Quantification Method, Device and Storage Medium for Fire Safety Risks

Abstract

The present application provides a method, apparatus, and storage medium for quantifying fire safety risks. The method includes: obtaining fire-related data of fire supervision objects monitored by the fire protection Internet of Things; determining a reference vector based on the fire-related data and establishing a fire safety risk quantification model; inputting the fire-related data into the fire safety risk quantification model to obtain the fire safety risk quantification result of the fire supervision object output by the fire safety risk quantification model; and sorting the fire safety risk quantification results of different fire supervision objects. Based on the fire-related data of fire supervision objects actually monitored by the fire protection Internet of Things, the present application outputs the fire safety risk quantification result of the fire supervision object through the fire safety risk quantification model, deepens the algorithm application of the fire protection Internet of Things monitoring data, and realizes the quantification of the fire safety risks of social units based on the fire protection Internet of Things monitoring data.

Description

Technical Field

[0001] This application relates to the field of fire safety technology, and in particular, to a method, device, and storage medium for quantifying fire safety risks. Background Art

[0002] In terms of the fire supervision mode, the current fire supervision team implements a "double random, one public" fire supervision mode to reduce the influence of human subjective intervention on inspection results.

[0003] With the continuous increase in the number of social units, the risk points of fire hazards are increasing, and the pressure of fire supervision and inspection is also increasing. Currently, the "Fire Eye - Fire Risk Prediction System" is used for fire risk early warning. This system uses big data and artificial intelligence technologies to perform machine learning on a large amount of historical data such as fires, unit buildings, hidden dangers, and illegal acts, and the computer conducts dynamic and quantitative fire risk ranking for all buildings and automatically outputs early warning analysis results regularly.

[0004] However, this system requires a large amount of work in the early stage, and the data basis comes from a large amount of manual data. For example, the potential safety hazards and illegal acts entered into the supervision and management system by fire supervision and inspection personnel. Such data has a large degree of subjectivity and will affect the accuracy of fire risk prediction results. Summary of the Invention

[0005] In view of the above problems existing in the prior art, embodiments of this application provide a method, device, and storage medium for quantifying fire safety risks.

[0006] This application provides a method for quantifying fire safety risks, including:

[0007] Obtain the fire-related data of the fire supervision objects monitored by the fire Internet of Things;

[0008] Determine a reference vector based on the fire-related data and establish a fire safety risk quantification model;

[0009] Input the fire-related data into the fire safety risk quantification model to obtain the fire safety risk quantification result of the fire supervision object output by the fire safety risk quantification model;

[0010] Rank the fire safety risk quantification results of different fire supervision objects.

[0011] Optionally, the determining a reference vector based on the fire-related data and establishing a fire safety risk quantification model includes:

[0012] Determine a comparison vector and the reference vector based on the fire-related data;

[0013] Dimensionalize the comparison vector and the reference vector;

[0014] Determine the correlation coefficient between the comparison vector and the reference vector;

[0015] Determine the correlation degree between the comparison vector and the reference vector according to the correlation coefficient as the quantification result of the fire safety risk of the fire supervision object.

[0016] Optionally, determining the comparison vector and the reference vector based on the fire correlation data includes:

[0017] Determine the reference vector according to the ideal state of the target index and the fire correlation data corresponding to the target index;

[0018] Determine the comparison vector according to the fire correlation data corresponding to the target index.

[0019] Optionally, the target indicators include: the on-duty rate of the fire control room operators, the alarm accuracy rate of the automatic fire alarm system, and the failure rate of the automatic fire alarm system.

[0020] Optionally, the fire supervision object is a key fire safety unit determined by the fire supervision agency and monitored through the fire Internet of Things.

[0021] This application also provides a fire safety risk quantification device, including:

[0022] The first acquisition module is used to acquire the fire correlation data of the fire supervision object monitored by the fire Internet of Things;

[0023] The determination module is used to determine the reference vector based on the fire correlation data and establish a fire safety risk quantification model;

[0024] The second acquisition module is used to input the fire correlation data into the fire safety risk quantification model to obtain the quantification result of the fire safety risk of the fire supervision object output by the fire safety risk quantification model;

[0025] The sorting module is used to sort the quantification results of the fire safety risks of different fire supervision objects.

[0026] Optionally, the determination module is further used for:

[0027] Determine the comparison vector and the reference vector based on the fire correlation data;

[0028] Dimensionalize the comparison vector and the reference vector;

[0029] Determine the correlation coefficient between the comparison vector and the reference vector;

[0030] Determine the degree of association between the comparison vector and the reference vector according to the correlation coefficient as the quantitative result of the fire safety risk of the fire supervision object.

[0031] Optionally, determining the comparison vector and the reference vector based on the fire-related data includes:

[0032] Determine the reference vector according to the ideal state of the target index and the fire-related data corresponding to the target index;

[0033] Determine the comparison vector according to the fire-related data corresponding to the target index.

[0034] This application also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the steps of any one of the above-mentioned fire safety risk quantification methods are implemented.

[0035] This application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the above-mentioned fire safety risk quantification methods are implemented.

[0036] This application also provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of any one of the above-mentioned fire safety risk quantification methods are implemented.

[0037] The fire safety risk quantification method and device provided by this application are based on the fire-related data of the fire supervision objects actually monitored by the fire Internet of Things. Through the fire safety risk quantification model, the quantitative result of the fire safety risk of the fire supervision objects is output, deepening the algorithm application of the fire Internet of Things monitoring data, and realizing the quantification of the fire safety risk of social units based on the fire Internet of Things monitoring data. Description of the Drawings

[0038] In order to more clearly illustrate the technical solutions in this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of this application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0039] Figure 1 is a schematic flowchart of the fire safety risk quantification method provided by an embodiment of this application;

[0040] Figure 2 is one of the schematic diagrams of the calculation results of the association degrees of 66 key fire safety units provided by an embodiment of this application;

[0041] Figure 3 It is the second schematic diagram of the calculation results of the correlation degrees of 66 key fire safety units provided by the embodiments of the present application;

[0042] Figure 4 It is the third schematic diagram of the calculation results of the correlation degrees of 66 key fire safety units provided by the embodiments of the present application;

[0043] Figure 5 It is the schematic diagram of the quantitative ranking of the correlation degrees of key fire safety units provided by the embodiments of the present application;

[0044] Figure 6 It is the structural schematic diagram of the fire safety risk quantification device provided by the embodiments of the present application;

[0045] Figure 7 It is the structural schematic diagram of the electronic device provided by the embodiments of the present application. Specific embodiments

[0046] In terms of the fire supervision mode, currently, the fire supervision team implements the "double random, one public" fire supervision mode. Through the corresponding information system, this mode randomly determines the units to be inspected, randomly matches the supervision and inspection personnel, and promptly discloses the inspection results to the society. This mode reduces the occurrence of human subjective intervention. However, with the continuous development of the economy, the number of social units has increased, the risk points of fire hazards have increased, and the pressure of fire supervision and inspection has been continuously increasing.

[0047] Currently, the "Fire Eye - Fire Risk Prediction System" is used for fire risk early warning. This system utilizes big data and artificial intelligence technologies, and through machine learning on a large amount of historical data such as fires, unit buildings, hidden dangers, and illegal acts, the computer conducts dynamic and quantitative fire risk ranking for all buildings, and automatically outputs early warning analysis results regularly.

[0048] However, the data basis in the "Fire Eye - Fire Risk Prediction System" comes from a large amount of manual data, such as the safety hazards and illegal acts input into the supervision and management system by fire supervision personnel. Since such data has certain subjectivity and untruthfulness, it will affect the accuracy of the data model prediction results. Moreover, this system requires a large amount of workload in the early stage of operation to construct a database, with a high cost and unable to be widely used.

[0049] The fire protection Internet of Things refers to linking the equipment and facilities in the traditional fire protection system through technologies such as Internet of Things information sensing and communication, connecting the fire protection information required for various elements involved in social fire supervision and management and the fire fighting and rescue of fire protection agencies, constructing a highly sensitive fire protection basic environment, realizing real-time, dynamic, interactive and integrated collection, transmission and processing of fire protection information, comprehensively promoting and improving the social fire supervision and management level of relevant agencies, and significantly enhancing the command, dispatch, decision-making and disposal capabilities of fire protection agencies in fire fighting and rescue.

[0050] At present, the Internet of Things construction of intelligent fire protection is being gradually promoted. However, the application of Internet of Things monitoring data still stays in the simple statistical analysis stage, and it is mainly used to more quickly and comprehensively perceive the occurrence of fires, so as to quickly carry out fire rescue operations and to evaluate the fire protection technical service capabilities of fire protection service agencies. The development and application of its prediction function are very scarce, and its application in fire supervision and management is even weaker.

[0051] In view of the above problems existing in the prior art, the embodiments of the present application provide a method, device and storage medium for quantifying fire safety risks, applying the data obtained from the fire protection Internet of Things to realize the quantification of the fire safety risks of fire protection supervision objects, and then supervising and managing the fire protection supervision objects.

[0052] To make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below with reference to the accompanying drawings in the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present application.

[0053] Figure 1 is a schematic flowchart of the method for quantifying fire safety risks provided by the embodiments of the present application. As Figure 1 shown, the embodiments of the present application provide a method for quantifying fire safety risks, the execution subject of which is a device for quantifying fire safety risks. The method at least includes the following steps:

[0054] Step 101, obtain the fire-related data of the fire protection supervision object monitored by the fire protection Internet of Things;

[0055] Step 102, determine a reference vector based on the fire-related data and establish a fire safety risk quantification model;

[0056] Step 103, input the fire-related data into the fire safety risk quantification model to obtain the fire safety risk quantification result of the fire protection supervision object output by the fire safety risk quantification model;

[0057] Step 104: Sort the fire safety risk quantification results of different fire supervision objects.

[0058] Specifically, the fire supervision objects refer to various social units supervised by the fire supervision and management department, and the fire Internet of Things mainly refers to the Internet of Things of the fire supervision agency.

[0059] In the embodiment of the present application, based on the Internet of Things monitoring data of the fire control room, the fire-related data of the fire supervision objects monitored by the fire Internet of Things is obtained. Among them, the fire-related data refers to the data associated with the fire safety risk of the fire supervision object, such as the name, location information, the number of fire facilities, the duty information of the fire duty personnel, the number of fire rescue equipment, the failure incidence rate, etc.

[0060] The obtained fire-related data is input into the fire safety risk quantification model to obtain the fire safety risk quantification results of the fire supervision objects, so as to facilitate the fire supervision agency to supervise and manage the fire supervision objects.

[0061] Among them, the fire safety risk quantification model is established based on the grey correlation analysis method to realize the quantification of the fire safety risk of the fire supervision objects.

[0062] Specifically, before quantifying the fire safety risk of the fire supervision objects, it is necessary to construct a fire safety risk quantification model. This model is constructed based on the actual fire-related data of the fire supervision objects monitored by the fire Internet of Things through the grey correlation analysis method. Compared with collecting data by fire supervision personnel and inputting it into the corresponding system, the data is objective and real, and the manual input is reduced. The determination of the reference vector is an important link in constructing the fire safety risk quantification model through the grey correlation analysis method.

[0063] After obtaining the fire safety risk quantification results of different fire supervision objects, visually sort the fire safety risk quantification results to guide the efficient and orderly development of fire supervision and management work. Focus on supervising and managing the social units with relatively high fire safety risks shown in the fire safety risk quantification results.

[0064] The fire safety risk quantification method provided by the embodiment of the present application is based on the fire-related data of the fire supervision objects actually monitored by the fire Internet of Things, and outputs the fire safety risk quantification results of the fire supervision objects through the fire safety risk quantification model, deepening the algorithm application of the fire Internet of Things monitoring data, realizing the quantification of the fire safety risk of social units based on the fire Internet of Things monitoring data, reducing the subjective influence on the fire safety risk assessment of the fire supervision objects, and increasing the objectivity and accuracy of the fire safety risk quantification results.

[0065] Optionally, determining a reference vector based on the fire-related data and establishing a fire safety risk quantification model includes:

[0066] Determining a comparison vector and the reference vector based on the fire-related data;

[0067] Performing dimensionless processing on the comparison vector and the reference vector;

[0068] Determining the correlation coefficient between the comparison vector and the reference vector;

[0069] Determining the correlation degree between the comparison vector and the reference vector according to the correlation coefficient as the quantification result of the fire safety risk of the fire supervision object.

[0070] Specifically, the fire safety risk quantification model in the embodiment of the present application is constructed based on the grey relational analysis method, including:

[0071] Determining a comparison vector and a reference vector;

[0072] Dimensionless processing of data;

[0073] Determining the correlation coefficient;

[0074] Determining the correlation degree.

[0075] (1) Determining a comparison vector and a reference vector

[0076] The reference vector, as an important reference benchmark in the grey relational analysis method, greatly affects the accuracy and rationality of the calculation result. The reference vector is the ideal state of the comparison vector.

[0077] Optionally, determining a comparison vector and a reference vector includes:

[0078] Determining the reference vector according to the ideal state of the target index and the fire-related data corresponding to the target index;

[0079] Determining the comparison vector according to the fire-related data corresponding to the target index.

[0080] In the embodiment of the present application, for each index, it is represented by two values. For example, the target index is determined to be three indexes, namely: the occupancy rate of the fire control room duty personnel, the alarm accuracy rate of the fire automatic alarm system, and the failure rate.

[0081] Among them, a good on-duty situation of the duty personnel can reflect the attention paid to fire safety work within the social unit. Therefore, the ideal state of the personnel on-duty rate is recorded as 1. A high accuracy rate of the fire alarm reported by the fire automatic alarm system means that the operation state of the fire automatic alarm system of the social unit is in good condition and effective. Therefore, the ideal state is recorded as 1. The failure information incidence rate of the fire automatic alarm system is the lower the better. A low failure incidence rate means that the operation state effect of the fire automatic alarm system of the social unit is good. Therefore, the ideal state is recorded as 0.

[0082] Each index is represented by two numbers. One number is the ideal state of the index, and the other number corresponds to the actual data of the index, which can be set according to needs. For example, the reference vector or eigenvector is determined to be [1, 0, 1, 0, 0, 0]. The eigenvector involved in the embodiments of the present application is the reference vector.

[0083] The comparison vector is the actual data of the target indexes of each fire supervision object under the fire IoT monitoring, which is compared with the reference vector. For one reference vector, there are several comparison vectors.

[0084] (2) Dimensionless processing of data

[0085] Since the physical meanings of various factors in the system under IoT monitoring are different, the dimensions of each data are not necessarily the same, which is not convenient for comparison or it is difficult to obtain correct conclusions when comparing. Therefore, dimensionless data processing is required during the grey relational analysis process.

[0086] Optionally, interval processing is performed on the data to compress the data within the range of [a, b], maintaining the consistency of the data mathematical units. The values of a and b are set according to needs. For example, a = 0 and b = 1, that is, normalization processing is performed on the data.

[0087] Optionally, the dimensionless processing of the data can be transformed through Formula 1. The expression of Formula 1 is:

[0088]

[0089] Among them, max k X i (k) represents the maximum value of the sample data, min k X i (k) represents the minimum value of the sample data, and k represents the serial number of the sample data.

[0090] (3) Determine the correlation coefficient

[0091] The reference vector X’0 after dimensionless processing is:

[0092] X’0 = {X’0(1), X’0(2), …, X’0(n)}

[0093] Comparison vector X’ i is:

[0094] X’ i = {X’ i (1), X’ i (2), …, X’ i (n)}, i = 1, 2, …, n

[0095] where i represents the serial number of the comparison vector.

[0096] Geometrically speaking, the degree of association refers to the similarity between the shapes of the reference vector and the comparison vector curves. The closer the curve shapes between the comparison vector and the reference vector are, the greater the degree of association between the two; conversely, the greater the difference in curve shapes, the lower the degree of association between the two. Therefore, the difference between the comparison vector and the reference vector curves can be used as a measure of the degree of association.

[0097] Optionally, the difference between the comparison vector and the reference vector curves can be determined by Formula 2, and the expression of Formula 2 is:

[0098] Δ i (k) = |X’0(k) - X’ i (k)|, k = 1, 2, …, n

[0099] The maximum difference and the minimum difference at two levels are respectively:

[0100]

[0101]

[0102] Therefore, the correlation coefficient is:

[0103]

[0104] where ρ is the discrimination coefficient, which is used to improve the significance of the difference between correlation coefficients, and its value ranges from 0 to 1, for example, 0.5 is taken.

[0105] (4) Determine the degree of association

[0106] Since the correlation coefficient is a value that compares the degree of correlation between the vector and the reference vector curve, there are multiple such values, and the data is too scattered to facilitate overall comparison. Therefore, it is necessary to centralize the correlation coefficients and concentrate each correlation coefficient into one value. Taking the average is one way of information centralization, and the average value of each correlation coefficient is used as a quantitative representation of the degree of correlation between the comparison vector and the reference vector. The average value of each correlation coefficient can be determined by Formula 3, and the expression of Formula 3 is:

[0107]

[0108] where γ 0i represents the correlation degree of the comparison vector to the reference vector, or is also called sequence correlation degree, average correlation degree, and line correlation degree. The closer the value of γ 0i is to 1, the higher the degree of correlation between the comparison vector and the reference vector, and the better the correlation between the two.

[0109] In the embodiments of the present application, the higher the correlation degree, the lower the fire safety risk, and the lower the correlation degree, the higher the fire safety risk. The higher the fire safety risk, the more urgent it is to carry out supervision and treatment in a timely manner.

[0110] For the same fire supervision object, inputting the fire correlation data at different times under the fire IoT monitoring into the fire safety risk quantification model can obtain the correlation degrees at different times. Sorting multiple correlation degree values, according to the change of the correlation degree values, the supervision intensity for different periods of this fire supervision object can be determined.

[0111] For different fire supervision objects, inputting the fire correlation data in the same period under the fire IoT monitoring into the fire safety risk quantification model can obtain the correlation degrees of different fire supervision objects. According to the numerical levels of the correlation degrees of different fire supervision objects, key supervision and treatment are carried out for the fire supervision objects whose correlation degree values are lower than the threshold.

[0112] The fire safety risk quantification method provided by the embodiments of the present application analyzes the fire IoT data in the fire monitoring room based on the grey correlation analysis method, quantifies the fire safety risks of each fire supervision object, highlights the key social units for fire supervision, provides a technical basis for the efficient application of supervision forces to fire supervision objects with higher fire safety risks, and realizes efficient and accurate prediction and discrimination of fire safety risks.

[0113] Optionally, the target indicators include: the on-duty rate of the fire control room operators, the alarm accuracy rate of the fire automatic alarm system, and the failure incidence rate of the fire automatic alarm system.

[0114] In the embodiments of the present application, based on the Internet of Things data of the fire control room, the target indicators are determined as follows: the on-duty rate of the fire control room operators, the alarm accuracy rate of the automatic fire alarm system, and the failure incidence rate of the automatic fire alarm system. Based on these three indicators, a reference vector is constructed. Using the actual software and hardware management Internet of Things data of the social unit itself as the basis for quantifying its fire safety risk, the data is more objective and real, and the operating cost of manpower is reduced.

[0115] The automatic fire alarm system is composed of a triggering device, a fire alarm device, a linkage output device, and other auxiliary function devices. Its alarm accuracy rate and failure incidence rate can effectively evaluate the fire rescue ability of the fire supervision object.

[0116] Optionally, the fire supervision object is a key fire safety unit determined by the fire supervision agency and monitored through the fire Internet of Things.

[0117] Specifically, before evaluating the fire safety risk of a social unit, key fire safety units screened out by the fire supervision and management agency can be targeted, overcoming the blind and random inspection mode without discrimination, improving the accuracy and efficiency of fire risk discrimination, and saving cost investment.

[0118] Key fire safety units generally include: ① Units with high fire risk and large economic losses after a fire. Such as factories, warehouses, oil depots, liquid storage yards, and flammable material storage yards with Class A and B fire risks; shantytowns, etc. ② Units with concentrated personnel and heavy casualties after a fire: Such as the Great Hall of the People, auditoriums, cinemas, hospitals, high-class hotels, and residential buildings. ③ Units with large economic losses after a fire. Such as department store warehouses, libraries, national material warehouses, archives, large and medium-sized computer rooms, and buildings with valuable equipment. ④ Units with great political influence after a fire. Such as telecommunications buildings, broadcasting buildings, postal buildings, and exhibition buildings. ⑤ Units that are likely to cause large-scale fires and require a large amount of fire water after a fire, such as textile factories, linen factories, and wholesale markets such as wood processing factories.

[0119] Key fire safety units are fire supervision objects determined by the fire supervision agency according to fire safety management regulations and monitored through the fire Internet of Things.

[0120] Next, a specific example is used to illustrate the fire safety risk quantification method provided by the embodiments of the present application.

[0121] Example 1: The feature vector is determined as [1, 0, 1, 0, 0, 0]. Combining with the formula of the grey relational analysis method, a fire safety risk quantification model is constructed to quantify the fire safety risk of the fire supervision object. Its pseudo-code is as follows:

[0122]

[0123]

[0124] Figure 2 One of the schematic diagrams of the correlation calculation results of 66 key fire safety units provided by the embodiments of the present application; Figure 3 One of the schematic diagrams of the correlation calculation results of 66 key fire safety units provided by the embodiments of the present application; Figure 4 One of the schematic diagrams of the correlation calculation results of 66 key fire safety units provided by the embodiments of the present application. As Figures 2 to 4 shown, it records the unit names and serial numbers of 66 key fire safety units in a certain city, as well as multiple correlation calculation results obtained by performing correlation calculation with the reference vector [1, 0, 1, 0, 0, 0] after normalizing the fire IoT monitoring data on a weekly basis, and finally calculates the average value of multiple correlations.

[0125] Figure 5 A schematic diagram of the quantitative ranking of the correlation of key fire safety units provided by the embodiments of the present application. As Figure 5 shown, the average correlation results calculated in Figures 2 to 4 are sorted to obtain the quantitative ranking of the correlation of some key fire safety units. The abscissa corresponds to the serial number of the key fire safety unit in Figures 2 to 4 and the ordinate corresponds to the average correlation calculation result. The lower the correlation value, the more emphasis needs to be placed on the supervision and management of the social unit.

[0126] Figure 6 A schematic diagram of the structure of the fire safety risk quantification device provided by the embodiments of the present application. As Figure 6 shown, the embodiments of the present application provide a fire safety risk quantification device, which includes:

[0127] A first acquisition module 601, configured to acquire the fire correlation data of the fire supervision object monitored by the fire IoT;

[0128] A determination module 602, configured to determine a reference vector based on the fire correlation data and establish a fire safety risk quantification model;

[0129] A second acquisition module 603, configured to input the fire correlation data into the fire safety risk quantification model to obtain the fire safety risk quantification result of the fire supervision object output by the fire safety risk quantification model;

[0130] A sorting module 604, configured to sort the fire safety risk quantification results of different fire supervision objects.

[0131] Optionally, the determination module is further configured to:

[0132] Determine a comparison vector and the reference vector based on the fire-related data;

[0133] Perform dimensionless processing on the comparison vector and the reference vector;

[0134] Determine the correlation coefficient between the comparison vector and the reference vector;

[0135] Determine the correlation degree between the comparison vector and the reference vector according to the correlation coefficient as the quantitative result of the fire safety risk of the fire supervision object.

[0136] Optionally, the determining the comparison vector and the reference vector based on the fire-related data includes:

[0137] Determine the reference vector according to the ideal state of the target index and the fire-related data corresponding to the target index;

[0138] Determine the comparison vector according to the fire-related data corresponding to the target index.

[0139] Optionally, the target indicators include: the on-duty rate of the fire control room operators, the alarm accuracy rate of the fire automatic alarm system, and the failure incidence rate of the fire automatic alarm system.

[0140] Optionally, the fire supervision object is a key fire safety unit determined by the fire supervision agency and monitored through the fire Internet of Things.

[0141] It should be noted here that the above-mentioned fire safety risk quantification device provided by the embodiment of the present application can implement all the method steps implemented by the above-mentioned fire safety risk quantification method embodiment, and can achieve the same technical effect. The same parts and beneficial effects as those in the method embodiment will not be specifically described in this embodiment.

[0142] Figure 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 7 shown, the electronic device may include: a processor 701, a communication interface 702, a memory 703, and a communication bus 704. Among them, the processor 701, the communication interface 702, and the memory 703 communicate with each other through the communication bus 704. The processor 701 can call the logic instructions in the memory 703 to execute the fire safety risk quantification method, and the method includes:

[0143] Obtain the fire-related data of the fire supervision object monitored by the fire Internet of Things;

[0144] Determine a reference vector based on the fire-related data and establish a fire safety risk quantification model;

[0145] Input the fire-related data into the fire safety risk quantification model to obtain the fire safety risk quantification result of the fire supervision object output by the fire safety risk quantification model;

[0146] Sort the fire safety risk quantification results of different fire supervision objects.

[0147] Optionally, the determining a reference vector based on the fire-related data and establishing a fire safety risk quantification model includes:

[0148] Determine a comparison vector and the reference vector based on the fire-related data;

[0149] Perform dimensionless processing on the comparison vector and the reference vector;

[0150] Determine the correlation coefficient between the comparison vector and the reference vector;

[0151] Determine the correlation degree between the comparison vector and the reference vector according to the correlation coefficient as the fire safety risk quantification result of the fire supervision object.

[0152] Optionally, the determining a comparison vector and the reference vector based on the fire-related data includes:

[0153] Determine the reference vector according to the ideal state of the target index and the fire-related data corresponding to the target index;

[0154] Determine the comparison vector according to the fire-related data corresponding to the target index.

[0155] Optionally, the target index includes: the on-duty rate of the fire control room operators, the alarm accuracy rate of the automatic fire alarm system, and the failure incidence rate of the automatic fire alarm system.

[0156] Optionally, the fire supervision object is a key fire safety unit determined by the fire supervision agency and monitored through the fire Internet of Things.

[0157] In addition, when the logical instructions in the above-mentioned memory 703 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0158] On the other hand, this application also provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the fire safety risk quantification method provided by the above-mentioned various methods. The method includes:

[0159] Obtain the fire-related data of the fire supervision objects monitored by the fire Internet of Things;

[0160] Determine a reference vector based on the fire-related data and establish a fire safety risk quantification model;

[0161] Input the fire-related data into the fire safety risk quantification model to obtain the fire safety risk quantification result of the fire supervision object output by the fire safety risk quantification model;

[0162] Sort the fire safety risk quantification results of different fire supervision objects.

[0163] On another aspect, this application also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the fire safety risk quantification method provided by the above-mentioned various methods. The method includes:

[0164] Obtain the fire-related data of the fire supervision objects monitored by the fire Internet of Things;

[0165] Determine a reference vector based on the fire-related data and establish a fire safety risk quantification model;

[0166] Input the fire-related data into the fire safety risk quantification model to obtain the fire safety risk quantification result of the fire supervision object output by the fire safety risk quantification model;

[0167] Rank the quantification results of fire safety risks for different fire supervision objects.

[0168] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0169] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0170] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for quantifying fire safety risks, characterized in that, Including: Obtaining the fire-related data of the fire supervision objects monitored by the fire Internet of Things; Determining a reference vector based on the fire-related data and establishing a fire safety risk quantification model; The fire safety risk quantification model is established by the following method: determining a comparison vector and the reference vector based on the fire-related data; performing dimensionless processing on the comparison vector and the reference vector; Determining the correlation coefficient between the comparison vector and the reference vector; Determining the correlation degree between the comparison vector and the reference vector according to the correlation coefficient as the fire safety risk quantification result of the fire supervision object; Inputting the fire-related data into the fire safety risk quantification model to obtain the fire safety risk quantification result of the fire supervision object output by the fire safety risk quantification model; Sorting the fire safety risk quantification results of different fire supervision objects; The determining the comparison vector and the reference vector based on the fire-related data includes: Determining the reference vector according to the ideal state of the target index and the fire-related data corresponding to the target index; Determining the comparison vector according to the fire-related data corresponding to the target index; The target index includes: the on-duty rate of the fire control room operators, the alarm accuracy rate of the fire automatic alarm system, and the failure incidence rate of the fire automatic alarm system.

2. The fire safety risk quantification method according to claim 1, wherein The fire supervision object is a key fire safety unit determined by the fire supervision agency and monitored through the fire Internet of Things.

3. A fire safety risk quantification device, characterized in that, Including: A first obtaining module, configured to obtain the fire-related data of the fire supervision objects monitored by the fire Internet of Things; A determining module, configured to determine a reference vector based on the fire-related data and establish a fire safety risk quantification model; The fire safety risk quantification model is established by the following method: determining a comparison vector and the reference vector based on the fire-related data; performing dimensionless processing on the comparison vector and the reference vector; Determining the correlation coefficient between the comparison vector and the reference vector; Determining the correlation degree between the comparison vector and the reference vector according to the correlation coefficient as the fire safety risk quantification result of the fire supervision object; The determining the comparison vector and the reference vector based on the fire-related data includes: determining the reference vector according to the ideal state of the target index and the fire-related data corresponding to the target index; determining the comparison vector according to the fire-related data corresponding to the target index; The target index includes: the on-duty rate of the fire control room operators, the alarm accuracy rate of the fire automatic alarm system, and the failure incidence rate of the fire automatic alarm system; A second obtaining module, configured to input the fire-related data into the fire safety risk quantification model to obtain the fire safety risk quantification result of the fire supervision object output by the fire safety risk quantification model; A sorting module, configured to sort the fire safety risk quantification results of different fire supervision objects.

4. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the fire safety risk quantification method according to any one of claims 1 to 2.

5. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the fire safety risk quantification method according to any one of claims 1 to 2.

Images