City safety risk grading assessment early warning system

Abstract

The invention relates to the technical field of safety risk grading, in particular to an urban safety risk grading evaluation early warning system which comprises a risk sampling module, a region division module, a risk load module, a risk progressive module and a risk updating module. Risk data and risk types in a sampling area are listed; performing area grading by using the risk type and the area risk load capacity of each sampling area, and determining an area risk distribution diagram of each sampling area; extracting risk points from the regional risk distribution map, and generating a regional risk load probability according to the data proportion of each risk point and the regional risk load capacity; setting the risk point load capacity of each risk point, and extracting the progressive probability of the risk point load capacity to obtain the relative risk state of each sampling area; according to the relative risk state of each sampling area, identifying a risk entity of each sampling area and an updating range of the risk entity, and carrying out risk level iteration updating on each sampling area; and the efficiency of risk grade division is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of safety risk classification, and in particular to a city safety risk classification assessment and early warning system. Background Art

[0002] In modern society, urban safety risk assessment is a crucial issue. As crucial places for human life, work, and recreation, urban safety directly impacts quality of life and social stability. Static scoring card models are often used to stratify urban safety risks, but they fail to reflect the dynamic evolution of risk. Furthermore, because spatial analysis often relies on coarse-grained demarcation of administrative boundaries, it is difficult to pinpoint risk hotspots during risk stratification. This leads to delays and reduced accuracy in urban risk identification.

[0003] For example, Chinese patent publication number CN118297409A discloses a method, device, electronic device, and storage medium for urban underground safety risk assessment. This method, which belongs to the field of geological hazard assessment technology, includes: obtaining risk factors that affect urban underground safety; normalizing the risk factors according to a pre-constructed risk assessment matrix to obtain normalized risk factors; constructing an urban underground safety risk assessment model structure based on the risk factors and the causal relationships between the risk factors; determining an urban underground safety risk assessment model based on the normalized risk factors and the urban underground safety risk assessment model structure; obtaining safety risk data for the urban underground to be assessed, inputting the safety risk data into the urban underground safety risk assessment model, and obtaining an assessment result for the urban underground to be assessed.

[0004] For example, Chinese patent publication number CN117952413A discloses a method and system for assessing urban safety risks, which involves the technical field of safety risk assessment. The method involves collecting urban safety risk information about a specific area through urban IoT devices. An urban safety risk assessment center obtains the urban safety risk information collected by the IoT devices and compares it with historical data in a database to identify the urban safety risk category. After confirming the urban safety risk category, the IoT devices collect detailed information about the risk source, assess the urban safety risk level, and send a notification. The beneficial effects of the present invention include utilizing IoT devices to monitor the urban environment in real time, collecting various types of safety risk information, and then comparing and analyzing the information with historical data in a database to identify the risk type and assess the risk level.

[0005] The existing technology uses Bayesian networks to provide early warning descriptions of accident types and describes the status of risk sources in terms of risk status. However, the existing technology only considers the risk sources existing in a single area, and does not comprehensively classify the distribution of multiple risk points in the city. As a result, there are problems such as small data samples considered in risk classification and insufficient correlation in identifying risk areas. As a result, the comprehensive classification corresponding to risk areas cannot be quickly identified through the focus areas existing in each risk source, which is not conducive to overall decision-making and observation of urban risks. Summary of the Invention

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: a city safety risk classification assessment and early warning system, including: a risk sampling module, used to sample data on urban safety risks, list risk data in the sampling area, and describe the risk type in the sampling area with risk data.

[0007] The regional division module is used to classify regions according to the risk type and regional risk load capacity of each sampling area, and determine the regional risk distribution map of each sampling area.

[0008] The risk load module is used to extract risk points from the regional risk distribution map, and quantitatively evaluate the regional risk load capacity of each sampling area based on the data proportion of each risk point in the regional risk distribution map to generate the regional risk load probability.

[0009] The risk progression module is used to identify the risk radius of each risk point in the sampling area, set the risk point load capacity of each risk point based on the risk type and regional risk load probability within the risk radius, and extract the progressive probability of the risk point load capacity to obtain the relative risk status of each sampling area.

[0010] The risk update module is used to construct a risk event network to analyze the logical transmission relationship of each risk point based on the relative risk status of each sampling area, identify the risk entities and the update scope of risk entities under each sampling area, and iteratively update the risk level of each sampling area in combination with the risk evolution path of the risk event network.

[0011] The beneficial effects of the present invention are: 1. The present invention samples the distribution of urban safety risk data in a grid form through a data structure of sampling points, risk types and characteristic gradients, and sets risk labels for each risk type to construct data content about the distribution of risk types in the city. After dynamically displaying the probability of integrating each risk type, the accuracy of risk assessment and setting can be improved.

[0012] 2. The present invention optimizes the efficiency of grading each region by adjusting the risk probability of the regional risk based on the relative data of multiple time intervals, and then grading the risk types in each region and introducing the relatively set regional risk load capacity of each region; by using the probability interval after the risk probability adjustment as the basis for setting the graded area, introducing the number of grades and the area of the region after grading, and adjusting the number of grades, the method of regional adaptive adjustment when dividing the risk area is realized, which improves the cycle of regional grading and shortens the update cycle of urban risk data when risks occur.

[0013] 3. The present invention extracts labels from the regional risk distribution map based on the proportion of risk types, regional risk load capacity and regional risk load probability, sets a combined label for each risk point, and describes the regional risk load probability of each risk point; then introduces the Bayesian theorem and risk radius to dynamically update the progressive probability of each risk point, realizing a mapping relationship between multiple risk points and the carrying capacity of urban infrastructure, and by calculating the corresponding transmission form of its progressive probability, it can identify the corresponding range and update range of each risk entity when the risk occurs, thereby realizing the calibration and iterative update process of the dynamic transfer of risks, and establishing an early warning and protection mechanism related to risk entities, risk evolution paths and urban infrastructure. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention will be further described below with reference to the accompanying drawings and examples.

[0015] Figure 1 It is a system diagram of a city safety risk classification assessment and early warning system.

[0016] Figure 2 The present invention is a flowchart of a risk sampling module of a city safety risk grading assessment and early warning system.

[0017] Figure 3 The present invention is a flowchart of a regional division module of a city safety risk classification assessment and early warning system.

[0018] Figure 4 The present invention is a flow chart of the risk load module of a city safety risk classification assessment and early warning system.

[0019] Figure 5 The present invention is a flow chart of the risk progression module of a city safety risk grading assessment and early warning system.

[0020] Figure 6 The present invention is a flowchart of a risk update module of a city safety risk classification assessment and early warning system. DETAILED DESCRIPTION

[0021] The following embodiments of the present invention are described in detail. The embodiments described below are exemplary and are only used to explain the present invention, and are not to be construed as limiting the present invention. Where specific techniques or conditions are not specified in the embodiments, the techniques or conditions described in the literature in the art or in the product specifications shall be followed.

[0022] See Figure 1 A city safety risk classification assessment and early warning system includes: a risk sampling module, a regional division module, a risk load module, a risk progression module and a risk update module; wherein the output end of the risk sampling module is connected to the regional division module, the output end of the regional division module is connected to the risk load module, the output end of the risk load module is connected to the risk progression module, and the output end of the risk progression module is connected to the risk update module.

[0023] The risk sampling module is used to sample data on urban safety risks, list the risk data within the sampling area, and describe the risk types within the sampling area with risk data.

[0024] The regional division module is used to classify regions according to the risk type and regional risk load capacity of each sampling area, and determine the regional risk distribution map of each sampling area.

[0025] The risk load module is used to extract risk points from the regional risk distribution map, and quantitatively evaluate the regional risk load capacity of each sampling area based on the data proportion of each risk point in the regional risk distribution map to generate the regional risk load probability.

[0026] The risk progression module is used to identify the risk radius of each risk point in the sampling area, set the risk point load capacity of each risk point based on the risk type and regional risk load probability within the risk radius, and extract the progressive probability of the risk point load capacity to obtain the relative risk status of each sampling area.

[0027] The risk update module is used to construct a risk event network to analyze the logical transmission relationship of each risk point based on the relative risk status of each sampling area, identify the risk entities and the update scope of risk entities under each sampling area, and iteratively update the risk level of each sampling area in combination with the risk evolution path of the risk event network.

[0028] Preferably, when sampling data for urban safety risks, potential risks that may occur in the city, such as natural disasters and man-made accidents, are described, and the form and content of the risk are defined. After the risk is defined, data is extracted from the database where the urban risk is located, and the risk types present in the data are described. The frequency of occurrence of each type of risk in the sampling area, the scope of impact, the possible losses, and the location where each type of risk occurs are marked in the risk data, and the label of the risk type is explained.

[0029] like Figure 2 As shown, the implementation method of the risk sampling module also includes: specifying each sampling area, obtaining sampling points of risk data in each sampling area, and listing the risk data in the sampling area according to the risk type of multiple sampling points.

[0030] Based on the gradient of each risk type, the frequency of occurrence, scope of impact, losses caused and geographical location of the risk type in the sampling area are characterized, and risk labels corresponding to the risk types are set.

[0031] Determine whether the risk label matches the current sampling area. If so, calculate the probability of the current risk label appearing at each sampling point based on the risk type; if not, mark the risk label as a no-risk event.

[0032] After adding risk tags to risk types, the corresponding risk types will be output.

[0033] Preferably, the sampling area includes multiple urban divisions such as commercial areas, industrial areas, and residential areas. Then, in each sampling area, by searching historical data, the problems existing in the area are represented by risk points, such as restaurant kitchen fire risk points in commercial areas, hazardous chemical warehouse leakage risk points in industrial areas, etc. After listing all possible risk locations in each sampling area, they are classified according to the risk types of their risk points, such as fire, theft, environmental pollution, heavy snowfall, etc., which represent risk types of urban risks. Then, the frequency of occurrence, scope of impact, loss caused and geographical location of each risk type are extracted for description, such as the historical number of occurrences and time period, and the average annual occurrence of fires in a certain area is 3 times. After defining the scope of the risk, the loss caused by the corresponding risk is checked, such as the average loss of 500,000 yuan for a single fire, and other quantitative data to illustrate the specific situation of the corresponding risk type; the geographical location mainly describes the relative coordinates of the risk point, which is used for the subsequent description of the relative impact of the region and individual risk points. Finally, determine whether the risk label describing the risk type can match the location of the sampling area. For example, a red label is marked on a residential area indicating a hazardous chemical leak. If there is an obvious mismatch, the mismatched risk label will be marked as an invalid risk, thereby completing the risk listing of the current sampled data. These risk types are used to list the risk situations in different areas, which serve as the main conditions and main data framework for urban risk assessment.

[0034] Preferably, the gradient of risk types represents the values of frequency of occurrence, scope of impact, loss caused and geographical location.

[0035] Preferably, to determine whether a risk label matches the current sampling area, the area represented by each sampling area can be used to determine whether the risk label of the risk category is correct based on the pre-set association rules of the risk label's description in historical data. If correct, this facilitates the subsequent use of the risk type to describe the risk load capacity of the current sampling area. The pre-set association rules primarily determine whether the risk type is data that normally appears in the sampling area, thereby preventing data acquisition errors.

[0036] In one embodiment of the present invention, the regional division module mainly adopts regional risk load capacity to carry out hierarchical planning for each region. Regional risk load capacity refers to the comprehensive ability of a specific region to withstand, respond to and recover from risk events within a unit time; regional risk load capacity can be set through the following contents, such as response capacity, bearing capacity and recovery capacity. For example, bearing capacity can be through infrastructure disaster resistance, evacuation capacity, key resource redundancy, such as power / communication dual-circuit coverage, etc.; response capacity can be expressed through emergency response timeliness, emergency resource reserves and emergency plan completeness, etc., to describe the speed of each region's response to risks and the completeness of preset plans to describe the region's response capabilities; recovery capacity can choose dimensions such as economic resilience, social resilience, and ecological restoration capacity to illustrate the speed and ability to recover after the risk occurs.

[0037] At this time, the situations represented by the response capability, tolerance and recovery capability in the current sampling area are digitally represented, and the conditional probability of the three capabilities and various risk types appearing together represents the regional risk load capacity in the current sampling area. The nonlinear relationship between capability and risk is reflected by the conditional probability to describe the hierarchical differentiation of regional capabilities under different risks. For example, if the current risk type is leakage of a certain item, then the response capability, tolerance and recovery capability of the facilities in the area are respectively selected as 0.6, 0.75 and 0.5. At this time, the probability of leakage of this risk type is calculated when the corresponding capability is at the corresponding value, thereby describing the value of regional risk load capacity in different sampling areas; that is, the index value of regional risk load capacity is based on the conditional probability of the preset response capability, tolerance and recovery capability of the region under different risk types.

[0038] Preferably, Figure 3 As shown, the implementation method of the regional division module includes: using the regional risk load capacity of each sampling area to determine whether the basic risk probability when the current risk type occurs is greater than the index value of the regional risk load capacity; if it is greater, the difference between the basic risk probability when the current risk type last occurred and the index value of the regional risk load capacity is used as the basic risk probability of the current risk type.

[0039] If it is less than, the risk excess probability is set based on the upper limit of the difference between the basic risk probability in the current risk type and the index value of the current regional risk load capacity.

[0040] According to the risk excess probability, the increasing probability difference between the current risk type and the regional risk load capacity in multiple time intervals is identified, and the increasing probability difference is used as the probability interval for regional classification; according to the probability interval of regional classification, the regional risk distribution map is output.

[0041] Preferably, the above-mentioned basic risk probability represents the probability value of a certain risk type occurring, and the basic risk probability will be determined based on the number of times the corresponding risk type appears in historical data divided by the number of times all risk types appear; then the probability value of the risk occurrence is judged and compared with the index value of the regional risk load capacity to prevent the occurrence of a single risk probability that is too high and triggers an over-response, resulting in large data fluctuations when identifying historical risk events in the sampling area. At the same time, the index value of the regional risk load capacity will use the basic risk probability of the risk type and the conditional probability corresponding to the corresponding response capacity, tolerance and recovery capacity of the facilities in the current area. The conditional probability is calculated based on the sampled historical data; risk The basic risk probability of the type is also calculated based on the historical data of the sampling. After that, when the basic risk probability is reduced through dynamic adjustment, the basic risk probability of all risk types is identified, and the difference with the regional risk load capacity is obtained. The upper limit of the difference is expressed in the form of the absolute value when the two are subtracted. Then, according to the time series, the probability difference of the risk excess probability of the different types corresponding to the difference is found at different time points to evolve whether the risk events of the corresponding risk type increase or decrease over time, to indicate whether the area needs to be adjusted, to represent the evolution trend of different risk types over time, and to divide these areas into regional risk distribution maps on the sampling area through the intervals shown by the increasing probability difference.

[0042] That is, according to the probability interval of regional classification, when outputting the regional risk distribution map, a mapping relationship is established between the probability interval of regional classification and the sampling area, the area corresponding to the value of each probability interval is regarded as the classification area, and the positions of each classification area are combined into a regional risk distribution map.

[0043] Preferably, the incremental probability difference is expressed as the difference in the risk excess probability of the corresponding risk type in the current risk data within multiple time intervals, which is regarded as the incremental probability difference to identify whether the risk in the current area is gradually increasing or decreasing, so as to determine the regional risk and dynamic probability of each area under the risk classification.

[0044] Preferably, it performs regional classification according to the risk type and regional risk load capacity of each sampling area, and the implementation method of determining the regional risk distribution map of each sampling area also includes: loading the mapping relationship between risk type and sampling area, and calculating the number of levels and the size of the graded area when grading the area.

[0045] According to the data distribution of each graded area during regional classification, the distance between the center points of each graded area is used to cluster the data.

[0046] The difference in the number of grades of the corresponding graded areas before and after clustering is recorded, and the difference in the number of grades is output as a remark label of its regional risk distribution map.

[0047] Preferably, the number of levels during regional classification is used to indicate the number of levels the sampling area is divided into. The number of levels is set based on the value of the probability interval. For example, when each risk type is incrementally judged using the risk excess probability in the current sampling area, an area of probability value change will be formed. For example, in four consecutive time zones, the difference between the values of the risk excess probability in two consecutive time intervals forms an interval, such as a probability interval in the form of {+0.1, -0.1, +0.2}. After obtaining the probability interval corresponding to each risk type, multiple groups of numerical values in different forms of change can be obtained, and then multiple risk points representing different areas can be obtained. These points are then clustered to obtain a comprehensive regional risk distribution map.

[0048] Preferably, the mapping relationship between the loaded risk type and the sampling area is used to view the corresponding risk type of the graded area in the regional risk distribution map, and how the risk type is recorded in the current sampling area. Then, the number and area size of the graded areas divided at this time are identified to identify the distribution form of different risk types in the current sampling area. Then, clustering is performed on the distribution of corresponding data of each graded area and the center point of the corresponding area to identify the risk propagation pattern or hot spot area in different probability intervals. When the final output regional risk distribution map is generated, its XY axis is used as the geographical coordinates of the corresponding sampling area, and the Y axis is used to display the increasing probability difference between the risk type and the regional risk load capacity of each area in multiple time intervals to represent the risk situation generated at the geographical coordinates of the corresponding area.

[0049] Preferably, when calculating the number of classifications in regional classification, the data of each classification area is loaded to obtain the area occupied by each classification area in the sampling area, and the classification area with the largest area is taken as the starting point, and the size of the classification area is set to , obtain the secondary area of the hierarchical area, and make the secondary area according to the preset ratio value To set, the area of the secondary area of the current classification area is located in arrive Between, let the secondary area be divided continuously according to the preset ratio value, and obtain 、 The divided intervals are repeated until no corresponding grading area exists in the divided intervals. The number of divisions is regarded as the number of levels in the current grading area. The preset ratio value is a positive integer greater than 0, which is used to adjust the number of levels in the current grading area. The value can be based on the preset ratio value that is used most frequently in the grading area division in the historical data, or the average value of the preset ratio value used in the historical data.

[0050] Subsequently, data clustering using the distance between the center points of each grading area also includes clustering the nearest grading area to the center point of any grading area, where the nearest grading area indicates that the distance between the center points of two adjacent grading areas is the smallest, and the grading areas are continuously clustered until the average values of the distances between the center points of each grading area in the multiple areas composed of the grading areas are equal, thereby obtaining multiple areas after the grading areas are clustered, and calculating the grading number of the clustered areas in the same way as the grading number of the grading areas, and then calculating the difference between the grading numbers before and after clustering as the output annotation label; the multiple areas after clustering are used as the output regional risk distribution map.

[0051] In one embodiment of the present invention, the risk load module is mainly used to identify the position of the risk point in the regional risk distribution map and set the regional risk load probability that the risk point can correspond to.

[0052] Preferably, when extracting risk points, the risk points are selected from the regions after hierarchical regional clustering to represent the proportion of data representing regional risks in the clustered regions to the total sampled data. Subsequently, when describing the regional risk load capacity of each sampling region, it can be understood as integrating the conditional probabilities of the response capacity, tolerance, and recovery capacity of the region corresponding to the current risk point for the corresponding risk type to obtain the regional risk load probability.

[0053] For example, the ratio of data collected within the current sampling area for a risk point corresponding to a single risk type is set as the type ratio. After multiplying the type ratio by the indicator value of the regional risk load capacity, the product is averaged based on the number of risk types that can be matched in the area where the current risk point is located. This average is used as the regional risk load probability. Finally, the calculation is performed for the area where each risk point is located to obtain the regional risk load probability for multiple risk points.

[0054] like Figure 4As shown, the implementation method of the risk load module also includes: extracting labels from the regional risk distribution map and setting a combined label for each risk point; combining the risk type and remark label existing in each cluster area in the regional risk distribution map into a combined label for the current risk point.

[0055] Determine the risk type of the corresponding risk point from the group label, determine the type proportion corresponding to each risk point based on the risk type of each risk point, and describe the regional risk load probability of the corresponding risk point based on the type proportion and regional risk load capacity.

[0056] In one embodiment of the present invention, the risk progression module mainly describes the risk type corresponding to the risk radius of the risk point to identify the comprehensive data situation of the corresponding risk point.

[0057] Preferably, the risk radius of each risk point is based on the radius of the minimum inscribed circle of multiple regions in the regional risk distribution map generated by the final clustering in the regional division module. This risk radius is used to identify urban safety risks arising in different regions. When the risk radius of different regions is accurately set, it is easier to identify risk boundary areas and promote risk management and emergency response cooperation between different regions. This helps to form a unified risk management strategy and improve overall risk response capabilities.

[0058] Preferably, the risk load capacity of a risk point tends to indicate the number of risk events occurring in the area corresponding to the current risk point. When the number of risk events changes, whether the regional risk load capacity of each area is affected under different classifications is considered as the risk point load capacity.

[0059] The progressive probability indicates whether each risk point has linear attenuation or exponential attenuation under the corresponding risk radius, and its attenuation form is used as the relative risk status of each sampling area.

[0060] like Figure 5 As shown, the implementation method of the risk progression module includes: setting the risk radius of each risk point based on the minimum inscribed circle of multiple areas in the regional risk distribution map of each risk point, updating the regional risk load probability of each risk point using the risk type within the risk radius and the corresponding regional risk load probability using the Bayesian theorem, and setting the risk point load capacity of each risk point. At this time, the load capacity of each risk point is the probability value updated by the Bayesian theorem, and then judging whether the risk radius of each risk point overlaps. If so, identify the risk points corresponding to the overlapping risk radii, and calculate the difference in risk point load capacity between the corresponding risk points as the progressive probability of the current risk point, and use the attenuation coefficient of the progressive probability as the relative risk status output of each sampling area.

[0061] If they do not overlap, the difference in risk point load capacity between the two adjacent risk points of the current risk point is used as the progressive probability of the current risk point, and the attenuation coefficient of the progressive probability is used as the relative risk status output of each sampling area.

[0062] Preferably, the method for updating the probability value of each risk point using Bayes' theorem is as follows: assuming that the risk type and risk point are represented by j and i respectively, there are m risk types, where the number of risk types and risk points are set based on their number in the corresponding area of the regional risk distribution map. The regional risk load probability is then updated.

[0063] The formula can be expressed as: ;in, The risk point load capacity of risk point i is expressed as updating and adjusting the regional risk load probability calculated for that risk point to illustrate the value of a single risk point after multiple update iterations. The upper part of this formula describes the relative product of the type proportion and the conditional probability represented by the regional risk load capacity, while the lower part describes the value when the number of events of risk type j contained in risk point i changes after multiple iterations, to illustrate whether its probability value will change accordingly in multiple time intervals; represents the proportion of risk type j, Indicates that risk type j is The index value of regional risk load capacity under the condition of The number of events of risk type j within the risk radius of the current risk point i is used to illustrate the relative value of the regional risk load capacity under the corresponding data proportion of the current risk type. The time quantity is also linked to the type proportion. During the city safety sampling, each data point represents a risk event. Indicates the number of steps to update, The number of events of risk type j within the risk radius of the current risk point i at the kth update step, Indicates that risk type j is This mainly indicates whether the index value of regional risk load capacity will change due to the amount of data when multiple iterations or multiple time intervals are used to iterate and update data for the same risk point and risk type. Under normal circumstances, the regional risk load capacity of risk type j is expressed as ;in, represents the basic risk probability of risk type j, It represents the probability of the corresponding response capability, tolerance capability and recovery capability scores of risk type j in the current region. If the probability value obtained under the relative time quantity is identified, the value is obtained by marking the number of events.

[0064] If i1 and i2 are used to represent overlapping risk points, their attenuation coefficients are It can be expressed as: ;in, It represents the difference in risk point load capacity between risk points i1 and i2, represents the exponential constant, Indicates the linear attenuation exponent, which is generally set to 0.001. Indicates the distance between risk points i1 and i2; the attenuation coefficient output at this time will be output as the label corresponding to its sampling area, and the progressive probability of overlap will be summed to indicate whether the risk of the corresponding area is high risk or low risk. For example, 0.8 and 0.5 are used as the dividing nodes, and the part greater than 0.8 is considered high risk, the part between 0.5 and 0.8 is considered medium risk, and the rest is considered low risk.

[0065] If there is no overlap, let the two adjacent risk points of the current risk point i1 be i3 and i4, and their attenuation coefficients are It is expressed as ;in, It represents the difference in risk point load capacity between the two risk points i3 and i4 adjacent to the current risk point i1; ,in 、 and Represent the risk point load capacity of risk points i1, i3 and i4 respectively, Represents the average distance between the two adjacent risk points i3 and i4, i1, and the previous risk point. The attenuation coefficient obtained here accounts for the difference between the two adjacent risk points and the current risk point, describing their relative risk. Subsequent processing is similar to the attenuation coefficient calculation for overlaps, primarily to determine whether certain areas present elevated urban safety risks.

[0066] In one embodiment of the present invention, Figure 6 As shown, the implementation method of the risk update module includes: starting from the relative risk status, combining the risk entities associated with each risk point, and setting up a risk event network.

[0067] Determine whether there is a relationship between the risk entities in the risk event network. If there is a relationship, set the update scope of the risk entity based on the updated data each time the relationship is established.

[0068] The shortest connection path of the update range of the risk entity at each association is set as the risk path, and the differential path of the risk path at each update is set as the risk evolution path. The risk level iterative update is completed with the risk evolution path.

[0069] Preferably, when setting up the risk event network, the relative risk status of each risk point is used as the weight of the edge, and the risk point load capacity of each risk point is used as the value of the risk point. The risk points with associated relationships are connected to form a risk event network.

[0070] For example, in the scenario of heavy rain → drainage system failure → waterlogging, the areas with waterlogging will be regarded as risk entities, and then it will be explained whether these risk entities are associated in the scenario of waterlogging. If there is an association, these risk entities will be organized into a risk event network in a corresponding manner. Then, the data range updated each time the association is determined, such as the area within 3 kilometers affected by waterlogging risk to the area within 4 kilometers affected by waterlogging risk. The risk entities in the extra part after the update will be marked as the update range of the risk entity. Then, after finding the shortest connection path when the risk entities within this update range are associated, the difference between these paths after the risk entity is updated will be compared to explain how it evolves under a risk event, so as to facilitate the subsequent iterative update of the content of its regional risk classification, so as to realize the dynamic capture of the risk evolution path and complete the accurate perception and early warning from local risk points to the global risk situation.

[0071] Assist subsequent staff to make decisions on current urban safety risks based on multiple probability values such as the corresponding output risk evolution path and the corresponding risk point load capacity, so as to improve the setting and association of various risks.

[0072] Ultimately, the processing sequence is achieved: regional risk sampling and planning → regional load capacity classification and verification → geographic space risk radius analysis → dynamic update of risk logic relationships, so as to complete the classification of urban safety risks and the real-time update of urban risk classification data in each region.

[0073] Afterwards, when completing the iterative update of the risk level based on the risk evolution path, the iterative update of the risk level is mainly completed based on the relative value and weight change rate of the risk entity corresponding to the risk evolution path.

[0074] For example, the path weight change rate of each risk entity on the risk evolution path is obtained, and the risk level of each risk entity is updated in combination with the relative risk status before the update.

[0075] At this point, a sensitivity coefficient is introduced. The sensitivity coefficient can be set to 0.1 or other values. The sensitivity coefficient is multiplied by the path weight change rate and then added to the relative risk state corresponding to the risk entity before the update to obtain the updated risk level. Alternatively, the risk entity on the risk evolution path can be introduced into the regional risk distribution map to obtain the re-divided classification areas of multiple regions before and after the risk entity is added, and this classification area is used as the content of the iterative update.

[0076] The above-mentioned path weight change rate represents the rate of change of the sum of the weights of each risk point edge in the risk event network on the corresponding risk evolution path, which is used to describe whether a larger risk range and more serious risk situations will arise as the data is updated.

[0077] Preferably, the logical transmission relationship of each risk point indicates whether there is an association between the risk entities represented by each risk point. Only risk entities with associations can be combined into a risk event network. At this time, the association rules of the risk entities will be set in advance in the database to facilitate the subsequent establishment of the parts of each sampling area that require risk warnings. These iteratively updated parts will be used for subsequent alarm decisions to complete the hierarchical processing of urban safety risks.

[0078] Although the embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and are not to be construed as limitations on the present invention. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention, which are still covered by the scope of protection of the present invention.

Claims

1. A city safety risk classification assessment and early warning system, characterized by: include: The risk sampling module is used to sample data on urban safety risks, list risk data within the sampling area, and describe the risk types within the sampling area with risk data; The regional division module is used to classify the regions according to the risk type and regional risk load capacity of each sampling area and determine the regional risk distribution map of each sampling area; The risk load module is used to extract risk points from the regional risk distribution map, quantitatively evaluate the regional risk load capacity of each sampling area based on the data proportion of each risk point in the regional risk distribution map, and generate the regional risk load probability; The risk progression module is used to identify the risk radius of each risk point in the sampling area, set the risk point load capacity of each risk point based on the risk type and regional risk load probability within the risk radius, and extract the progressive probability of the risk point load capacity to obtain the relative risk status of each sampling area; The risk update module is used to construct a risk event network to analyze the logical transmission relationship of each risk point based on the relative risk status of each sampling area, identify the risk entities and the update scope of risk entities under each sampling area, and iteratively update the risk level of each sampling area in combination with the risk evolution path of the risk event network.

2. The city safety risk grading assessment and early warning system according to claim 1 is characterized in that: The implementation of the risk sampling module also includes: Specify each sampling area, obtain the sampling points of risk data in each sampling area, and list the risk data in the sampling area based on the risk types of multiple sampling points; Based on the gradient of each risk type, the frequency of occurrence, scope of impact, losses caused, and geographical location of the risk type in the sampling area are characterized, and risk labels corresponding to the risk types are set; Determine whether the risk label matches the current sampling area. If so, calculate the probability of the current risk label appearing at each sampling point based on the risk type; if not, mark the risk label as a no-risk event; After adding risk tags to risk types, the corresponding risk types will be output.

3. The city safety risk grading assessment and early warning system according to claim 1 is characterized in that: The implementation methods of the region division module include: Using the regional risk load capacity of each sampling area, determine whether the basic risk probability when the current risk type occurs is greater than the index value of the regional risk load capacity; if it is greater, the difference between the basic risk probability when the current risk type last occurred and the index value of the regional risk load capacity is used as the basic risk probability of the current risk type; If it is less than, the risk excess probability is set based on the upper limit of the difference between the basic risk probability in the current risk type and the indicator value of the risk load capacity of the current region; According to the risk excess probability, the incremental probability difference between the current risk type and the regional risk load capacity in multiple time intervals is identified, and the incremental probability difference is used as the probability interval for regional classification; A mapping relationship is established between the probability interval of regional classification and the sampling area, the area corresponding to the value of each probability interval is regarded as the classification area, and the positions of each classification area are combined into a regional risk distribution map.

4. The city safety risk grading assessment and early warning system according to claim 3 is characterized in that: The implementation method of performing regional classification based on the risk type and regional risk load capacity of each sampling area and determining the regional risk distribution map of each sampling area also includes: Load the mapping relationship between risk type and sampling area, and calculate the number of levels and the size of the graded area when grading the area; According to the data distribution of each graded area during regional classification, the distance between the center points of each graded area is used to cluster the data; The difference in the number of grades of the corresponding graded areas before and after clustering is recorded, and the difference in the number of grades is output as a remark label of its regional risk distribution map.

5. The city safety risk grading assessment and early warning system according to claim 4 is characterized in that: The number of levels when calculating regional levels also includes: Load the data of each grading area, obtain the area occupied by each grading area in the sampling area, take the grading area with the largest area as the starting point, obtain the secondary area of the grading area, and set the secondary area according to the preset ratio value. The secondary area is continuously divided according to the preset ratio value until there is no corresponding grading area in the divided interval. The number of divisions is regarded as the number of levels when the current area is graded.

6. The city safety risk grading assessment and early warning system according to claim 4 is characterized in that: Clustering data using the distance between the center points of each classification area also includes: Cluster the nearest grading areas to the center point of any grading area until the average value of the distance between the center points of each grading area in the multiple areas composed of the grading areas is equal, and use the multiple clustered areas as the output regional risk distribution map.

7. The city safety risk grading assessment and early warning system according to claim 1 is characterized in that: That is, the implementation of the risk load module also includes: Extract labels from the regional risk distribution map and set the combined labels for each risk point; combine the risk type and remark labels in each cluster area in the regional risk distribution map into the combined label of the current risk point; Determine the risk type of the corresponding risk point from the group label, determine the type proportion corresponding to each risk point based on the risk type of each risk point, and describe the regional risk load probability of the corresponding risk point based on the type proportion and regional risk load capacity.

8. The city safety risk grading assessment and early warning system according to claim 1 is characterized in that: The implementation methods of the risk progression module include: The risk radius of each risk point is set based on the minimum inscribed circle of multiple areas in the regional risk distribution map. The regional risk load probability of each risk point is updated using the Bayesian theorem based on the risk type within the risk radius and the corresponding regional risk load probability. The risk point load capacity of each risk point is set to determine whether the risk radius of each risk point overlaps. If so, the risk points corresponding to the overlapping risk radius are identified, and the difference in risk point load capacity between the corresponding risk points is calculated as the progressive probability of the current risk point. The attenuation coefficient of the progressive probability is used as the relative risk status output of each sampling area. If they do not overlap, the difference in risk point load capacity between the two risk points adjacent to the current risk point is used as the progressive probability of the current risk point, and the attenuation coefficient of the progressive probability is used as the relative risk status output of each sampling area.

9. The city safety risk grading assessment and early warning system according to claim 1 is characterized in that: The implementation of the risk update module includes: Based on the relative risk status, the risk entities associated with each risk point are combined to set up a risk event network; Determine whether there is a relationship between the risk entities in the risk event network. If there is a relationship, set the update scope of the risk entity based on the updated data of each relationship. The shortest connection path of the update range of the risk entity at each association is set as the risk path, and the differential path of the risk path at each update is set as the risk evolution path. The risk level iterative update is completed with the risk evolution path.

10. The city safety risk grading assessment and early warning system according to claim 9 is characterized in that: The implementation methods for iteratively updating risk levels based on the risk evolution path include: Obtain the path weight change rate of each risk entity on the risk evolution path, and update the risk level of each risk entity based on the relative risk status before the update.

Images