safety problems found” indicator in the past 10 years and the corresponding time series {Y t}.

[0108] Step S2032, using a unit root test algorithm to check whether the distribution of the historical weighted time series is stationary, and performing a difference operation on the non-stationary time series until the time series distribution is in a stationary state, and obtaining the difference order.

[0109] Specifically, the unit root test algorithm (Augmented Dickey-Fuller, ADF for short) is an algorithm used to test whether there is a unit root process in a time series, thereby ensuring the stability of the series. For example, the ADF test algorithm is used to test whether there is a unit root in the time series distribution of the historical weight ω' of the "total number of fire safety problems found" in the past 10 years. If there is a unit root, it means that the time series {Y t} is not stationary, otherwise, the time series {Y t} is a stable state. Or for the time series {Y t}, the mean and variance are the same for any time period t, and for any same time interval, the covariance Cov(t, t+) is also the same, then the time series is called stationary.

[0110] For a non-stationary time series {Y t} Perform d-order difference operation, and you can perform first-order difference, second-order difference, etc. until it is converted into a stationary time series, and determine the difference order in turn. The specific mathematical expression of d-order difference is as follows:

[0111] d_order_Y=(1-B) d Y (1).

[0112] Among them, d_order_Y is the lag operation, B represents the defined lag operator, d is the difference order, and Y is a stationary time series.

[0113] Step S2033, determining the autoregressive order model and the moving average order model in the time series under the steady state.

[0114] Specifically, the autoregressive order (p) and the moving average order (q) are determined based on the historical weight ω' time series of the "total number of fire safety problems detected" in the past 10 years after the difference operation.

[0115] Among them, the autoregressive order (p) model is expressed as AR, and the formula is as follows:

[0116]

[0117] Where c is the constant term estimated during the model fitting process, are the parameters of the autoregressive order (p) model, which are used to describe the relationship between the current annual weight value ω of the “total number of fire safety problems found” and the values ​​at the past p time points, ∈ t The mean is equal to 0 and the variance is equal to σ 2 White noise sequence.

[0118] The moving average order (q) model is expressed as MA, and the formula is as follows:

[0119] MA:Y t =μ+∈ t +θ1∈ t-1 +θ2∈ t-2 +…+θ q ∈ t-q

[0120] Where μ is the constant term estimated during the model fitting process, θ1, θ2, …, θ q are the parameters of the moving average order (q) model, which are used to describe the relationship between the current annual weight value ω of the “total number of fire safety problems found” and the error at the past q time points, ∈ t The mean is equal to 0 and the variance is equal to σ 2 White noise sequence.

[0121] Step S2034, based on the autoregressive order model, the difference order and the moving average order model, the autoregressive integrated moving average model is used to fit the time series in the steady state, and the comprehensive weight of each independent indicator and each associated indicator is calculated.

[0122] Specifically, the Autoregressive Integrated Moving Average Model (ARIMA) makes the non-stationary time series data stationary by differencing the time series data, and then uses the Autoregressive (AR) and Moving Average (MA) models to model and predict it, so as to analyze the characteristics of the time series and predict the future weight values.

[0123] The autoregressive integrated moving average model includes three parameters, namely the autoregressive order (p), the difference order (d) and the moving average order (q). You can also use the graphs of the autocorrelation function (ACF) and the partial autocorrelation function (PACF), as well as information criteria (such as Akaikeinformation criterion, AIC, Bayesian Information Criterion, BIC) to select appropriate model parameters. The autoregressive model corresponding to the autoregressive order (p) is the AR (Autoregressive) model, the model corresponding to the moving average order (q) is the MA (MovingAverage) model, and the model corresponding to the difference order (d) is the I model.

[0124] The autoregressive integrated moving average model extracts the time series pattern hidden behind the data through the autocorrelation and difference of the data, and then uses the time series pattern to predict future data. Among them:

[0125] 1. The AR model is used to process the autoregressive part of the time series, which takes into account the impact of observations from several past periods on the current value.

[0126] 2. The I model is used to make non-stationary time series stationary. Through first-order or second-order difference processing, the trend and seasonal factors in the time series are eliminated.

[0127] 3. The MA model is used to process the moving average part of the time series, which takes into account the impact of past forecast errors on current values.

[0128] The above three models are combined to form the Autoregressive Integrated Moving Average Model (ARIMA model). The ARIMA model can not only capture the trend changes of data, but also handle temporary, sudden changes or data with large noise.

[0129] The autoregressive integrated moving average model formula is as follows:

[0130]

[0131] Among them, Y t is the historical weighted ω′ data of “total number of fire safety problems found” in the past 10 years, …, are the parameters of the AR model, θ1, θ2, …, θ qare the parameters of the MA model, ∈ t The mean is equal to 0 and the variance is equal to σ 2 is a white noise sequence, and c is the constant term estimated during the model fitting process.

[0132] The autoregressive integrated moving average model (ARIMA model) is used to fit the model to the historical weighted ω' time series (i.e., the time series Y under the steady state) of the "total number of fire safety problems found" in the past 10 years after the difference operation.

[0133] In order to minimize the prediction error, the fitted ARIMA model is diagnosed and the ARIMA model is modified according to the diagnosis results to improve the applicability of the ARIMA model. The modified ARIMA model is used to predict the comprehensive weight ω of the indicator "total number of fire safety problems found" in the current year.

[0134] It should be noted that if the indicator “total number of fire safety problems found” does not exist in the historical inspection data, the expert scoring method and the Delphi method are used to obtain the final comprehensive weight ω.

[0135] Step S204, calculating the indicator scores of each independent indicator and each associated indicator in the indicator system based on the historical inspection data and the actual inspection results.

[0136] Independent indicators and related indicators are divided into linear characteristic indicators or nonlinear characteristic indicators according to the continuity of indicator values. Linear characteristic indicators refer to indicators with continuous indicator values, and nonlinear characteristic indicators refer to indicators with discontinuous indicator values.

[0137] In the above step S204, for the indicators with historical data of fire safety inspection effect evaluation, when the independent indicators and the related indicators have linear characteristics, the indicator scores of each independent indicator and each related indicator in the indicator system are calculated based on the historical inspection data and the actual inspection results, including:

[0138] Step S2041, when the independent indicator and the associated indicator have linear characteristics, the historical inspection data and the actual inspection result corresponding to each independent indicator and each associated indicator are obtained.

[0139] Specifically, the historical inspection data and actual inspection results of fire safety inspectors over the past 10 years were obtained from the emergency management data platform.

[0140] Step S2042: Filter the highest inspection sample data and the lowest inspection sample data of each independent indicator and each associated indicator from the historical inspection data.

[0141] Specifically, the top 10% and bottom 10% of the historical inspection data are selected according to various indicators to evaluate the highest inspection data and the lowest inspection data, respectively, as the highest inspection sample data and the lowest inspection sample data. For example, for the indicator "total number of fire safety problems found", the historical inspection data of the top 10% of fire safety inspectors in the historical inspection data are obtained as the highest inspection sample data. Similarly, the historical inspection data of the bottom 10% of fire safety inspectors in the historical inspection data are obtained as the lowest inspection sample data.

[0142] Step S2043, based on the highest inspection sample data and the lowest inspection sample data, the autoregressive integrated moving average model is used to determine the highest inspection standard and the lowest inspection standard for each independent indicator and each associated indicator; the indicator score corresponding to the highest inspection standard is the preset full score value, and the indicator score corresponding to the lowest inspection standard is zero.

[0143] For example, for the indicator of “total number of fire safety problems found”, the inspection data of the best 10% inspectors in the historical inspection data are obtained, and each inspector can check at most p1, p2, ..., p n If the optimal result p is obtained for each fire safety problem, the optimal result p is used as the highest inspection standard for this indicator, and the score corresponding to the highest inspection standard is full marks. If no fire safety problems are found, the lowest inspection standard for this indicator is used, and the score corresponding to the lowest inspection standard is zero.

[0144] Step S2044, calculating the indicator unit score based on the highest inspection standard and the lowest inspection standard.

[0145] Specifically, before calculating the indicator unit score, the score interval of each indicator in the indicator system needs to be unified to [0, T], and the score interval of each indicator needs to be further normalized according to [0, T], so that the full score of the indicator can be unified when calculating the indicator unit score later. The normalization formula is:

[0146]

[0147] Among them, y(k) is the normalized value of the kth indicator, T is the unified full score of the indicator, x(k) is the highest or lowest score of the kth indicator obtained in step S2037; minx(k) is the lowest score of the indicator obtained in step S2037, and max·x(k) is the highest score of the indicator obtained in step S2037.

[0148] The formula for calculating the indicator unit score is as follows:

[0149]

[0150] Among them, v(k) represents the unit score of the kth indicator, T represents the full score of the single indicator, p(k) represents the highest inspection standard of the kth indicator, and p'(k) represents the lowest inspection standard of the kth indicator.

[0151] For example, for the indicator "Total number of fire safety problems found", if the highest inspection standard p in the actual inspection results is 500, the lowest inspection standard p' is 0, and the full score of the single indicator T is 100, then the unit score is That is, 0.2 points can be obtained for each fire safety issue found.

[0152] Step S2045, calculating the indicator score of each independent indicator and each associated indicator based on the indicator unit score and the actual inspection result of the corresponding indicator.

[0153] Specifically, the calculation formula for the indicator score of each independent indicator and each associated indicator is as follows:

[0154] t(k)=v(k)×q(k)(6).

[0155] Among them, t(k) represents the indicator score of each independent indicator and each associated indicator, v(k) represents the indicator unit score, and q(k) represents the actual inspection result of the corresponding indicator.

[0156] For example: for the indicator "Total number of fire safety issues found", if the number of fire safety issues found by the inspectors to be evaluated is 300, and the indicator unit score is 0.2, then the indicator score of "Total number of fire safety issues found" is t=0.2×300=60 points.

[0157] In the above step S204, when the independent indicator and the associated indicator have nonlinear characteristics, the indicator scores of each independent indicator and each associated indicator in the indicator system are calculated based on the historical inspection data and the actual inspection results, including:

[0158] Step S2046, when the independent indicators and the associated indicators have nonlinear characteristics, the highest inspection standard and the lowest inspection standard of each independent indicator and each associated indicator are determined by using the expert scoring method and the Delphi method based on historical inspection data and actual inspection results.

[0159] Specifically, the score corresponding to the highest inspection standard of each independent indicator and each associated indicator is the full score T of the indicator, and the score corresponding to the lowest inspection standard is zero.

[0160] Step S2047, calculating the indicator unit score based on the highest inspection standard and the lowest inspection standard.

[0161] For example, for the nonlinear characteristic "qualification certificate acquisition status" indicator, the score corresponding to the highest inspection standard is set to the full score of the indicator T, and the scoring standard for each type of certificate, that is, the indicator unit score is: each municipal certificate can obtain 5% T points, provincial certificates 10% T points, and national certificates 20% T points.

[0162] Step S2048, calculating the indicator score of each independent indicator and each associated indicator based on the indicator unit score and the actual inspection result of the corresponding indicator.

[0163] For example, for the nonlinear characteristic "qualification certificate acquisition status" indicator, the scoring standard for each type of certificate is determined based on historical inspection data and actual inspection results through expert scoring method and Delphi method, that is, the indicator unit score: each municipal certificate can get 5% T points, provincial certificate 10% T points, national certificate 20% T points, and each indicator unit score is accumulated to get the final indicator score, but the full score does not exceed T points.

[0164] It should be noted that for the indicators of historical data on the evaluation of the effect of no inspection, when determining the highest inspection standard and the lowest inspection standard, the expert scoring method and the Delphi method are used, and industry experts judge the highest inspection standard p and the lowest inspection standard p' for full marks and zero marks for each indicator based on their own experience and knowledge.

[0165] Step S205, calculate the correlation index coefficient of each correlation index based on the actual inspection result. Figure 1 Step S105 of the illustrated embodiment will not be described in detail here.

[0166] Step S206, calculate the total score of all indicators in the indicator system based on the comprehensive weight, indicator score and related indicator coefficient. Figure 1 Step S106 of the illustrated embodiment will not be described in detail here.

[0167] Step S207: Rating the fire safety inspection based on the total score. Figure 1 Step S107 of the illustrated embodiment will not be described in detail here.

[0168] The fire safety inspection and evaluation method provided in this embodiment calculates the autoregressive order, differential order and moving average order based on historical inspection data, and uses the autoregressive integral sliding average model to fit the time series in a stable state, and calculates the comprehensive weight of each independent indicator and each related indicator, thereby reducing the calculation error of the comprehensive weight, making the calculation of the comprehensive weight more scientific and reasonable, and providing a data basis for the subsequent calculation of the total score of the indicator. By analyzing and refining historical inspection data and actual inspection results, the zero score and full score standards of each independent indicator and each related indicator are scientifically determined through the linear characteristics or nonlinear characteristics of the indicators, the calculation accuracy of each indicator score is improved, and the purpose of scientifically and reasonably calculating each indicator score is achieved, which is in line with the actual inspection work and provides objective and fair indicator scores for subsequent fire safety inspection and evaluation.

[0169] In this embodiment, a fire safety inspection and evaluation method is provided, which can be used in a main control computer. Figure 3 is a flow chart of a fire safety inspection and evaluation method according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0170] Step S301: construct a fire safety inspection and evaluation index system, which includes multiple independent indicators and multiple related indicators. Figure 2 Step S201 of the illustrated embodiment will not be described in detail here.

[0171] Step S302: Obtain historical inspection data and actual inspection results. Figure 2 Step S202 of the illustrated embodiment will not be described in detail here.

[0172] Step S303, based on the historical inspection data, calculate the comprehensive weight of each independent indicator and each related indicator in the indicator system. Figure 2 Step S203 of the illustrated embodiment will not be described in detail here.

[0173] Step S304: Calculate the index score of each independent index and each related index in the index system based on the historical inspection data and the actual inspection results. Figure 2 Step S204 of the illustrated embodiment will not be described in detail here.

[0174] Step S305, calculating the correlation index coefficient of each correlation index based on the actual inspection result.

[0175] Specifically, the above step S305 includes:

[0176] Step S3051, obtaining the actual inspection result corresponding to each associated indicator.

[0177] Specifically, the actual inspection result corresponding to each associated indicator is obtained from the emergency management data platform, and the actual inspection result includes the actual inspection result interval data of each associated indicator and the corresponding associated indicator coefficient.

[0178] Step S3052: Use a piecewise function to determine the reasonable interval division result of each correlation index and the corresponding correlation index coefficient.

[0179] Specifically, through the expert scoring method and the Delphi method, industry experts independently judge the reasonable interval division results of each correlation indicator based on their own experience and knowledge, and then determine the corresponding correlation indicator coefficient for each reasonable interval after the division. For example: according to the actual work situation of the fire safety inspectors, the most ideal reasonable interval among multiple reasonable intervals is selected, and the correlation indicator coefficient of the most ideal reasonable interval is assigned to 1, and the correlation index coefficients of other reasonable intervals that do not reach the most ideal reasonable interval or exceed the most ideal reasonable interval are floated up and down based on the correlation indicator coefficient of 1 corresponding to the most ideal reasonable interval.

[0180] For example, the correlation indicator "accidents occurring in key firefighting units" is expressed by the severity of the accident: it is divided into five accident levels: major and above, less than 3 deaths, less than 10 serious injuries, other impacts, and no accidents. The five accident levels are reasonable intervals for the divisions. No accidents are determined as the most ideal reasonable interval, and the correlation indicator coefficient corresponding to this reasonable interval is assigned a value of 1. The correlation indicator coefficients corresponding to the other four accident levels of major and above are 0, the correlation indicator coefficients corresponding to less than 3 deaths are 0.25, the correlation indicator coefficients corresponding to less than 10 serious injuries are 0.5, and the correlation indicator coefficients corresponding to other impacts are 0.75.

[0181] Step S3053, based on the reasonable interval division result and the corresponding correlation index coefficient, determine the corresponding correlation index coefficient according to the reasonable interval where the actual inspection result is located.

[0182] For example, when the correlation indicator "accidents occurring in key firefighting units" in the actual inspection results is less than 10 people seriously injured, it can be determined that the corresponding correlation indicator coefficient is 0.5.

[0183] Taking the fire safety inspection index system of fire safety inspectors as an example, the related indicators and corresponding related indicator coefficients are shown in Table 2 below:

[0184] Table 2 Correlation index coefficients

[0185]

[0186]

[0187] Step S306, calculate the total score of all indicators in the indicator system based on the comprehensive weight, indicator score and related indicator coefficient. Specifically, the total score calculation formula of all indicators in the indicator system is as follows:

[0188]

[0189] Among them, s represents the total score; t represents the score of each indicator, t i represents the score of the i-th indicator, ω represents the weight of the indicator, ω i represents the weight of the i-th indicator; θ represents the correlation coefficient of the correlation indicator, θ j represents the jth correlation index coefficient; m represents the number of correlation index coefficients; j = 1, 2, 3..., m; n represents the number of all indicators; i = 1, 2, 3..., n.

[0190] For example, if the only related indicators in the indicator system are "accidents in key firefighting units" and "degradation of actual risk in key firefighting units", for the indicator "accidents in key firefighting units", the related indicator coefficients for accidents with major or above, less than 3 deaths, less than 10 serious injuries, and other impacts in key firefighting units are set to 0, 0.25, 0.5, 0.75 respectively, and the related indicator coefficient for no casualties is 1; for the indicator "degradation of actual risk of fire safety", the coefficients for actual risk of fire safety decreasing by 3 levels (such as red to blue), 2 levels, 1 level, 0 level, -1 level (such as blue to yellow), -2 level, and -3 level are set to 1.5, 1.3, 1.1, 1, 0.9, 0.7, and 0.5 respectively. For example, among the key fire protection units under the supervision of a certain inspector, the actual fire safety risk of one unit has dropped from red to yellow (dropped by 2 levels, with a coefficient of 1.3), the actual fire safety risk of another unit has increased from yellow to orange (dropped by -1 level, with a coefficient of 0.9), and there is a key fire protection unit with a fatal accident of less than 3 people (with a coefficient of 0.25). If the total score of each indicator is 80 points, the total score of the fire safety inspection of the inspector calculated by the comprehensive scoring method of the inspection effect is:

[0191] s=80×1.3×0.9×0.25=23.4.

[0192] Step S307, rating the fire safety inspection results based on the total score.

[0193] Specifically, the above step S307 includes:

[0194] Step S3071, setting the passing score using estimation method.

[0195] Specifically, the estimation method is used to set the passing score λ as a reference benchmark for fire safety inspection effect rating.

[0196] Step S3072, ranking the inspection results from high to low according to the total scores.

[0197] Specifically, the inspection effects of fire safety inspectors in the actual inspection results are ranked from high to low according to the total scores.

[0198] Step S3073, using a piecewise function to determine the inspection effect level based on the passing score and the inspection effect ranking.

[0199] Exemplarily, based on the passing score λ and the high and low inspection effect rankings, a piecewise function is used to determine the inspection effect level of the inspectors. In the actual fire safety inspection evaluation, the number of inspectors to be evaluated whose total number meets the percentage threshold can be selected in each inspection effect level:

[0200] For those with a total score ≥λ and ranking in the top 10%, the evaluation level is excellent;

[0201] If the total score is ≥λ and the ranking is in the top 10% to 20%, the evaluation level is good;

[0202] For those with a total score ≥ λ and ranking after the top 20%, the evaluation level is competent;

[0203] The total score is less than λ, and the evaluation level is incompetent.

[0204] Among them, excellent grade inspectors have profound professional knowledge, work conscientiously and responsibly, attach importance to reality, can proactively discover and solve complex safety problems, and have made positive contributions to fire safety management in key fire units.

[0205] Good grade inspectors have solid professional knowledge, work conscientiously and responsibly, pay attention to reality, solve some common safety problems, and demonstrate good ability and results.

[0206] The quality and level of fire safety inspection work performed by inspectors of competent grades have basically met the requirements, but there are still certain shortcomings that need to be strengthened and improved.

[0207] Incompetent inspectors have serious problems and defects in their fire safety inspection work, the inspection quality and results fail to meet basic standards, and they are unable to perform their inspection duties.

[0208] Step S3074, rating the fire safety inspection based on the inspection effect level to obtain an evaluation result.

[0209] Specifically, a suitable segmentation interval is selected for the inspection effect score of each inspector to be evaluated, so as to obtain a corresponding inspection effect level as the evaluation result.

[0210] Step S308, carry out behavioral risk warning and formulate reward and punishment measures based on the evaluation results.

[0211] Specifically, behavioral risk warning: risk prediction is carried out based on the inspection effect evaluation results of the inspectors, and the list of behavioral risk personnel is set as the focus of attention, and reminders are set. The individual scores of the five indicators of "excessive inspection", "on-schedule inspection", "total number of fire safety problems found", "average number of fire safety problems found per time", and "average number of complaints" in the evaluation index system are extracted to predict whether the inspectors' future inspection behaviors have the risk of violating the code of conduct.

[0212] If there is a single item score < λ (baseline), the inspector's future inspection behavior will be at higher risk. The inspector's inspection behavior can be further analyzed and predicted based on the evaluation results and specific inspection data, and a warning can be issued to the inspector to urge him to abide by the code of conduct and strengthen self-discipline. At the same time, the assessment department can be reminded to pay more attention to the inspection behavior of the person.

[0213] For example, if the score of the indicator "Total number of fire safety problems found" of an inspector is less than λ, there are two possible situations: first, the inspector's professional ability is insufficient, and the number of fire safety problems found in the multiple key fire units under his management is too small; second, the inspector may have accepted benefits from key fire units, concealed the fire safety problems found, and violated the code of conduct. Therefore, the inspection behavior of the inspector is judged to have behavioral risks, and a behavioral risk warning is issued to strengthen the self-discipline of the inspector, and at the same time remind the assessment department to strengthen its attention to the inspection behavior of the person.

[0214] Reward and punishment measures: Based on the evaluation results, provide rewards such as bonuses, promotion opportunities, honorary titles, publicity and promotion; deduct bonuses or check the results, terminate the labor contract, publicize dereliction of duty and other disciplinary measures.

[0215] The fire safety inspection and evaluation method provided in this embodiment has a relatively important role in the fire safety inspection and evaluation of the inspectors. Based on the reasonable interval division results and the corresponding correlation index coefficients, the corresponding correlation index coefficients are determined according to the reasonable interval where the actual inspection results are located. The calculated correlation index coefficients reflect the important impact of the correlation index on the overall fire safety inspection, fit the actual inspection situation, and make the calculated correlation index coefficients more scientific and reasonable, providing a coefficient basis for the subsequent calculation of the total score of all indicators. The qualified score line is set by the estimation method; the inspection effect is ranked from high to low according to the total score; based on the qualified score line and the inspection effect ranking, the inspection effect level is determined by a piecewise function to obtain the rating result, and an automated evaluation method based on the big data of fire safety inspection is realized, which effectively reduces the workload of fire safety inspection effect evaluation, improves the efficiency of inspection effect evaluation, promotes the transparency of fire safety inspection evaluation, and improves the objectivity, fairness and accuracy of fire safety inspection evaluation. Carrying out behavioral risk warnings and formulating reward and punishment measures based on the evaluation results will help standardize the fire safety inspection team and improve the overall safety inspection level.

[0216] In this embodiment, a fire safety inspection and evaluation system is also provided. Figure 4 As shown, the system includes: an emergency management data platform 401, a data calling module 402, a rule setting module 403, an inspection and evaluation module 404 and a behavior risk warning module 405;

[0217] The data calling module is used to obtain historical inspection data and actual inspection results from the emergency management data platform;

[0218] The rule setting module communicates with the data calling module. The rule setting module is used to construct a fire safety inspection and evaluation index system. The index system includes multiple independent indicators and multiple related indicators. The comprehensive weights of each independent indicator and each related indicator in the index system are calculated based on historical inspection data.

[0219] The inspection and evaluation module communicates with the rule setting module. The inspection and evaluation module is used to calculate the index scores of each independent indicator and each related indicator in the index system based on historical inspection data and actual inspection results; calculate the related index coefficient of each related indicator based on the actual inspection results, and calculate the total score of all indicators in the index system based on the comprehensive weight, indicator score and related index coefficient, and rate the fire safety inspection based on the total score.

[0220] The behavior risk warning module communicates with the inspection and evaluation module, and is used to carry out behavior risk warning. The system also includes: a data cleaning module, an inspection effect display module and a background management module.

[0221] Among them: the data cleaning module communicates with the data calling module and the rule setting module respectively, and is used to receive the historical inspection data and actual inspection results obtained by the data calling module, and clean the historical inspection data and actual inspection results, remove redundant and non-compliant information, perform necessary standardization processing on the data, and transmit the processed data to the rule setting module.

[0222] The inspection effect display module communicates with the inspection evaluation module. The inspection effect display module is used to generate visual fire safety inspection evaluation results, including charts and documents showing the inspector's total inspection score, the ranking of the city, district, and street where the inspector is located, the inspection effect score details, and suggestions for improving the inspection effect.

[0223] The background management module communicates with the rule setting module, and the background management module is used to update evaluation indicators, indicator weights and indicator coefficients, evaluation rules, model parameters, evaluation cycles, etc.

[0224] The further functional description of each of the above modules is the same as that of the above corresponding embodiments and will not be repeated here.

[0225] The embodiment of the present invention also provides a computer device having the above Figure 4 The fire safety inspection and evaluation system shown.

[0226] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0227] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0228] The memory 20 stores instructions executable by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0229] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0230] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0231] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 5 The example of connecting through bus is taken in the following.

[0232] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0233] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0234] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A fire safety inspection and evaluation method, characterized in that: The method comprises: Constructing a fire safety inspection effect evaluation index system, wherein the index system includes multiple independent indicators and multiple related indicators; Obtain historical inspection data and actual inspection results; Calculate the comprehensive weight of each independent indicator and each related indicator in the indicator system based on historical inspection data; Calculate the indicator scores of each independent indicator and each related indicator in the indicator system based on historical inspection data and actual inspection results; Calculate the correlation index coefficient of each of the correlation indicators based on the actual inspection results; Calculate the total score of all indicators in the indicator system based on the comprehensive weight, indicator score and related indicator coefficient; rating the effectiveness of the fire safety inspection based on the total score; The comprehensive weights of each independent indicator and each associated indicator in the indicator system are calculated based on the historical inspection data, including: Get the historical weight time series in the historical check data for each independent indicator and each associated indicator; A unit root test algorithm is used to check whether the distribution of the historical weight time series is stable, and a difference operation is performed on the non-stationary time series until the time series distribution is in a stable state, and the difference order is obtained; Determine the autoregressive order model and the moving average order model in the time series under the stationary state; Based on the autoregressive order model, the difference order and the moving average order model, the autoregressive integrated moving average model is used to fit the time series in the steady state, and the comprehensive weight of each independent indicator and each related indicator is calculated; The independent index and the associated index have linear characteristics or nonlinear characteristics; When the independent indicators and the associated indicators have linear characteristics, the indicator scores of each independent indicator and each associated indicator in the indicator system are calculated based on the historical inspection data and the actual inspection results, respectively, including: When the independent indicator and the associated indicator have linear characteristics, the historical inspection data and the actual inspection results corresponding to each independent indicator and each associated indicator are obtained; Filter the highest inspection sample data and the lowest inspection sample data of each independent indicator and each associated indicator from the historical inspection data; Based on the highest inspection sample data and the lowest inspection sample data, the autoregressive integrated moving average model is used to determine the highest inspection standard and the lowest inspection standard for each independent indicator and each associated indicator; the highest inspection standard corresponds to an indicator score of a preset full score, and the lowest inspection standard corresponds to an indicator score of zero; Calculate the indicator unit score based on the highest inspection standard and the lowest inspection standard; Calculate the indicator score of each independent indicator and each associated indicator based on the indicator unit score and the actual inspection result of the corresponding indicator; When the independent indicators and the associated indicators have nonlinear characteristics, the indicator scores of each independent indicator and each associated indicator in the indicator system are calculated based on the historical inspection data and the actual inspection results, respectively, including: When independent indicators and related indicators have nonlinear characteristics, the highest inspection standard and the lowest inspection standard for each independent indicator and each related indicator are determined by using the expert scoring method and the Delphi method based on historical inspection data and actual inspection results; Calculate the indicator unit score based on the highest inspection standard and the lowest inspection standard; Calculate the indicator score of each independent indicator and each associated indicator based on the indicator unit score and the actual inspection results of the corresponding indicator; The calculation of the correlation index coefficient of each correlation index based on the actual inspection result includes: Obtaining actual inspection results corresponding to each of the associated indicators; Using a piecewise function to determine a reasonable interval division result of each of the correlation indicators and a corresponding correlation indicator coefficient; Based on the reasonable interval division result and the corresponding correlation index coefficient, determining the corresponding correlation index coefficient according to the reasonable interval where the actual inspection result is located; When calculating the total score of all indicators, first obtain the number of related indicators in the indicator system, then calculate the sum of the scores of all indicators based on the comprehensive weights and indicator scores using the inspection effect comprehensive scoring method, and then calculate the total score of all indicators based on the sum of the scores of all indicators, the number of related indicators and the related indicator coefficients.

2. The method according to claim 1, characterized in that The fire safety inspection effect evaluation index system is constructed as follows: Obtain inspection type, inspection standard and inspection content; The Delphi method and analytic hierarchy process are used to construct a fire safety inspection effect evaluation index system including primary, secondary and tertiary indicators based on inspection type, inspection standard and inspection content; The explanatory structural model is used to divide the three-level indicators into multiple independent indicators and multiple related indicators.

3. The method according to claim 1, characterized in that The rating of the fire safety inspection effectiveness based on the total score includes: Use estimation method to set the passing score; The inspection results are ranked from high to low according to the total score; Based on the passing score and the ranking of inspection results, a piecewise function is used to determine the inspection effect level; Fire safety inspections are rated based on the inspection effectiveness level to obtain evaluation results.

4. The method according to claim 3, characterized in that The method further comprises: Conduct behavioral risk warnings and formulate reward and punishment measures based on the evaluation results.

5. A fire safety inspection and evaluation system, characterized in that: The system includes: an emergency management data platform, a data calling module, a rule setting module, an inspection and evaluation module, and a behavior risk warning module; The data calling module is used to obtain historical inspection data and actual inspection results from the emergency management data platform; The rule setting module communicates with the data calling module, and the rule setting module is used to construct a fire safety inspection evaluation index system, wherein the index system includes multiple independent indicators and multiple related indicators; and the comprehensive weight of each independent indicator and each related indicator in the index system is calculated based on the historical inspection data; The inspection and evaluation module communicates with the rule setting module, and the inspection and evaluation module is used to calculate the index score of each independent indicator and each associated indicator in the index system based on the historical inspection data and the actual inspection results; calculate the associated index coefficient of each associated indicator based on the actual inspection results, and calculate the total score of all indicators in the index system based on the comprehensive weight, the index score and the associated index coefficient, and rate the fire safety inspection based on the total score; The comprehensive weights of each independent indicator and each associated indicator in the indicator system are calculated based on the historical inspection data, including: Get the historical weight time series in the historical check data for each independent indicator and each associated indicator; A unit root test algorithm is used to check whether the distribution of the historical weight time series is stable, and a difference operation is performed on the non-stationary time series until the time series distribution is in a stable state, and the difference order is obtained; Determine the autoregressive order model and the moving average order model in the time series under the stationary state; Based on the autoregressive order model, the difference order and the moving average order model, the autoregressive integrated moving average model is used to fit the time series in the steady state, and the comprehensive weight of each independent indicator and each related indicator is calculated; The independent index and the associated index have linear characteristics or nonlinear characteristics; When the independent indicators and the associated indicators have linear characteristics, the indicator scores of each independent indicator and each associated indicator in the indicator system are calculated based on the historical inspection data and the actual inspection results, respectively, including: When the independent indicator and the associated indicator have linear characteristics, the historical inspection data and the actual inspection results corresponding to each independent indicator and each associated indicator are obtained; Filter the highest inspection sample data and the lowest inspection sample data of each independent indicator and each associated indicator from the historical inspection data; Based on the highest inspection sample data and the lowest inspection sample data, the autoregressive integrated moving average model is used to determine the highest inspection standard and the lowest inspection standard for each independent indicator and each associated indicator; the highest inspection standard corresponds to an indicator score of a preset full score, and the lowest inspection standard corresponds to an indicator score of zero; Calculate the indicator unit score based on the highest inspection standard and the lowest inspection standard; Calculate the indicator score of each independent indicator and each associated indicator based on the indicator unit score and the actual inspection result of the corresponding indicator; When the independent indicators and the associated indicators have nonlinear characteristics, the indicator scores of each independent indicator and each associated indicator in the indicator system are calculated based on the historical inspection data and the actual inspection results, respectively, including: When independent indicators and related indicators have nonlinear characteristics, the highest inspection standard and the lowest inspection standard for each independent indicator and each related indicator are determined by using the expert scoring method and the Delphi method based on historical inspection data and actual inspection results; Calculate the indicator unit score based on the highest inspection standard and the lowest inspection standard; Calculate the indicator score of each independent indicator and each associated indicator based on the indicator unit score and the actual inspection results of the corresponding indicator; The calculation of the correlation index coefficient of each correlation index based on the actual inspection result includes: Obtaining actual inspection results corresponding to each of the associated indicators; Using a piecewise function to determine a reasonable interval division result of each of the correlation indicators and a corresponding correlation indicator coefficient; Based on the reasonable interval division result and the corresponding correlation index coefficient, determining the corresponding correlation index coefficient according to the reasonable interval where the actual inspection result is located; When calculating the total score of all indicators, first obtain the number of related indicators in the indicator system, then calculate the sum of the scores of all indicators based on the comprehensive weight and indicator score using the inspection effect comprehensive score method, and then calculate the total score of all indicators based on the sum of the scores of all indicators, the number of related indicators and the related indicator coefficient; The behavior risk warning module communicates with the inspection and evaluation module, and the behavior risk warning module is used to carry out behavior risk warning.

6. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the fire safety inspection and evaluation method according to any one of claims 1 to 4 by executing the computer instructions.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the fire safety inspection and evaluation method according to any one of claims 1 to 4.

Images