Fire hazard identification method, system, medium and device based on smart city

Abstract

The present invention provides a method, system, medium and device for identifying fire hazards based on a smart city. The method includes: selecting key nodes and obtaining the completion status of sub-events; obtaining the impact of the historical data of sub-events at each key node on fire hazards to obtain the key values of the sub-events; obtaining the impact of the historical data of sub-events at different key nodes on fire hazards to obtain the weight values of the sub-events; fusing the key values and weight values of the sub-events to obtain the importance degree; based on the importance degree, obtaining sub-ratings, and fusing all sub-ratings at the key nodes to obtain the comprehensive rating at the key nodes; based on the comprehensive ratings of all key nodes, constructing a fire safety statistical chart and obtaining the correlation between any location in the city and fire hazards. The present invention comprehensively and comprehensively evaluates the degree of fire hazards in a city from a digital perspective, so that before a danger occurs, safety deployments can be made for areas with fire hazards.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent fire protection, and particularly relates to a method, system, medium and device for identifying fire hazards based on a smart city. Background Art

[0002] Fires are characterized by high occurrence frequency and large spatio-temporal span, and the losses caused are also very serious. Therefore, fire monitoring and timely alarm of fire incidents are particularly important in people's daily lives.

[0003] In the existing technology, intelligent fire protection has been popularized. Cameras in various key areas of the city are used to detect objects or behaviors with fire hazards, and then the monitoring data is uploaded to the terminal for hazard monitoring. Currently, the monitoring of fire hazards is often carried out through a visual solution. In this way, measures are usually taken synchronously after detecting the hazards, without making full use of the historical data affecting fire hazards to prevent fire hazards in advance, which is not conducive to the development of digital intelligent fire protection. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the purpose of the present invention is to provide a method for identifying fire hazards based on a smart city, aiming to solve the technical problems mentioned in the background art.

[0005] To achieve the above purpose, the present invention is implemented through the following technical solutions:

[0006] A method for identifying fire hazards based on a smart city includes the following steps:

[0007] Select key nodes in the city, and based on the monitoring system of the smart city, obtain the completion status of sub-events related to fire at the key nodes;

[0008] Based on the monitoring system of the smart city, obtain the influence of the historical data of sub-events at each key node on fire hazards, and comprehensively consider the completion status of the sub-events to obtain the key value of sub-events at each key node;

[0009] Obtain the influence of the historical data of sub-events at different key nodes on the fire hazards to obtain the weight value of each sub-event itself;

[0010] Fuse the key value of sub-events at each key node with the weight value of the sub-event itself to obtain the importance degree of sub-events at each key node;

[0011] Based on the importance degree of sub-events at each key node, obtain the sub-score of each sub-event for the key node, and fuse all sub-scores at the key node to obtain the comprehensive score at the key node;

[0012] Based on the comprehensive scores of all the key nodes, a fire safety statistical chart of the city is constructed. According to the fire safety statistical chart, the correlation between any place in the city and the fire hazards is obtained.

[0013] According to one aspect of the above technical solution, the monitoring system based on the smart city obtains the influence of the historical data of sub-events at each key node on fire hazards, and synthesizes the completion status of the sub-events to obtain the key values of the sub-events at each key node, specifically including:

[0014] Define multiple intermediate events under fire hazards as (Q1, Q2, ……, Q n ), and define multiple sub-events as (q1, q2, ……, q m ); where n represents the number of the intermediate events, and m represents the number of the sub-events;

[0015] Obtain the historical estimated probability ζ j of the historical data of each sub-event q i for the corresponding intermediate event Q ij from the monitoring system of the smart city; i = (1, 2, ……, n), j = (1, 2, ……, m);

[0016] Optimize the historical estimated probability ζ ij according to the completion status of the sub-event to obtain the current estimated probability Y ij of the intermediate event;

[0017] Calculate the occurrence probability of the fire hazard based on the current estimated probability Y ij of each intermediate event:

[0018] ;

[0019] Among them, θ = (1, 2, ……, v), v represents the total number of key nodes, P(θ) represents the occurrence probability of fire hazards at the θ-th key node, q j ∈ Q i represents the sub-event j under the intermediate event i, k ∈ [1, n], q j ∈ Q i U Q k represents the sub-event j under the intermediate event i or k;

[0020] Calculate the partial derivative of the sub-event q ij under each intermediate event according to the occurrence probability P of the fire hazard to obtain the key value E ij of the sub-event q ij;

[0021] 。

[0022] According to one aspect of the above technical solution, obtaining the influence of the historical data of sub-events at different key nodes on the fire hazards to obtain the weight value of each sub-event itself specifically includes:

[0023] Obtaining the historical data of the influence of sub-events at different key nodes on intermediate events from the monitoring system of the smart city and constructing a standardized matrix Ζ(θ);

[0024] ;

[0025] where ζ nmv represents the historical estimated probability of intermediate event n caused by the influence of m sub-event at key node θ;

[0026] Calculating the weights of the historical estimated probabilities ζ nmv of each sub-event at different key nodes for different intermediate events;

[0027] ;

[0028] where H j represents the entropy of the j-th sub-event, represents the weight of the j-th sub-event under the i-th intermediate event in key node θ;

[0029] Multiplying the weights of the corresponding sub-events in each key node to obtain the weight value W of the influence of each sub-event itself on each intermediate event ij 。

[0030] According to one aspect of the above technical solution, the formula for fusing the key values of sub-events at each key node with the weight values of the sub-events themselves to obtain the importance of sub-events at each key node is as follows:

[0031] W ij ·E ij =G ij ;

[0032] where G represents the importance.

[0033] According to one aspect of the above technical solution, based on the importance of sub-events at each key node, to obtain the sub-scores of each sub-event for the key node, and fusing all the sub-scores at the key node to obtain the comprehensive score at the key node, specifically includes:

[0034] Define a sub-scoring interval O for the importance, and calculate the expected value, entropy value, and hyper-entropy value of the sub-events at each of the key nodes according to the sub-scoring interval O;

[0035] ;

[0036] ;

[0037] ;

[0038] Among them, represents the expected value, represents the entropy value, represents the hyper-entropy value, = 0.02, and respectively represent the upper limit value and the lower limit value of the scoring interval o, represents the order of the normal function within the scoring interval O;

[0039] Calculate the matching degree ψ of the sub-events in the key nodes within the sub-scoring interval;

[0040] ;

[0041] Fuse the matching degrees of all sub-events in the key nodes within the sub-scoring interval to obtain the total matching degree K;

[0042] Based on the total matching degree K, quantitatively comprehensively score η for the key nodes;

[0043] ;

[0044] Among them, β represents the level of the total matching degree K.

[0045] According to one aspect of the above technical solution, based on the comprehensive scores of all the key nodes, construct a fire safety statistical chart for the city, and according to the fire safety statistical chart, obtain the correlation between any place in the city and the fire hazards, specifically including:

[0046] Construct a kernel density map of the city according to the floor plan of the city;

[0047] ;

[0048] ;

[0049] Among them, f(x) represents the kernel density at position x, represents the position of the θ-th key node on the kernel density map, T represents the spatial dimension, represents the bandwidth, and L represents the spatial weight function;

[0050] Calculate the bandwidth in the kernel density map based on the comprehensive scores of all the key nodes ;

[0051] ;

[0052] ;

[0053] where VD represents the weighted standard distance, represents the comprehensive score at the θ-th key node, { , , } respectively represent the three-axis coordinates at the θ-th key node, { , , } respectively represent the weighted average centers of the three axes after considering the comprehensive scores. The kernel density map has multiple field values that convert non-quantitative features into quantitative features, μ represents the sum of all field values in the kernel density map, and D m represents the median distance of the weighted average center of the three axes;

[0054] Substitute the bandwidth into the kernel density map to obtain the fire safety statistical map of the city;

[0055] Analyze the kernel density of each region in the fire safety statistical map based on the Moran index analysis method to obtain the Moran index of each region. Consider the regions with the Moran index greater than the preset index as the regions with a high degree of correlation with the fire hazards and record them.

[0056] The present invention also provides a fire hazard identification system based on a smart city, including:

[0057] The first acquisition module: used to select key nodes in the city and obtain the completion status of sub-events related to fire at the key nodes based on the monitoring system of the smart city;

[0058] The second acquisition module: used to obtain the impact of the historical data of sub-events at each key node on fire hazards based on the monitoring system of the smart city, and synthesize the completion status of the sub-events to obtain the key values of sub-events at each key node;

[0059] Specifically, the second acquisition module is used for:

[0060] Define multiple intermediate events under fire hazards as (Q1, Q2,..., Q n ), and define multiple sub-events as (q1, q2,..., q m ); where n represents the number of intermediate events and m represents the number of sub-events;

[0061] Obtain the historical data of each of the sub - events q from the monitoring system of the smart city j for the corresponding intermediate event Q i of the historical estimated probability ζ ij ; i = (1, 2, ……, n), j = (1, 2, ……, m);

[0062] According to the completion situation of the sub - event, optimize the historical estimated probability ζ ij to obtain the current estimated probability Y of the intermediate event ij ;

[0063] Based on the current estimated probability Y of each intermediate event ij , calculate the occurrence probability of the fire hazard:

[0064] ;

[0065] where θ = (1, 2, ……, v), v represents the total number of key nodes, P(θ) represents the occurrence probability of the fire hazard in the θ - th key node, q j ∈Q i represents the sub - event j under the intermediate event i, k ∈ [1, n], q j ∈Q i UQ k represents the sub - event j under the intermediate event i or k;

[0066] According to the occurrence probability P of the fire hazard, calculate the partial derivative of the sub - event q under each intermediate event ij to obtain the key value E of the sub - event q under each intermediate event ij ; ij ;

[0067] ;

[0068] The third acquisition module: used to obtain the influence of the historical data of the sub - events at different key nodes on the fire hazard, so as to obtain the weight value of each sub - event itself;

[0069] The third acquisition module is specifically used for:

[0070] Obtain the historical data of the influence of the sub - events at different key nodes on the intermediate events from the monitoring system of the smart city, and construct the standardized matrix Ζ(θ);

[0071] ;

[0072] where ζ nmvRepresents the historical estimated probability of the intermediate event n caused by the m sub-events at the θ key node;

[0073] Calculate the historical estimated probability ζ of each of the sub-events at different key nodes for different intermediate events nmv of the weight;

[0074] ;

[0075] where H j represents the entropy of the j-th sub-event, represents the weight of the j-th sub-event under the i-th intermediate event at the key node θ;

[0076] Multiply the weights of the corresponding sub-events in each of the key nodes to obtain the weight value W of the influence of each of the sub-events itself on each of the intermediate events ij ;

[0077] Fusion module: used to fuse the key values of the sub-events at each of the key nodes with the weight values of the sub-events themselves to obtain the importance degrees of the sub-events at each of the key nodes;

[0078] Scoring module: used to obtain the sub-scores of each of the sub-events for the key nodes based on the importance degrees of the sub-events at each of the key nodes, and fuse all the sub-scores at the key nodes to obtain the comprehensive score at the key node;

[0079] The scoring module is specifically used for:

[0080] Define a sub-score interval O for the importance degree, and calculate the expected value, entropy value, and hyper-entropy value of the sub-events at each of the key nodes according to the sub-score interval O;

[0081] ;

[0082] ;

[0083] ;

[0084] where, represents the expected value, represents the entropy value, represents the hyper-entropy value, = 0.02, and respectively represent the upper limit value and the lower limit value of the scoring interval o, represents the order of the normal function within the scoring interval O;

[0085] Calculate the matching degree ψ of the sub-events in the key node within the sub-scoring interval;

[0086] ;

[0087] Fuse the matching degrees of all sub-events of the key node within the sub-scoring interval to obtain the total matching degree K;

[0088] Based on the total matching degree K, quantitatively comprehensively score the key node η;

[0089] ;

[0090] Among them, β represents the level of the total matching degree K;

[0091] Statistics module: used to construct a fire safety statistical chart of the city based on the comprehensive scores of all the key nodes, and obtain the correlation between any place in the city and the fire hazards according to the fire safety statistical chart;

[0092] Specifically, the statistics module is used for:

[0093] Construct a kernel density map of the city according to the plan view of the city;

[0094] ;

[0095] ;

[0096] Among them, f(x) represents the kernel density at position x, represents the position of the θ-th key node on the kernel density map, T represents the spatial dimension, represents the bandwidth, and L represents the spatial weight function;

[0097] Calculate the bandwidth in the kernel density map based on the comprehensive scores of all the key nodes ;

[0098] ;

[0099] ;

[0100] Among them, VD represents the weighted standard distance, represents the comprehensive score at the θ-th key node, { , , } respectively represent the three-axis coordinates at the θ-th key node, { , , } respectively represent the weighted average centers of the three axes after considering the comprehensive score. The kernel density map has multiple field values that convert non-quantitative features into quantitative features. μ represents the sum of all field values in the kernel density map, D m represents the median distance of the weighted average center of the three axes;

[0101] Substitute the bandwidth into the kernel density map to obtain the fire safety statistical chart of the city;

[0102] Analyze the kernel density of each area in the fire safety statistical chart based on the Moran index analysis method to obtain the Moran index of each area. Consider the areas with Moran index greater than the preset index as areas with high correlation with the fire hazards and record them.

[0103] The present invention also provides a storage medium, on which a computer program is stored. When the computer program is executed by a processor, the fire hazard identification method based on a smart city as described above is implemented.

[0104] The present invention 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 computer program, the fire hazard identification method based on a smart city as described above is implemented.

[0105] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0106] By distinguishing multiple key nodes in the city for zonal monitoring, first collect historical data on the impact of sub-events at key nodes on fire hazards in the local area through the monitoring system of the smart city to obtain key values, and then collect historical data on the impact of sub-events at other key nodes on fire hazards to obtain weight values. Integrate the key values and weight values to obtain the importance of sub-events at key nodes. This method takes into account the impact of sub-events at other key nodes on fire hazards, avoiding the situation where sub-events in a single key node are only trapped in their own historical data of good, medium, and poor, and more comprehensively reflects the comprehensive importance of sub-events; then give sub-ratings to sub-events in key nodes, and then integrate all sub-ratings to obtain the comprehensive rating in the key node area. The comprehensive rating reflects the probability of fire hazards in the area. The higher the comprehensive rating, the higher the probability of fire hazards; finally, consider the fire hazards of each key node to construct a fire safety statistical chart to comprehensively reflect the safety level of each area in a city, that is, the correlation between any place in the city and fire hazards, and then carry out corresponding rectification of sub-events according to the safety level of each area;

[0107] From a digital perspective, the present invention comprehensively integrates the degree of fire hazards in a city, so that before a danger occurs, safety deployments can be made in areas with fire hazards. Description of the Drawings

[0108] Figure 1 It is a flowchart of the fire hazard identification method based on a smart city in the first embodiment of the present invention;

[0109] Figure 2 It is a structural block diagram of the fire hazard identification system based on a smart city in the second embodiment of the present invention;

[0110] Figure 3 It is a structural block diagram of an electronic device in the third embodiment of the present invention;

[0111] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. Specific Embodiments

[0112] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are given in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0113] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly on the other element or there can also be an intermediate element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be an intermediate element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0114] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the description of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0115] Please refer to Figure 1 , which shows a fire hazard identification method based on a smart city in the first embodiment of the present invention, including the following steps:

[0116] S10. Select key nodes in the city and obtain the completion status of sub-events related to fire at the key nodes based on the monitoring system of the smart city;

[0117] S20. Based on the monitoring system of the smart city, obtain the impact of the historical data of sub-events at each of the key nodes on fire hazards, and comprehensively consider the completion status of the sub-events to obtain the key values of the sub-events at each of the key nodes;

[0118] S30. Obtain the impact of the historical data of sub-events at different key nodes on the fire hazards to obtain the weight values of each of the sub-events themselves;

[0119] S40. Integrate the key values of the sub-events at each of the key nodes with the weight values of the sub-events themselves to obtain the importance degrees of the sub-events at each of the key nodes;

[0120] S50. Based on the importance degrees of the sub-events at each of the key nodes, obtain the sub-ratings of each of the sub-events for the key nodes, and integrate all the sub-ratings at the key nodes to obtain the comprehensive rating at the key node;

[0121] S60. Based on the comprehensive ratings of all the key nodes, construct a fire safety statistical chart for the city, and according to the fire safety statistical chart, obtain the correlation degree between any location in the city and the fire hazards.

[0122] It can be understood that the present invention conducts zonal monitoring by distinguishing multiple key nodes in the city. First, through the monitoring system of the smart city, collect the historical data of the impact of sub-events at the key nodes on the fire hazards within the region to obtain key values, and then collect the historical data of the impact of sub-events at other key nodes on the fire hazards to obtain weight values. Integrate the key values and weight values to obtain the importance degree of the sub-events at the key nodes. This method takes into account the impact of sub-events in other key nodes on the fire hazards, and can prevent sub-events in one key node from simply being trapped in their own excellent historical data, and more comprehensively reflects the comprehensive importance of the sub-events; then give sub-ratings to the sub-events in the key nodes, and then integrate all the sub-ratings to obtain the comprehensive rating in the key node area. The comprehensive rating reflects the probability of fire hazards in the area. The higher the comprehensive rating, the higher the probability of fire hazards; finally, consider the fire hazards of each key node to construct a fire safety statistical chart to comprehensively reflect the safety degree of each region of a city, that is, the correlation degree between any location in the city and the fire hazards, and then according to the safety degree of each region, carry out corresponding rectification of sub-events;

[0123] The present invention comprehensively and fully considers the degree of fire hazards in a city from a digital perspective, and thus can deploy safety measures for areas with fire hazards before the occurrence of dangers.

[0124] Among them, the key nodes include places prone to fire such as schools, factories, hospitals, etc. The completion status of sub-events includes the quantity of flammable materials, the inspection status of fire-fighting facilities, the usage status of fire-proof materials at key nodes, the coverage of safety publicity, etc. With the popularization of intelligent fire protection, the completion status of these sub-events can be obtained from the monitoring system of the smart city;

[0125] Furthermore, the specific steps of the said step S20 include:

[0126] Define multiple intermediate events under fire hazards as (Q1, Q2, ……, Q n ), and define multiple sub-events as (q1, q2, ……, q m ); where n represents the number of the intermediate events, and m represents the number of the sub-events;

[0127] Obtain the historical data of each said sub-event q j for the historical estimated probability ζ i of the corresponding said intermediate event Q ij ; i = (1, 2, ……, n), j = (1, 2, ……, m);

[0128] According to the completion status of the said sub-events, optimize the said historical estimated probability ζ ij to obtain the current estimated probability Y ij of the said intermediate event;

[0129] Based on the current estimated probability Y ij of each said intermediate event, calculate the occurrence probability of the said fire hazard:

[0130] ;

[0131] where, θ = (1, 2, ……, v), v represents the total number of key nodes, P(θ) represents the occurrence probability of the fire hazard in the θ-th key node, q j ∈Q i represents the sub-event j under the intermediate event i, k ∈ [1, n], q j ∈Q i UQ k represents the sub-event j under the intermediate event i or k;

[0132] According to the occurrence probability P of the said fire hazard, calculate the partial derivative of each said sub-event q ij under each said intermediate event to obtain the key value E ij of each said sub-event q ij ;

[0133] .

[0134] It is understandable that intermediate events are the causes of fire hazards, including the fire in the reference room, casualties, house damage, etc. Among them, the influence degree of each sub-event on the intermediate event is different according to historical data. For example, whether to set fireproof materials for the storage cabinets will greatly affect the probability of a fire in the reference room, but has less direct impact on casualties. What this invention discusses is the direct impact; through historical data, the sub-events q j For the corresponding intermediate event Q i The historical estimated probability ζ ij , and then update the historical estimated probability ζ ij according to the completion situation of the sub-events. For example, in historical data, when the number of fire-fighting facilities in the reference room is 2, the probability of causing a fire in the reference room is 0.5. Then when it is reduced to 1, we optimize the probability to 1%, and then obtain the current estimated probability Y ij ; Then, after comprehensively considering all intermediate events, the occurrence probability of the fire hazard can be calculated. In the formula, the first term represents the sum of the occurrence probabilities of each sub-event in each intermediate event. Since some sub-events have duplicate calculations for intermediate events, the second term represents subtracting the probability of simultaneous occurrence due to the same sub-event in any two intermediate events, and then calculating the occurrence probability P of the fire hazard. Since the P(θ) function is a multivariate function, taking the partial derivative of the sub-events can obtain the sub-events q ij The key value E ij of, and the key value E ij reflects the influence degree of the sub-events revealed by historical data on the fire hazard at the current key node.

[0135] Furthermore, the specific steps of the step S30 include:

[0136] Obtain the historical data of the influence of sub-events on intermediate events at different key nodes from the monitoring system of the smart city, and construct a standardized matrix Ζ(θ);

[0137] ;

[0138] Among them, ζ nmv represents the historical estimated probability of intermediate event n caused by the influence of m sub-event at the θ key node;

[0139] Calculate the weights of the historical estimated probabilities ζ nmv of each sub-event on different intermediate events at different key nodes;

[0140] ;

[0141] Among them, Hj represents the entropy of the j-th sub-event represents the weight of the j-th sub-event under the i-th intermediate event in the key node θ;

[0142] Multiply the weights of the corresponding sub-events in each of the said key nodes to obtain the weight value W of the influence of each of the said sub-events itself on each of the said intermediate events ij .

[0143] It can be understood that in order to avoid the influence of sub-events in a region on fire hazards from forming local optima or local minima, it is necessary to consider the influence of sub-events in other regions on fire hazards. First, a standardization matrix is constructed for each key node θ. The values in the standardization matrix reflect the influence of sub-events on intermediate events in different key regions. Here, we use the entropy calculation method to measure the influence of sub-events on fire hazards. First, calculate the entropy of the sub-events, then calculate the weights of the sub-events in different key nodes for different intermediate events, and then multiply the weights of the sub-events in each key node for the same intermediate event to obtain the weight value W of the influence of the sub-events themselves on each intermediate event ij .

[0144] Furthermore, in the step S40, the formula for obtaining the importance of the sub-events at each of the said key nodes is as follows:

[0145] W ij ·E ij =G ij ;

[0146] where G represents the importance.

[0147] It can be understood that after obtaining the weight value W of the influence of the sub-events themselves on each intermediate event ij its value is multiplied by the key value E of the sub-events in each key node ij to obtain the importance, which more accurately reflects the influence of the sub-events on fire hazards in each key node.

[0148] Furthermore, the specific steps of the step S50 include:

[0149] Define a sub-scoring interval O for the importance, and calculate the expected value, entropy value, and hyper-entropy value of the sub-events at each of the said key nodes according to the sub-scoring interval O;

[0150] ;

[0151] ;

[0152] ;

[0153] Among them, represents the expected value, represents the entropy value, represents the hyperentropy value, = 0.02, and respectively represent the upper limit value and the lower limit value of the scoring interval o, represents the order of the normal function within the scoring interval O;

[0154] Calculate the matching degree ψ of the sub-events in the key node within the sub-scoring interval;

[0155] ;

[0156] Fuse the matching degrees of all sub-events in the key node within the sub-scoring interval to obtain the total matching degree K;

[0157] Based on the total matching degree K, quantitatively comprehensively score the key node η;

[0158] ;

[0159] Among them, β represents the level of the total matching degree K.

[0160] It can be understood that after obtaining the influence of each sub-event in the key area on the fire hazard, the matching degree of the sub-event within the self-defined sub-scoring interval can be calculated according to the above algorithm. Through the matching degree, the influence of the sub-event on the fire hazard can be more intuitively measured. This algorithm is based on the cloud model, which has been widely used in the field of safety assessment. Its idea is to convert the importance of qualitative analysis into a quantitative concept. The expected value, entropy value, and hyperentropy value are the characteristics of the cloud model. Then, based on the expected value, entropy value, and hyperentropy value, the matching degree is obtained, and the importance of qualitative analysis is mapped to the matching degree; then, the matching degrees of all sub-events in a key node are added to obtain the total matching degree K, and then through the comprehensive scoring formula, the comprehensive score of the entire key area is obtained. This comprehensive score reflects the safety situation of a region. Since all the sub-events in this solution are analyzed based on the events that have an adverse impact on the fire situation, the higher the score, the higher the fire hazard and the less safe, and the lower the score, the lower the fire hazard and the safer.

[0161] Furthermore, the specific steps of step S60 include:

[0162] Based on the comprehensive scores of all the key nodes, construct a fire safety statistical chart of the city. According to the fire safety statistical chart, obtain the correlation between any place in the city and the fire hazard, specifically including:

[0163] Construct the kernel density map of the city according to the city's floor plan;

[0164] ;

[0165] ;

[0166] where f(x) represents the kernel density at position x, represents the position of the θ-th key node on the kernel density map, T represents the spatial dimension, represents the bandwidth, and L represents the spatial weight function;

[0167] Calculate the bandwidth in the kernel density map based on the comprehensive scores of all the key nodes ;

[0168] ;

[0169] ;

[0170] where VD represents the weighted standard distance, represents the comprehensive score at the θ-th key node, { , , } respectively represent the three-axis coordinates at the θ-th key node, { , , } respectively represent the weighted average centers of the three axes after considering the comprehensive score. The kernel density map has multiple field values that convert non-quantitative features into quantitative features. μ represents the sum of all field values in the kernel density map, and D m represents the median distance of the weighted average center of the three axes;

[0171] Substitute the bandwidth into the kernel density map to obtain the fire safety statistical map of the city;

[0172] Analyze the kernel density of each region in the fire safety statistical map based on the Moran index analysis method to obtain the Moran index of each region. Consider the regions with Moran index greater than the preset index as regions with high correlation with the fire hazards and record them.

[0173] It can be understood that after obtaining the comprehensive scores of each key node, the comprehensive scores of the key nodes can be embedded in the map. Specifically, construct the kernel density map, and then reasonably calculate the most critical parameter - bandwidth in the kernel density map through the comprehensive scores of each key node. By using the comprehensive score as the weight, let the points on the three axes at each key node { , , } are weighted to obtain the weighted average center { , , }, and then the weighted distance VD can be calculated. Then, the bandwidth is calculated through the weighted distance VD. The bandwidth obtained by this algorithm is more reasonable. When the bandwidth is too large, the conclusion reflected by the kernel density map is rougher. When the bandwidth is too small, it cannot reflect the overall safety level of the city. Then, the kernel density map is calculated through the bandwidth, and then the kernel density values of each location in the city can be obtained. Furthermore, the fire hazard situation in different regions can be intuitively felt in the kernel density map. Then, the Moran index is used to evaluate the autocorrelation degree of each location in the kernel density map. The autocorrelation degree can reflect the spatial correlation degree between a region and the whole, and then the correlation between the fire hazard degree of each location and other locations can be obtained. Thus, whether the Moran index of this region exceeds the preset Moran index threshold is used to judge whether this region is in a dangerous state, and then fire hazard prevention is carried out in advance for each region from the level of big data.

[0174] In summary, the fire hazard identification method based on a smart city in the above embodiments of the present invention comprehensively considers the fire hazard degree of a city from a digital perspective, and then, before a danger occurs, safety deployment can be carried out for the areas with fire hazards.

[0175] Please refer to Figure 2 , which shows the fire hazard identification system based on a smart city in the second embodiment of the present invention, including:

[0176] The first acquisition module 11: is used to select key nodes in the city and obtain the completion status of sub-events related to fire at the key nodes based on the monitoring system of the smart city;

[0177] The second acquisition module 12: is used to obtain the influence of the historical data of sub-events at each key node on fire hazards based on the monitoring system of the smart city, and comprehensively consider the completion status of the sub-events to obtain the key values of sub-events at each key node;

[0178] Specifically, the second acquisition module 12 is used for:

[0179] Define multiple intermediate events under fire hazards as (Q1, Q2,..., Q n ), and define multiple sub-events as (q1, q2,..., q m ); where n represents the number of intermediate events, and m represents the number of sub-events;

[0180] Obtain the historical estimated probability ζ of the historical data of each sub-event q j for the corresponding intermediate event Q i from the monitoring system of the smart cityij ; i = (1, 2, ……, n), j = (1, 2, ……, m);

[0181] According to the completion status of the sub - events, optimize the historical estimated probability ζ ij to obtain the current estimated probability Y of the intermediate event ij ;

[0182] Based on the current estimated probability Y of each intermediate event ij , calculate the occurrence probability of the fire hidden danger:

[0183] ;

[0184] where, θ = (1, 2, ……, v), v represents the total number of key nodes, P(θ) represents the occurrence probability of the fire hidden danger in the θ - th key node, q j ∈Q i represents the sub - event j under the intermediate event i, k ∈ [1, n], q j ∈Q i UQ k represents the sub - event j under the intermediate event i or k;

[0185] According to the occurrence probability P of the fire hidden danger, calculate the partial derivative of the sub - event q ij under each intermediate event to obtain the critical value E ij of the sub - event q ij ;

[0186] ;

[0187] The third acquisition module 13: used to acquire the influence of the historical data of the sub - events at different key nodes on the fire hidden danger, so as to obtain the weight value of each sub - event itself;

[0188] The third acquisition module 13 is specifically used for:

[0189] Acquire the historical data of the influence of the sub - events at different key nodes on the intermediate events from the monitoring system of the smart city, and construct a standardized matrix Ζ(θ);

[0190] ;

[0191] where, ζ nmv represents the historical estimated probability of the intermediate event n caused by the influence of the m sub - event at the θ key node;

[0192] Calculate the weight of the historical estimated probability ζ nmv of each sub - event at different key nodes for different intermediate events

[0193] ;

[0194] wherein, H j represents the entropy of the j-th sub-event, represents the weight of the j-th sub-event under the i-th intermediate event in the key node θ;

[0195] Multiply the weights of the corresponding sub-events in each of the said key nodes to obtain the weight value W of the influence of each of the said sub-events on each of the said intermediate events ij ;

[0196] Fusion module 14: used to fuse the key values of the sub-events at each of the said key nodes with the weight values of the sub-events themselves to obtain the importance degrees of the sub-events at each of the said key nodes;

[0197] Scoring module 15: used to obtain the sub-scores of each of the said sub-events for the key nodes based on the importance degrees of the sub-events at each of the said key nodes, and fuse all the sub-scores at the key nodes to obtain the comprehensive score at the key nodes;

[0198] The said scoring module 15 is specifically used for:

[0199] Define a sub-score interval O for the said importance degree, and calculate the expected value, entropy value, and hyper-entropy value of the sub-events at each of the said key nodes according to the sub-score interval O;

[0200] ;

[0201] ;

[0202] ;

[0203] wherein, represents the expected value, represents the entropy value, represents the hyper-entropy value, = 0.02, and respectively represent the upper limit value and the lower limit value of the score interval o, represents the order of the normal function within the score interval O;

[0204] Calculate the matching degree ψ of the sub-events in the said key nodes within the said sub-score interval;

[0205] ;

[0206] Fuse the matching degrees of all the sub-events in the said key nodes within the said sub-score interval to obtain the total matching degree K;

[0207] Based on the total matching degree K, quantitatively comprehensively score η for the key nodes;

[0208] ;

[0209] Among them, β represents the level of the total matching degree K;

[0210] Statistics module 16: Used to construct a fire safety statistical graph of the city based on the comprehensive scores of all the key nodes, and obtain the correlation degree between any place in the city and the fire hazards according to the fire safety statistical graph;

[0211] The statistics module 16 is specifically used for:

[0212] Construct a kernel density map of the city according to the floor plan of the city;

[0213] ;

[0214] ;

[0215] Among them, f(x) represents the kernel density at position x, represents the position of the θ-th key node on the kernel density map, T represents the spatial dimension, represents the bandwidth, and L represents the spatial weight function;

[0216] Calculate the bandwidth in the kernel density map based on the comprehensive scores of all the key nodes ;

[0217] ;

[0218] ;

[0219] Among them, VD represents the weighted standard distance, represents the comprehensive score at the θ-th key node, { , , } respectively represent the three-axis coordinates at the θ-th key node, { , , } respectively represent the weighted average centers of the three axes after considering the comprehensive score. The kernel density map has multiple field values that convert non-quantitative features into quantitative features, μ represents the sum of all field values in the kernel density map, and D m represents the median distance of the weighted average center of the three axes;

[0220] Substitute the bandwidth into the kernel density map to obtain the fire safety statistical graph of the city;

[0221] Analyze the kernel density of each area in the fire safety statistical chart based on the Moran index analysis method to obtain the Moran index of each area. Consider the areas with the Moran index greater than the preset index as areas with a high degree of correlation with the fire hazards and record them.

[0222] The present invention also provides an electronic device. Please refer to Figure 3 , which shows the electronic device in the third embodiment of the present invention, including a memory 10, a processor 20, and a computer program 30 stored on the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, the above-mentioned fire hazard identification method based on a smart city is implemented.

[0223] Among them, the memory 10 includes at least one type of storage medium. The storage medium includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 10 can be an internal storage unit of the electronic device in some embodiments, such as the hard disk of the electronic device. The memory 10 can also be an external storage device in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Further, the memory 10 can also include both the internal storage unit of the electronic device and the external storage device. The memory 10 can be used not only to store application software and various data installed in the electronic device, but also to temporarily store data that has been output or will be output.

[0224] Among them, the processor 20 can be an Electronic Control Unit (ECU, also known as a vehicle computer), a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments, and is used to run the program code stored in the memory 10 or process data, such as executing an access restriction program, etc.

[0225] It should be noted that Figure 3 the shown structure does not limit the electronic device. In other embodiments, the electronic device can include fewer or more components than shown, or combine some components, or have different component arrangements.

[0226] The embodiment of the present invention also provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned fire hazard identification method based on a smart city is implemented.

[0227] Those skilled in the art can understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0228] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection part (electronic device) having one or more wirings, a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0229] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0230] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0231] The above-described embodiments merely represent several implementation manners of the present invention. Their descriptions are relatively specific and detailed, but should not be construed as limiting the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

[0232] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0233] The above-described embodiments merely represent several implementation manners of the present invention. Their descriptions are relatively specific and detailed, but should not be construed as limiting the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the patent for the present invention shall be subject to the appended claims.

Claims

1. A fire hazard identification method based on smart city, characterized in that: The steps include: Select key nodes in the city and obtain the completion status of fire-related sub-events at key nodes based on the smart city monitoring system; Based on the monitoring system of the smart city, the impact of the historical data of the sub-events at each of the key nodes on the fire hazards is obtained, and the completion status of the sub-events is integrated to obtain the key values ​​of the sub-events at each of the key nodes; Obtaining the impact of historical data of sub-events at different key nodes on the fire hazards to obtain the weight value of each sub-event itself; The key value of the sub-event at each of the key nodes is combined with the weight value of the sub-event itself to obtain the importance of the sub-event at each of the key nodes; Based on the importance of the sub-events at each of the key nodes, a sub-score of each of the sub-events at the key node is obtained, and all the sub-scores at the key node are integrated to obtain a comprehensive score at the key node; Based on the comprehensive scores of all the key nodes, a fire safety statistical map of the city is constructed, and according to the fire safety statistical map, the correlation between any place in the city and the fire hazards is obtained; The monitoring system based on the smart city obtains the impact of the historical data of the sub-events at each of the key nodes on the fire hazards, and integrates the completion status of the sub-events to obtain the key values ​​of the sub-events at each of the key nodes, specifically including: Define multiple intermediate events under fire hazards as (Q1, Q2, ..., Q n ), and define multiple sub-events as (q1, q2, ..., q m ); wherein n represents the number of the intermediate events, and m represents the number of the sub-events; Obtain each of the sub-events q from the monitoring system of the smart city j The historical data for the corresponding intermediate event Q i The historical estimated probability ζ ij ;i=(1,2,…,n), j=(1,2,…,m); According to the completion of the sub-event, the historical estimated probability ζ ij Optimize to get the current estimated probability Y of the intermediate event ij ; Based on the current estimated probability Y of each intermediate event ij , calculate the probability of occurrence of the fire hazard: ； Among them, θ = (1, 2, ..., v), v represents the total number of key nodes, P (θ) represents the probability of occurrence of fire hazards in the θth key node, q j ∈Q i represents the sub-event j under the intermediate event i, k∈[1,n], q j ∈Q i UQ k represents the sub-event j under the intermediate event i or k; According to the occurrence probability P of the fire hazard, the sub-event q under each intermediate event ij Calculate partial derivatives to obtain the sub-event q under each intermediate event ij The key value E ij ; ； The importance of each sub-event at each key node is used to obtain a sub-score of each sub-event at the key node, and all sub-scores at the key node are integrated to obtain a comprehensive score at the key node, specifically including: Defining a sub-scoring interval O for the importance, and calculating the expected value, entropy value and super entropy value of the sub-event at each of the key nodes according to the sub-scoring interval O; ； ； ； in, Indicates the expected value, represents the entropy value, represents the super entropy value, =0.02, and They represent the upper and lower limits of the scoring interval o respectively. represents the order of the normal function in the scoring interval O; Calculate the matching degree ψ of the sub-event in the key node in the sub-scoring interval; ； Among them, G represents importance; Merging the matching degrees of all sub-events of the key node in the sub-scoring interval to obtain a total matching degree K; Based on the total matching degree K, a quantitative comprehensive score η is given to the key node; ； Among them, β represents the level of the total matching degree K; Based on the comprehensive scores of all the key nodes, a fire safety statistical map of the city is constructed. According to the fire safety statistical map, the correlation between any place in the city and the fire hazards is obtained, including: According to the city's floor plan, construct the city's kernel density map; ； ； Where f(x) represents the kernel density at position x, represents the position of the θth key node on the kernel density map, T represents the spatial dimension, represents bandwidth, L represents the spatial weight function; Based on the comprehensive scores of all the key nodes, the bandwidth in the kernel density map is calculated ; ； ； Among them, VD represents the weighted standard distance, represents the comprehensive score at the θth key node, { , , } respectively represent the three-axis coordinates of the θth key node, { , , } respectively represent the weighted average center of the three axes after considering the comprehensive score, the kernel density map has multiple field values ​​that convert non-quantitative features into quantitative features, μ represents the sum of all field values ​​in the kernel density map, D m represents the median distance of the weighted average center of the three axes; The bandwidth Substitute it into the kernel density map to obtain the fire safety statistics map of the city; The kernel density of each area in the fire safety statistical diagram is analyzed based on the Moran's index analysis method to obtain the Moran's index of each area. The area where the Moran's index is greater than the preset index is regarded as an area with a high correlation with the fire hazard and is recorded.

2. The fire hazard identification method based on smart city according to claim 1 is characterized in that: The acquisition of the influence of the historical data of sub-events at different key nodes on the fire hazards to obtain the weight value of each sub-event itself specifically includes: Obtain historical data on the impact of sub-events at different key nodes on intermediate events from the monitoring system of the smart city, and construct a standardized matrix ζ(θ); ； Among them, nmv represents the historical estimated probability of the intermediate event n caused by the influence of the m sub-event at the key node θ; Calculate the historical estimated probability ζ of each sub-event at different key nodes for different intermediate events nmv The weight of ； Among them, H j represents the entropy of the j-th sub-event, represents the weight of the jth sub-event under the i-th intermediate event in the key node θ; The weight of the corresponding sub-event in each key node Multiply them to obtain the weight value W of each sub-event's influence on each intermediate event. ij .

3. The fire hazard identification method based on smart city according to claim 2 is characterized in that: The formula for fusing the key value of the sub-event at each key node with the weight value of the sub-event itself to obtain the importance of the sub-event at each key node is as follows: W ij ·HAVE BEEN ij =G ij ; Among them, G represents importance.

4. A fire hazard identification system based on smart city, characterized in that: include: The first acquisition module is used to select key nodes in the city and obtain the completion status of sub-events related to fire protection at the key nodes based on the monitoring system of the smart city; The first acquisition module is specifically used for: Define multiple intermediate events under fire hazards as (Q1, Q2, ..., Q n ), and define multiple sub-events as (q1, q2, ..., q m );in n represents the number of the intermediate events, and m represents the number of the sub-events; Obtain each of the sub-events q from the monitoring system of the smart city j The historical data for the corresponding intermediate event Q i The historical estimated probability ζ ij ;i=(1,2,…,n), j=(1,2,…,m); According to the completion of the sub-event, the historical estimated probability ζ ij Optimize to get the current estimated probability Y of the intermediate event ij ; Based on the current estimated probability Y of each intermediate event ij , calculate the probability of occurrence of the fire hazard: ； Among them, θ = (1, 2, ..., v), v represents the total number of key nodes, P (θ) represents the probability of occurrence of fire hazards in the θth key node, q j ∈Q i represents the sub-event j under the intermediate event i, k∈[1,n], q j ∈Q i UQ k represents the sub-event j under the intermediate event i or k; According to the occurrence probability P of the fire hazard, the sub-event q under each intermediate event ij Calculate partial derivatives to obtain the sub-event q under each intermediate event ij The key value E ij ; ； The second acquisition module is used to acquire the impact of the historical data of the sub-events at each of the key nodes on the fire hazard based on the monitoring system of the smart city, and to obtain the key value of the sub-event at each of the key nodes by integrating the completion status of the sub-events; The third acquisition module is used to acquire the impact of the historical data of sub-events at different key nodes on the fire hazards, so as to obtain the weight value of each sub-event itself; Fusion module: used to fuse the key value of the sub-event at each key node with the weight value of the sub-event itself to obtain the importance of the sub-event at each key node; Scoring module: used to obtain the sub-score of each sub-event at the key node based on the importance of the sub-event at each key node, and integrate all the sub-scores at the key node to obtain the comprehensive score at the key node; The scoring module is specifically used for: Defining a sub-scoring interval O for the importance, and calculating the expected value, entropy value and super entropy value of the sub-event at each of the key nodes according to the sub-scoring interval O; ； ； ； in, Indicates the expected value, represents the entropy value, represents the super entropy value, =0.02, and They represent the upper and lower limits of the scoring interval o respectively. represents the order of the normal function in the scoring interval O; Calculate the matching degree ψ of the sub-event in the key node in the sub-scoring interval; ； Among them, G represents importance; Merging the matching degrees of all sub-events of the key node in the sub-scoring interval to obtain a total matching degree K; Based on the total matching degree K, a quantitative comprehensive score η is given to the key node; ； Among them, β represents the level of the total matching degree K; Statistics module: used to construct a fire safety statistics map of the city based on the comprehensive scores of all the key nodes, and obtain the correlation between any place in the city and the fire hazards according to the fire safety statistics map; The statistical module is specifically used for: According to the city's floor plan, construct the city's kernel density map; ； ； Where f(x) represents the kernel density at position x, represents the position of the θth key node on the kernel density map, T represents the spatial dimension, represents bandwidth, L represents the spatial weight function; Based on the comprehensive scores of all the key nodes, the bandwidth in the kernel density map is calculated ; ； ； Among them, VD represents the weighted standard distance, represents the comprehensive score at the θth key node, { , , } respectively represent the three-axis coordinates of the θth key node, { , , } respectively represent the weighted average center of the three axes after considering the comprehensive score, the kernel density map has multiple field values ​​that convert non-quantitative features into quantitative features, μ represents the sum of all field values ​​in the kernel density map, D m represents the median distance of the weighted average center of the three axes; The bandwidth Substitute it into the kernel density map to obtain the fire safety statistics map of the city; The kernel density of each area in the fire safety statistical diagram is analyzed based on the Moran's index analysis method to obtain the Moran's index of each area. The area where the Moran's index is greater than the preset index is regarded as an area with a high correlation with the fire hazard and is recorded.

5. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the fire hazard identification method based on a smart city as described in any one of claims 1 to 3 is implemented.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the fire hazard identification method based on smart city as described in any one of claims 1-3 is implemented.

Images