A method and device for early warning of a hazard source of a transportation system

Abstract

The application relates to a kind of early warning method and device of transport system hazard source. Including: obtaining the hazard source of transport system and the spatial coordinate point of each hazard source and current running state data;According to the individual risk information of each hazard source according to the current running state data of each hazard source;According to the spatial coordinate point of each hazard source, corresponding warning mark is generated at corresponding spatial coordinate point in three-dimensional digital safety map;According to the individual risk information of each hazard source, determine the risk aggregation area and the comprehensive risk information of risk aggregation area;According to the comprehensive risk information of risk aggregation area, and the warning mark of each hazard source in three-dimensional digital safety map covered by risk aggregation area, generate early warning information for risk aggregation area.The application solves the problem that only single object can output independent early warning, and cannot reflect the complex risk evolution trend of aggregation area.

Description

Technical Field

[0001] This application relates to the field of safety monitoring technology for transportation systems, and in particular to a method and device for early warning of hazardous sources in transportation systems. Background Technology

[0002] With the rapid development of the transportation industry, the scale of transportation systems is constantly expanding, and the number of major hazard sources involved in their operation has increased significantly. During the actual operation of the transportation system, the status data of various hazard sources are uploaded to the monitoring platform in real time through data acquisition devices such as IoT sensors and GPS, forming massive amounts of multi-source heterogeneous monitoring data.

[0003] Currently, safety monitoring in transportation systems typically involves presenting various collected monitoring data in numerical or simplified chart form on a monitoring interface. Monitoring personnel then manually interpret and analyze the data based on their experience, combining this with preset static risk standards to conduct independent risk assessments and early warnings for each monitored object within the transportation system. When a data indicator for a monitored object exceeds a preset static threshold, the system triggers an early warning signal for that single object.

[0004] However, when faced with the complex and ever-changing severe weather conditions encountered during the actual operation of transportation systems, the aforementioned risk assessment methods struggle to help monitoring personnel identify changes in the risk status of hazards from massive amounts of dynamic data in a timely and accurate manner. Furthermore, because multiple hazards in transportation systems often exhibit spatial clustering characteristics, the evolution of these hazards within spatial clusters is complex, resulting in one-dimensional and inaccurate early warning information output by the system. Consequently, subsequent early warning responses and resource scheduling lack effective and comprehensive data support. Summary of the Invention

[0005] Therefore, it is necessary to provide a method for early warning of hazardous sources in transportation systems that can provide effective and comprehensive risk warning for spatially concentrated areas, addressing the aforementioned technical problems.

[0006] Firstly, this application provides a method for early warning of hazards in a transportation system, including:

[0007] Acquire the hazardous sources in the transportation system, as well as the spatial coordinates and current operating status data of each hazardous source;

[0008] Based on the current operating status data of each of the aforementioned hazards, risk assessments are performed on each of the aforementioned hazards from multiple preset assessment dimensions to obtain individual risk information for each of the aforementioned hazards.

[0009] Based on the spatial coordinates of each hazard source, each hazard source is mapped to a corresponding spatial coordinate point in the three-dimensional digital safety map, and a corresponding warning marker is generated at the corresponding spatial coordinate point in the three-dimensional digital safety map according to the individual risk information of each hazard source; the three-dimensional digital safety map is pre-constructed based on the geographic information data of the area where the transportation system is located;

[0010] Based on the individual risk information of each of the aforementioned hazards, the risk clustering areas covering multiple hazards and the comprehensive risk information of the risk clustering areas are determined in the three-dimensional digital safety map.

[0011] Based on the comprehensive risk information of the risk cluster area and the warning markers of each hazard source covered by the risk cluster area in the three-dimensional digital safety map, warning information is generated for the risk cluster area. The warning information is used to visually mark the risk cluster area in the three-dimensional digital safety map for display on the terminal corresponding to the transportation system.

[0012] Secondly, this application also provides an early warning device for hazardous sources in a transportation system, comprising:

[0013] The acquisition module is used to acquire the hazard sources of the transportation system and the spatial coordinates and current operating status data of each hazard source.

[0014] The assessment module is used to assess the risk of each hazard source from multiple preset assessment dimensions based on the current operating status data of each hazard source, and obtain the individual risk information of each hazard source.

[0015] The mapping module is used to map each of the hazards to a corresponding spatial coordinate point in the three-dimensional digital safety map based on the spatial coordinate points of each hazard, and to generate a corresponding warning marker at the corresponding spatial coordinate point in the three-dimensional digital safety map according to the individual risk information of each hazard; the three-dimensional digital safety map is pre-constructed based on the geographic information data of the area where the transportation system is located;

[0016] The determination module is used to determine the risk cluster area covering multiple hazard sources and the comprehensive risk information of the risk cluster area in the three-dimensional digital safety map based on the individual risk information of each hazard source.

[0017] The generation module is used to generate early warning information for the risk cluster area based on the comprehensive risk information of the risk cluster area and the early warning marks of each hazard source covered by the risk cluster area in the three-dimensional digital safety map. The early warning information is used to visually mark the risk cluster area in the three-dimensional digital safety map for display on the terminal corresponding to the transportation system.

[0018] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps described in the first aspect.

[0019] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps described in the first aspect.

[0020] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps described in the first aspect.

[0021] The aforementioned method, device, computer equipment, computer-readable storage medium, and computer program product for early warning of hazards in a transportation system, on the one hand, automatically acquires operational status data and conducts risk assessment based on a multi-dimensional model. The entire process eliminates the need for monitoring personnel to manually interpret massive amounts of data under adverse weather conditions, avoiding problems such as limited perception, interpretation delays, and biases caused by severe weather. This ensures accurate identification of the individual risk status of each hazard under various complex weather conditions. On the other hand, by spatially mapping and marking hazards in a three-dimensional digital safety map, and further performing risk correlation and comprehensive aggregation analysis on multiple hazards within a spatially clustered area at the data processing level, it generates early warning information covering the overall risk situation of the clustered area. This solves the problem of only being able to output independent early warnings for a single object and failing to reflect the complex risk evolution of the clustered area, providing accurate and comprehensive data support for early warning response and resource scheduling. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is an application environment diagram of a hazard warning method for a transportation system in one embodiment;

[0024] Figure 2 This is a flowchart illustrating a method for early warning of hazards in a transportation system, as shown in one embodiment.

[0025] Figure 3 This is a schematic diagram of the early warning tag generation process based on individual risk level and individual occurrence probability in one embodiment;

[0026] Figure 4 This is a schematic diagram of the overall process of an early warning method for hazardous sources in a transportation system in one embodiment;

[0027] Figure 5 This is a structural block diagram of a hazard warning device for a transportation system in one embodiment;

[0028] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0029] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0030] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0031] This application provides an embodiment of a method for early warning of hazardous sources in a transportation system, which can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on another network server. Terminal 102 is used to collect the spatial coordinates and current operating status data of each hazard source in the transportation system in real time, and upload the collected data to server 104 via the network. Server 104 then performs risk assessment on each hazard source from multiple preset evaluation dimensions based on the received current operating status data of each hazard source, obtains individual risk information of each hazard source, maps the spatial coordinates of each hazard source to the corresponding spatial coordinates in a pre-constructed three-dimensional digital safety map, and generates corresponding warning markers according to the individual risk information. Furthermore, server 104 also determines the risk cluster area covering multiple hazard sources in the three-dimensional digital safety map and the comprehensive risk information of the area based on the individual risk information of each hazard source, and generates warning information for the risk cluster area based on the comprehensive risk information and the warning markers of each hazard source in the area. The three-dimensional digital safety map data containing the warning information is sent to terminal 102 for visualization. At the same time, server 104 can also match the corresponding risk control plan according to the individual risk information of each hazard source and send it to terminal 102 to assist transportation system managers in early warning response and resource scheduling. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection equipment. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0032] In one exemplary embodiment, such as Figure 2 As shown, a method for early warning of hazards in a transportation system is provided, which can be applied to... Figure 1 Taking the server in the example, the following steps 201 to 205 are used as an example:

[0033] Step 201: Obtain the hazard sources of the transportation system and their respective spatial coordinates and current operating status data.

[0034] In practical applications, transportation systems encompass various modes of transport, including road, rail, water, air, and pipeline transport. Correspondingly, hazards may involve different types of risk entities. For ease of understanding, the following explanations of relevant concepts will be provided from multiple perspectives, considering various transportation scenarios.

[0035] A hazard source refers to a potential source or carrier of safety risks that may occur during the operation of a transportation system. From the perspective of risk sources, hazard sources can be mobile transportation equipment such as vehicles, trains, ships, and aircraft (e.g., hazardous materials transport vehicles, tankers, passenger trains, etc.), critical infrastructure along transportation routes (e.g., tunnels, bridges, interchanges, rail transit stations, ports, airport runways, etc.), operational behaviors during transportation processes (e.g., loading and unloading operations, overtaking and lane changes, ship berthing, etc.), or external environmental factors (e.g., severe weather conditions such as heavy fog, heavy rain, snow, and strong winds). From a physical perspective, hazard sources can be point-like hazards with a clear spatial location, such as fixed monitoring stations and bridges, or linear hazards with a spatial trajectory, such as moving transport vehicles or specific sections of transportation routes.

[0036] Spatial coordinates are used to uniquely pinpoint the location of a hazard in three-dimensional space. For a fixed, point-like hazard, the spatial coordinates can be the latitude, longitude, and altitude of the facility's center point; for a mobile hazard, the spatial coordinates can be the real-time vehicle positioning coordinates; for a linear hazard, the spatial coordinates can be the starting and ending coordinates of the route section, or the coordinates of the center point of the section and its extending direction vector. In some scenarios, spatial coordinates may also include the hazard's attitude information to more accurately reflect its spatial orientation.

[0037] Current operational status data refers to the dynamic operational parameters of a hazard source at the current moment or within the current time window. The specific content of the current operational status data varies depending on the type of hazard source. For example, for hazard sources such as transport vehicles, current operational status data may include, but is not limited to, vehicle speed, acceleration, engine speed, braking status, tire pressure, load, and cargo type; for infrastructure hazard sources such as tunnels / bridges, current operational status data may include, but is not limited to, structural vibration frequency, stress-strain data, crack width, and water leakage monitoring data; for hazard sources related to severe weather, current operational status data may include, but is not limited to, meteorological parameters such as visibility, wind speed and direction, and precipitation. The server can acquire the above operational status data from various sensors, monitoring equipment, positioning terminals, and external meteorological data platforms via wired or wireless communication.

[0038] Step 202: Based on the current operating status data of each hazard source, conduct risk assessments on each hazard source from multiple preset assessment dimensions to obtain individual risk information for each hazard source.

[0039] Assessment dimensions refer to the different risk factor categories used in quantifying the risk of a hazard. The selection and number of assessment dimensions can be set according to the actual characteristics of the transportation system and safety management needs. For example, for hazard sources related to transport vehicles, multiple preset assessment dimensions may include at least two of the following: driving status dimension, driver status dimension, and environmental adaptability dimension. For infrastructure hazard sources, multiple preset assessment dimensions may include, but are not limited to: structural health dimension, equipment operation dimension, environmental load dimension, and usage load dimension. Each assessment dimension can be configured with corresponding scoring rules or scoring models to conduct a comprehensive multi-dimensional assessment of the hazard.

[0040] Individual risk information is comprehensive information used to describe the risk level of a single hazard, and may include indicators such as individual risk level and individual risk occurrence probability. Individual risk level characterizes the current severity of the risk hazard, for example, it can be divided into four levels: Level I (low risk), Level II (moderate risk), Level III (significant risk), and Level IV (major risk). Individual risk occurrence probability characterizes the likelihood of the hazard causing a safety accident under its current state, and can be expressed using a probability value (such as a number between 0 and 1) or a probability level (such as extremely low, low, medium, high, and extremely high).

[0041] Step 203: Based on the spatial coordinates of each hazard source, map each hazard source to the corresponding spatial coordinates in the 3D digital safety map, and generate corresponding warning markers at the corresponding spatial coordinates in the 3D digital safety map according to the individual risk information of each hazard source; the 3D digital safety map is pre-constructed based on the geographic information data of the area where the transportation system is located.

[0042] A 3D digital safety map is a 3D virtual map environment built upon real geographic information data, used to visualize the spatial information and risk situation of a transportation system and its surrounding geographic environment. Specifically, a 3D digital safety map can be pre-constructed as follows: acquiring multi-source geographic information data such as digital elevation model data, high-resolution remote sensing image data, road vector data, building vector data, and underground pipeline data for the area where the transportation system is located; performing preprocessing on the above data, including coordinate unification, format conversion, and accuracy registration; and using a 3D map engine or geographic information system platform to perform 3D modeling and visualization rendering of the preprocessed geographic information data, generating a 2.5-dimensional or 3D digital map containing complete spatial information such as topography, road networks, roadside facilities, and environmental elements. In the 3D digital safety map, each spatial coordinate point has unique latitude and longitude coordinates and altitude, corresponding one-to-one with its location in real geographic space.

[0043] Hazards are mapped to corresponding spatial coordinates on a 3D digital safety map. This means that based on the hazard's spatial coordinates, the map locates and positions the hazard at the same coordinates, achieving precise anchoring of the hazard in the virtual map space. For moving hazard sources, the server can dynamically update their mapped position on the 3D digital safety map based on real-time changes in their spatial coordinates, enabling real-time tracking and display of moving hazard sources.

[0044] Warning markers are graphical elements used in 3D digital safety maps to visualize the risk status of hazard sources. For example, warning markers can be presented at corresponding coordinate locations on the 3D digital safety map in the form of marker points, marker bars, marker spheres, marker icons, etc.

[0045] Step 204: Based on the individual risk information of each hazard source, determine the risk cluster area covering multiple hazard sources and the comprehensive risk information of the risk cluster area in the three-dimensional digital safety map.

[0046] A risk cluster area refers to a geographical region within the spatial scope of a 3D digital safety map where hazards are densely distributed and their risk impact ranges overlap or intersect. Risk cluster areas reflect the concentrated spatial distribution of multiple hazards and the potential for cumulative risk effects. Comprehensive risk information is a comprehensive indicator used to describe the overall risk level of a risk cluster area, and may include a comprehensive risk level and a comprehensive risk occurrence probability. The comprehensive risk level characterizes the overall severity of the risk in the risk cluster area, while the comprehensive risk occurrence probability characterizes the likelihood of a safety accident or cascading accident occurring in the risk cluster area.

[0047] Step 205: Based on the comprehensive risk information of the risk cluster area and the warning markers of each hazard source covered by the risk cluster area in the three-dimensional digital safety map, generate warning information for the risk cluster area. The warning information is used to visually mark the risk cluster area in the three-dimensional digital safety map for display on the corresponding terminal of the transportation system.

[0048] Warning information is a data instruction used to visually mark risk-concentrated areas on a 3D digital safety map. It may include information such as area fill style, boundary line style, and the rules for the coordinated display of warning markers for various hazards within the area. Terminals can be devices with display capabilities, such as large-screen displays in transportation safety management centers or computer terminals in dispatch command centers. After generating warning information, the server sends it to the terminal via wired or wireless network. Upon receiving the information, the terminal renders and displays the visual markers at the corresponding locations on the 3D digital safety map, allowing managers to intuitively view the risk situation.

[0049] On the one hand, by automatically acquiring operational status data and conducting risk assessments based on multi-dimensional models, the entire process eliminates the need for monitoring personnel to manually interpret massive amounts of data under adverse weather conditions. This avoids problems such as limited perception, interpretation delays, and biases caused by severe weather, ensuring accurate identification of the individual risk status of each hazard source under various complex weather conditions. On the other hand, by spatially mapping and marking hazard sources in a three-dimensional digital safety map, and further performing risk correlation and comprehensive aggregation analysis on multiple hazard sources within a spatial cluster area at the data processing level, early warning information covering the overall risk situation of the cluster area is generated. This solves the problem that traditional technologies can only output independent early warnings for a single object and cannot reflect the complex risk evolution of the cluster area, providing accurate and comprehensive data support for early warning response and resource scheduling.

[0050] In one optional embodiment, based on the current operational status data of each hazard source, risk assessments are performed on each hazard source from multiple preset assessment dimensions to obtain individual risk information for each hazard source. This includes: for each hazard source, extracting feature data corresponding to multiple preset assessment dimensions from its current operational status data; weighting and fusing the feature data corresponding to each assessment dimension according to their respective weight coefficients to obtain the current risk score of the hazard source; acquiring historical operational status data for the hazard source at multiple historical moments, and calculating the risk score for each historical moment based on the historical operational status data at each historical moment. Each hazard source is assigned a corresponding historical risk score. Based on a preset number of levels, multiple risk level intervals are divided, centered on the risk benchmark value and using risk fluctuation range as the scale unit. Different risk level intervals correspond to different levels. The level corresponding to the risk level interval into which the current risk score of the hazard source falls is determined as the individual risk level of the hazard source. The probability of individual risk occurrence of the hazard source is determined based on the degree of deviation between the current risk score and the risk benchmark value. The degree of deviation is positively correlated with the probability of risk occurrence. Based on the individual risk level and individual risk occurrence probability of each hazard source, the individual risk information of each hazard source is determined.

[0051] In practical applications, the current operational status data of a hazard source typically includes raw parameters across multiple dimensions, such as vehicle speed, engine speed, braking status, load, cargo pressure, and ambient temperature. To accurately assess risk, feature data matching each preset assessment dimension is selectively extracted from this raw data and used as input for subsequent quantitative assessment.

[0052] Assessment dimensions refer to the different risk factor categories used in quantifying the risk of a hazard. The number and selection of assessment dimensions can be set according to the specific type of transportation system and safety management needs. Feature data refers to the quantitative indicators extracted from the current operating status data that are directly related to the above assessment dimensions. For example, for the driving safety dimension, the server can extract the current vehicle speed and the number of rapid accelerations / decelerations in the last 5 minutes as feature data from the current operating status data; for the loading safety dimension, it can extract the ratio of the current load value to the vehicle's rated load and the percentage difference between the current tank pressure and the safety threshold as feature data; for the driver status dimension, it can extract the duration of continuous driving, the frequency of blinking during driving, or the frequency of steering wheel corrections as feature data; for the environmental adaptability dimension, it can extract the current road visibility value, road surface temperature, and friction coefficient as feature data. After obtaining the raw operating status data, the server extracts the corresponding feature data items from the raw data according to the preset data mapping rules for each assessment dimension, and stores the feature data of each dimension of the same hazard source in association for subsequent processing.

[0053] Weighting coefficients characterize the importance of each assessment dimension in the overall risk assessment. The magnitude of these weighting coefficients can be predetermined based on historical accident statistics and expert experience. For example, for vehicles transporting hazardous chemicals, the weight for the loading safety dimension can be set to a high value, such as 0.35; the weight for the driving safety dimension can be set to 0.30; the weight for the driver's condition dimension can be set to 0.25; and the weight for the environmental adaptability dimension can be set to 0.10, with the sum of all weights equal to 1. It is understandable that the weighting configurations for each dimension can differ under different transportation scenarios, and the weighting coefficients can be dynamically adjusted and optimized based on statistical analysis results from actual applications.

[0054] In one possible implementation, the server first normalizes the extracted feature data corresponding to each evaluation dimension, mapping each feature data to a unified unit of measurement. Specifically, for positive indicators (higher feature values ​​indicate greater risk, such as vehicle speed deviation), linear interpolation can be used to map the feature values ​​to a score; for negative indicators (higher feature values ​​indicate lower risk), inverse linear interpolation can be used. The maximum and minimum reference values ​​for each feature data can be determined based on industry safety standards or historical data statistical distributions. Then, the server multiplies the normalized score values ​​for each dimension by their corresponding weight coefficients, and sums the weighted results for each dimension to obtain the current risk score for the hazard. For example, suppose a hazardous materials transport vehicle has a normalized score of 80 for driving safety, 90 for loading safety, 60 for driver condition, and 70 for environmental adaptability, with weights of 0.30, 0.35, 0.25, and 0.10 respectively. Then, the vehicle's current risk score is calculated as follows: 80 × 0.30 + 90 × 0.35 + 60 × 0.25 + 70 × 0.10 = 78.5 points. A higher current risk score indicates a higher overall risk level for the hazard.

[0055] To accurately assess the current risk status, the current risk level of the hazard source is compared and analyzed with its historical risk levels to determine the degree of abnormality in the current state. For this purpose, the server acquires historical operational status data of the hazard source at multiple historical moments. A historical moment refers to multiple sampling time points prior to the current moment, such as the moment corresponding to the 1st, 2nd, ..., Nth sampling period prior to the current moment. The server reads the historical operational status data corresponding to each historical moment from the stored historical data. For each historical moment, the same method as described above is used to extract the feature data corresponding to each assessment dimension from the historical operational status data of that historical moment, and the same weighting coefficients are used to weight and fuse the feature data of each dimension to calculate the historical risk score corresponding to that historical moment. Through the above method, the server can obtain a set of historical risk score sequences, such as [score at time tn, score at time t-(n-1), ..., score at time t-1], where n is the number of selected historical moments. The number of historical moments can be set according to actual needs to construct a historical risk score sample set reflecting the long-term operational status fluctuation pattern of the hazard source.

[0056] A risk benchmark is a statistical measure that reflects the central trend of the historical risk level of a hazard. In one implementation, the risk benchmark can be the average of all historical risk scores. In another implementation, the risk benchmark can be the median of all historical risk scores to reduce the impact of extreme values ​​on the benchmark. The specific method used can be selected based on the data distribution characteristics of the historical risk scores; for example, when the historical score data shows a significant skewed distribution, the median is preferred as the risk benchmark.

[0057] Risk volatility is a statistical measure reflecting the dispersion of historical risk scores for a hazard. In one implementation, risk volatility can be the standard deviation of each historical risk score. The larger the standard deviation, the more volatile the historical risk level of the hazard; the smaller the standard deviation, the more stable the historical risk level.

[0058] The number of risk levels refers to the pre-defined number of risk levels. In this embodiment, the risk levels can be divided into four levels according to safety management needs: Level I (low risk), Level II (moderate risk), Level III (significant risk), and Level IV (major risk). However, the present invention is not limited to this; in other application scenarios, it can also be divided into three or five levels. The following explanation uses a four-level division as an example.

[0059] In specific segmentation, the server uses the risk benchmark value as the center point and the risk fluctuation range as the basic unit of measurement to divide the numerical axis into multiple continuous intervals. For example, assuming the risk benchmark value is μ and the risk fluctuation range is σ, the numerical axis can be divided into the following four intervals: intervals less than μ-σ correspond to Level I (low risk); intervals greater than or equal to μ-σ and less than μ correspond to Level II (moderate risk); intervals greater than or equal to μ and less than μ+σ correspond to Level III (significant risk); and intervals greater than or equal to μ+σ correspond to Level IV (major risk). It should be noted that the above interval division method is only an example, and the specific division can be determined according to actual security management requirements.

[0060] After dividing the risk level into multiple intervals, the server compares the current risk score of the hazard with the boundary values ​​of each interval to determine which interval the current risk score falls into. The risk level corresponding to that interval is then determined as the individual risk level of the hazard. For example, assuming a hazard's historical risk score has a mean of 70 and a standard deviation of 10, and the current risk score is 85, then this score falls within the interval μ to μ+σ (i.e., outside the 70-80 range; in fact, 85 is greater than μ+σ=80, falling into the interval greater than μ+σ), corresponding to Level IV (significant risk). If the current risk score is 75, then it falls within the interval μ to μ+σ, corresponding to Level III (relatively high risk).

[0061] Deviation degree is used to characterize the extent to which the current risk score deviates from a historical benchmark. In one implementation, deviation degree can be quantified as the ratio of the difference between the current risk score and the risk benchmark to the risk volatility, i.e., Deviation degree D = (Current risk score - Risk benchmark) / Risk volatility. The larger the D value, the greater the deviation of the current risk status from the historical average level, and the more abnormal the risk status. A positive D value indicates that the current risk is higher than the historical average level, while a negative D value indicates that the current risk is lower than the historical average level.

[0062] The probability of an individual risk occurring refers to the likelihood that a hazard will cause a safety accident under the current state. After calculating the degree of deviation, the server maps it to the probability of risk occurrence. Since the degree of deviation is positively correlated with the probability of risk occurrence—that is, the greater the deviation, the further the current operating state deviates from the normal fluctuation range, the lower the safety margin, and the higher the probability of a safety accident—the server can use a preset mapping function to convert the degree of deviation into a probability value.

[0063] For each hazard, the server associates and combines the probability of individual risks occurring to form the individual risk information for that hazard.

[0064] The beneficial effect of this embodiment is that by independently calculating the risk benchmark value and risk fluctuation range based on its own historical dataset for each hazard source, and dynamically dividing the risk level range accordingly, the risk assessment standard can adaptively reflect the individual operating characteristics and fluctuation patterns of different hazard sources. This effectively avoids the systematic misjudgment or omission caused by differences in different hazard source types, working conditions or environments when using a global fixed threshold for level classification, thereby improving the accuracy and personalization of individual risk assessment.

[0065] In one optional embodiment, based on the individual risk information of each hazard source, the risk clustering area covering multiple hazard sources and the comprehensive risk information of the risk clustering area in the three-dimensional digital safety map are determined, including: determining the risk influence radius of each hazard source based on its individual risk level; generating a risk intensity distribution for each hazard source centered on its spatial coordinate point and with its corresponding risk influence radius; the risk intensity distribution representing the risk intensity value of the hazard source at different spatial coordinate points; projecting the risk intensity distribution of each hazard source onto the three-dimensional digital safety map, and processing the risk intensity value at each spatial coordinate point on the three-dimensional digital safety map. The comprehensive risk intensity value at each spatial coordinate point on the 3D digital safety map is obtained by summing the values. Based on the comprehensive risk intensity value at each spatial coordinate point on the 3D digital safety map, spatial areas with a comprehensive risk intensity value greater than a preset clustering threshold and covering at least two hazard sources are identified as risk clustering areas. Based on the individual risk occurrence probability of each hazard source within the risk clustering area, the comprehensive risk occurrence probability of the risk clustering area is determined, and based on the comprehensive risk intensity value at each spatial coordinate point within the risk clustering area, the comprehensive risk level of the risk clustering area is determined. Based on the comprehensive risk level and comprehensive risk occurrence probability of the risk clustering area, the comprehensive risk information of the risk clustering area is determined.

[0066] In practical applications, the impact range and severity of hazards on the surrounding area vary significantly depending on the risk level of the hazard. Hazards with higher risk levels typically have a wider impact range once an accident occurs, thus requiring a larger risk impact radius; while hazard sources with lower risk levels have a relatively limited risk impact range.

[0067] The risk impact radius refers to the maximum spatial distance that the risk effect may extend from the hazard source. The value of the risk impact radius can be differentiated based on individual risk levels. For example, assuming risk levels are divided into four levels (Level I: low risk, Level II: moderate risk, Level III: significant risk, and Level IV: major risk), the server can determine the risk impact radius corresponding to each level according to a preset correspondence. For instance, Level I corresponds to an impact radius of 100 meters, Level II to 300 meters, Level III to 500 meters, and Level IV to 1000 meters. This correspondence can be pre-configured in the server's configuration file, and different impact radius bases can be configured for different transportation scenarios. Alternatively, the risk impact radius can also be calculated using a continuous function, where the individual risk level is quantified into a numerical value and then input into a preset function to calculate the corresponding impact radius, achieving a more refined radius value.

[0068] Risk intensity distribution refers to the risk intensity field centered on the hazard source, which decreases spatially with distance. Within the risk influence radius, the closer a location is to the hazard source, the stronger the risk influence; the farther away, the weaker the influence. Locations outside the risk influence radius have a risk intensity value of zero.

[0069] In one implementation, the risk intensity distribution can be generated using a distance attenuation model. Specifically, for any hazard source, the risk intensity value is set to its maximum value at the spatial coordinate point of the hazard source. As the distance from the center increases, the risk intensity value gradually decreases according to a preset attenuation function, reaching zero at the boundary of the risk influence radius. The attenuation function can be linear, i.e., risk intensity value = 1 - (d / R), where d is the spatial distance from the center of the hazard source, and R is the risk influence radius of the hazard source.

[0070] For example, assuming a hazard source has an individual risk level of III and a corresponding risk impact radius of 500 meters, the risk intensity value at the center of the hazard source is 1, the risk intensity value at 250 meters from the center is 1 - 250 / 500 = 0.5, and the risk intensity value at the boundary 500 meters from the center is 0. The server can generate a risk intensity function for each hazard source with the center of the hazard source as the origin and spatial location as the variable, or represent the risk intensity distribution in the form of raster data, dividing the space around the hazard source into several raster cells, with each raster cell storing the risk intensity value at that location.

[0071] After generating the risk intensity distribution for each hazard, the server maps these distributions to their corresponding spatial locations on the 3D digital safety map. Since each spatial coordinate point on the 3D digital safety map has a definite geographical location, the server calculates the risk intensity value for each spatial coordinate point within the risk intensity distribution range of each hazard. Points outside the influence range of any hazard have a risk intensity value of 0. Then, the risk intensity values ​​of all hazard sources at that spatial coordinate point are summed to obtain the overall risk intensity value for that point.

[0072] It should be noted that the shape of the risk intensity distribution can differ for different types of hazard sources. For example, for mobile hazard sources such as transport vehicles, due to the directional and motion characteristics of vehicles, the risk intensity distribution in the front area can be set to extend further, while the attenuation in the side and rear areas can be faster, forming an elliptical, non-uniform distribution. For fixed facility hazard sources, the risk intensity distribution can adopt a uniform circular distribution centered on the facility's center. The server can read the corresponding distribution shape parameters from the preset configuration based on the hazard source type identifier.

[0073] A preset clustering threshold is a pre-defined critical value for risk intensity, used to determine which spatial areas have reached a level of risk overlap that requires attention. The size of the clustering threshold can be set according to actual safety management needs. A higher clustering threshold means a higher threshold for identifying a risk cluster area, resulting in fewer identified areas and smaller areas; a lower threshold means more identified areas and larger areas. Covering at least two hazard sources is a necessary condition for determining a risk cluster area, meaning the risk cluster area contains either the center location of at least two hazard sources or the risk intensity distribution coverage area of ​​at least two hazard sources. The server can use a region growing algorithm or a contour tracing algorithm to determine the boundaries of risk cluster areas. Taking the region growing algorithm as an example: the server traverses every spatial coordinate point on the 3D digital safety map. If the comprehensive risk intensity value of a point is greater than the preset clustering threshold, that point is used as a seed point, and the server expands towards its adjacent spatial directions, grouping all adjacent points whose comprehensive risk intensity values ​​are greater than the clustering threshold into the same area, until expansion can no longer continue, forming a continuous spatial area. The server then determines whether the area covers at least two hazard sources; if the condition is met, the area is identified as a risk cluster area.

[0074] For each risk cluster area, the server will associate and combine the comprehensive risk level and the comprehensive risk occurrence probability to form the comprehensive risk information for that risk cluster area.

[0075] The beneficial effect of this embodiment is that by constructing the risk intensity distribution of each hazard source based on spatial distance and superimposing and accumulating it, the traditional single-point risk assessment is extended to a spatial continuous risk field assessment, realizing a full-coverage quantitative characterization of risk distribution within the transportation system area, and making up for the shortcomings of single-point risk assessment in reflecting regional cascading risks and spatial superposition effects.

[0076] Figure 3 This is a schematic diagram of the early warning tag generation process based on individual risk level and individual occurrence probability in one embodiment. Please refer to [link / reference]. Figure 3 In one optional embodiment, based on the individual risk information of each hazard source, a corresponding warning marker is generated at the corresponding spatial coordinate point in the three-dimensional digital safety map, including:

[0077] Step 301: Determine the corresponding marking color for each hazard source based on its individual risk level; different individual risk levels correspond to different marking colors.

[0078] In practical applications, color is one of the most intuitive visual channels in visualization. To enable managers to quickly identify the severity of different hazards on a map, risk levels are mapped to colors with clear visual distinction.

[0079] In a 3D digital safety map, color marking refers to the graphical colors used to represent the risk level of a hazard. The server pre-stores a mapping table between risk levels and colors. For example, assuming the risk levels are divided into four levels (Level I: low risk, Level II: moderate risk, Level III: significant risk, and Level IV: major risk), the corresponding color markings could be: Level I corresponds to green, indicating safe and controllable risk; Level II corresponds to yellow, indicating attention is needed and risk is moderate; Level III corresponds to orange, indicating high risk requiring close monitoring; and Level IV corresponds to red, indicating extremely high risk requiring immediate action. This color mapping follows the general convention of human visual perception, from cool to warm colors and from low to high alert, facilitating intuitive understanding by management personnel. It is understood that in other embodiments, other color systems such as blue, cyan, and purple can also be used for marking, as long as there is sufficient visual distinction between the colors corresponding to different levels.

[0080] Step 302: Determine the corresponding mark size for each hazard source based on the individual risk occurrence probability of each hazard source; wherein the mark size is positively correlated with the risk occurrence probability.

[0081] Size is another visual channel that intuitively reflects numerical magnitude. To simultaneously present information on both risk level and probability of occurrence on the map, the server determines the display size of the marker based on the probability of individual risks occurring. Marker size refers to the display size of the warning marker on the 3D digital safety map, and can be expressed in pixels, world units, or proportionally to the map zoom level. Marker size is positively correlated with the probability of risk occurrence; that is, the higher the probability of risk occurrence, the larger the display size of the marker; the lower the probability of risk occurrence, the smaller the display size of the marker. This mapping relationship is based on the understanding that a higher probability of risk occurrence indicates a greater likelihood of the hazard causing an accident, requiring a larger visual area to attract the attention of management personnel.

[0082] In one implementation, the server can determine the marker size using a linear mapping method. Specifically, the server presets a minimum and maximum marker size, and then calculates the corresponding marker size using linear interpolation based on the current risk occurrence probability's position within the 0-1 range. For example, assuming the minimum size is 5 pixels, the maximum size is 50 pixels, and the individual risk occurrence probability of a certain hazard source is 0.72, then the corresponding marker size = 5 + (50 - 5) × 0.72 = 37.4 pixels.

[0083] It should be noted that the specific size of the marker is related to the geometry of the warning marker. Those skilled in the art can select an appropriate marker format based on the display style of the 3D digital security map and actual needs.

[0084] Step 303: Based on the corresponding marker color and marker size of each hazard source, generate the corresponding warning marker at the corresponding spatial coordinate point in the three-dimensional digital safety map.

[0085] Based on the marker color and size of each hazard, the server generates warning markers with corresponding colors and sizes at the locations corresponding to the spatial coordinates of each hazard in the 3D digital safety map. Warning markers are graphical elements in the 3D digital safety map used to visually represent the risk status of hazard sources. Warning markers can take various geometric forms. In one implementation, the warning marker can be in the form of a 3D marker sphere. The server generates a 3D sphere centered on the spatial coordinates of the hazard source in the 3D digital safety map. The sphere's color is the marker color determined earlier, and its radius is the marker size determined earlier. The 3D sphere has good stereoscopic effect and visibility in the 3D map scene. Managers can observe the sphere's color and size from any perspective, thereby quickly obtaining information on the risk level and probability of occurrence of the hazard.

[0086] The beneficial effects of this embodiment are as follows: First, by encoding risk information in two dimensions—individual risk level and individual risk occurrence probability—through two independent visual channels, color and size, respectively, managers can simultaneously obtain the severity of the risk and the probability of its occurrence on the three-dimensional digital safety map through the visual attributes of the warning markers without having to click to view details or read specific values. This achieves efficient visual compression and rapid transmission of risk information, significantly improving the situational awareness speed and cognitive efficiency of managers when simultaneously monitoring a large number of hazard sources.

[0087] In one optional embodiment, early warning information for the risk cluster area is generated based on the comprehensive risk information of the risk cluster area and the early warning markers of each hazard source covered by the risk cluster area in the three-dimensional digital safety map. This includes: determining the fill color and fill transparency of the risk cluster area based on its comprehensive risk level; determining the boundary line type based on the comprehensive risk occurrence probability of the risk cluster area, and determining the boundary line width based on the marker size of the early warning markers corresponding to each hazard source covered by the risk cluster area; determining the boundary line color of the risk cluster area based on the marker color corresponding to the highest individual risk level among the early warning markers of each hazard source covered by the risk cluster area; filling and marking the risk cluster area in the three-dimensional digital safety map according to the fill color and fill transparency, and drawing the boundary line of the risk cluster area according to the boundary line type, boundary line width, and boundary line color to obtain the area early warning marker for the risk cluster area; and generating early warning information for the risk cluster area based on the area early warning marker.

[0088] Fill color refers to the color used to fill in areas within a risk cluster. Similar to the warning markers for individual hazard sources, the fill color for risk clusters is determined based on their overall risk level, with different fill colors corresponding to different overall risk levels. The logic for determining fill colors is consistent with the logic for determining the colors of individual hazard source markers, ensuring uniformity and consistency in the risk color coding system across the entire 3D digital safety map. Managers only need to memorize one set of color-risk mapping rules to understand the risk meaning of both dot markers and area markers.

[0089] Fill transparency refers to the degree of opacity of the fill color in high-risk cluster areas, expressed as a percentage or a value between 0 and 1. A fill transparency of 0 indicates complete transparency (invisible), while a fill transparency of 1 indicates complete opacity (solid fill). In one implementation, the higher the overall risk level, the lower the fill transparency can be set, meaning the fill is less transparent, making high-risk areas more prominent on the 3D digital safety map. This results in high-risk cluster areas being presented in a darker color on the map, enhancing the visual warning intensity. In another implementation, the opposite approach can be used: the higher the risk level, the higher the transparency, meaning the fill is more transparent, allowing the area boundary lines and warning markers for each hazard source within the area to be clearly visible through the fill layer, preventing the fill color from obscuring the underlying markers. The specific transparency strategy adopted can be flexibly set according to the display requirements of the 3D digital safety map and the actual application scenario.

[0090] Boundary line type refers to the style of the boundary line of a risk-concentrated area. For example, a solid line corresponds to a low overall risk probability, a closely spaced dashed line corresponds to a medium overall risk probability, a widely spaced dashed line or dotted line corresponds to a high overall risk probability, and a thick solid line with double lines or special warning lines corresponds to an extremely high overall risk probability. This mapping relationship allows the density of boundary line types to intuitively reflect the probability of risk occurrence; the more complex the line type and the larger the spacing, the higher the probability of risk. It should be noted that different line type mapping schemes can be used in different transportation scenarios, as long as the visual differences in line types can effectively distinguish different probability levels.

[0091] Boundary line width refers to the thickness of the line connecting the risk cluster area to the boundary, and can be expressed in pixels or map units. The server determines the boundary line width based on the size of the warning markers corresponding to each hazard source covered by the risk cluster area. In one implementation, the boundary line width can be the average size of all hazard source warning markers within the area, the maximum size of the warning markers within the area, or a weighted average of the warning marker sizes within the area. It can be understood that the size of the warning markers for each hazard source within the area reflects the individual probability of risk occurrence for that hazard source. The boundary line width is linked to the warning marker size, allowing the thickness of the boundary line to indirectly reflect the overall risk probability level of the hazard sources within the area, while also ensuring that the boundary line and the internal point markers maintain visual proportional harmony.

[0092] The server iterates through all hazard sources covered by the risk cluster area, obtains the color of each hazard source's warning marker, identifies the marker color corresponding to the highest individual risk level, and sets that color as the boundary color of the risk cluster area. The overall risk level of a risk cluster area is determined by the comprehensive risk intensity value of each spatial point within the area, but hazard sources with different individual risk levels may coexist within the area. Using the marker color corresponding to the highest individual risk level within the area reflects the severity of the risk at the most dangerous point in the cluster, allowing managers to quickly perceive the presence of high-risk hazard sources within the cluster area by observing the boundary color when rapidly browsing the map.

[0093] Filling refers to filling the space covered by a risk cluster area with a defined fill color and transparency. Specifically, the server generates a closed polygonal surface at the corresponding location on the 3D digital security map based on the set of spatial boundary coordinates of the risk cluster area, and applies fill color and transparency for rendering. The filled risk cluster area appears as a continuous colored block on the 3D digital security map, making it easy for managers to visually identify the spatial extent of the area.

[0094] A boundary line is a closed line drawn on the outer contour of a filled area. The server draws the boundary outline of the risk cluster area along the spatial boundary coordinate sequence, according to the boundary line type, width, and color. Once drawn, the risk cluster area has a complete visual representation with both internal fill and external boundary line, forming a regional early warning marker.

[0095] The server packages the generated regional warning markers into warning information for that risk-concentrated area. This warning information is then used to visually mark the risk-concentrated area on a 3D digital safety map for display on the corresponding terminals in the transportation system.

[0096] The beneficial effect of this embodiment is that by simultaneously generating fill markers and boundary line markers for risk cluster areas, and using fill color and fill transparency to represent the comprehensive risk level, boundary line type and boundary line width to represent the comprehensive risk occurrence probability, and boundary line color to represent the individual risk level of the highest hazard source in the area, it achieves efficient encoding and fusion presentation of multi-dimensional risk information of risk cluster areas in a limited visual space. Managers can simultaneously obtain three key information dimensions—comprehensive risk level, comprehensive risk occurrence probability, and the level of the highest risk point in the area—through a single area marker, thereby improving the efficiency of situational awareness and the speed of decision-making information acquisition.

[0097] In an optional embodiment, the method further includes: acquiring historical operational status data of each hazard source at multiple historical moments; fitting the operational status data change trend of each hazard source based on the historical operational status data of each hazard source at multiple historical moments; predicting the operational status data of each hazard source in a preset future time period based on the operational status data change trend of each hazard source, thereby obtaining the predicted operational status data of each hazard source; conducting risk assessments on each hazard source from multiple preset assessment dimensions based on the predicted operational status data of each hazard source, thereby obtaining the predicted risk information of each hazard source; and generating a predicted warning information for the hazard source when the predicted risk information of any hazard source reaches a preset warning condition.

[0098] Historical operational status data refers to the operational status parameters of a hazard source recorded at multiple historical points in time prior to the current moment. This data can originate from long-term accumulated sensor data, location data, equipment logs, and meteorological records in a server database. Corresponding to the current operational status data mentioned in step 202, historical operational status data forms the foundation for building trend prediction models.

[0099] The selection method and number of historical data points can be determined based on forecasting needs and data availability. For example, for short-term forecasts (such as predicting risk status within the next 5 minutes), historical data points at 10-second intervals within the past hour can be selected; for medium-term forecasts (such as predicting risk status within the next hour), historical data points at 5-minute intervals within the past 24 hours can be selected; and for long-term trend analysis (such as predicting risk status within the next 24 hours), historical data points at hourly intervals within the past 7 or 30 days can be selected. The server can adaptively determine the required historical data backtracking duration and data sampling frequency based on a preset forecasting time window to ensure a sufficient and representative sample size for trend fitting.

[0100] The trend of operational status data refers to the pattern or direction of the evolution of operational status parameters of a hazard source over time. For each hazard source, the server constructs a time series model or regression model, using historical time points as independent variables and various operational status data parameters as dependent variables, to fit the overall trend of each parameter's change over time. In one implementation, the server can use a linear regression model for trend fitting. Specifically, for a sequence of operational status parameter values ​​for a hazard source at multiple historical time points, the server fits a straight line y = a·t + b using the least squares method, where t is the time variable, a is the slope (reflecting the rate and direction of change), and b is the intercept. The sign of the slope a reflects the direction of the parameter's change over time (increasing or decreasing), and the absolute value of the slope a reflects the rate of change. This linear fitting method is computationally simple, highly interpretable, and suitable for scenarios where operational status parameters exhibit approximately linear change characteristics.

[0101] After completing the trend fitting, the server uses the fitted trend function to substitute the time points within the preset future time period into the trend function of each parameter, and extrapolates to calculate the predicted values ​​of the operating status data corresponding to each future time point.

[0102] Preset future time periods can be configured according to security management needs. For example, for scenarios requiring warnings a few minutes in advance, the preset future time period can be set to a corresponding short period; for scenarios requiring warnings a few hours in advance, the preset future time period can be set to a corresponding longer period; and for scenarios requiring warnings a few days in advance, the preset future time period can be set to a corresponding long period. The server can be configured with multiple different preset future time periods according to different warning scenarios to perform short-term, medium-term, and long-term predictions respectively.

[0103] After obtaining the predicted operational status data of each hazard source within a preset future time period, the server uses the same or similar risk assessment method as in step 202 to analyze and evaluate the predicted operational status data, obtaining the predicted risk information for each hazard source. Specifically, for each hazard source, the server extracts predicted feature data corresponding to multiple preset assessment dimensions from the predicted operational status data of that hazard source, and then performs weighted fusion of the predicted feature data according to the weight coefficients corresponding to each assessment dimension to obtain the predicted risk score for that hazard source. Further, the server compares the predicted risk score with the risk benchmark value and risk fluctuation range determined in step 202 above to determine the predicted individual risk level and the predicted individual risk occurrence probability. The methods for determining the predicted risk level and the predicted risk occurrence probability have been explained in detail above and will not be repeated here.

[0104] The preset warning conditions refer to the judgment rules that trigger the prediction warning. In one implementation, the warning condition may include: predicting that the individual's risk level reaches a preset level threshold (e.g., predicting that the individual's risk level reaches level III or above). In another implementation, the warning condition may include: predicting that the probability of the individual's risk occurring exceeds a preset probability threshold. In yet another implementation, the warning condition may be a combination of the above two conditions, that is, predicting that the individual's risk level reaches a preset level threshold and predicting that the probability of the individual's risk occurring exceeds a preset probability threshold. In one possible implementation, the warning condition may also include predicting the rate of deterioration of the risk status, that is, predicting that the slope of the risk score change within a preset future time period exceeds a preset slope threshold. Even if the predicted risk score has not yet reached a high-risk level, if its deterioration rate is too rapid, a warning will be triggered. This allows for the detection of scenarios where the current risk is manageable but is rapidly deteriorating.

[0105] When the server detects that the predicted risk information of any hazard source meets the preset warning conditions, it generates a predicted warning message for that hazard source. The server sends the predicted warning message to the corresponding terminal in the transportation system, where it is displayed through pop-up messages, voice broadcasts, list highlights, or special markers in a 3D digital safety map.

[0106] The beneficial effect of this embodiment is that by acquiring historical operational status data of each hazard source and fitting its changing trend, quantitative prediction of the future operational status of the hazard source is achieved, transforming the traditional passive response warning into an active forward warning, thus gaining valuable emergency response preparation time for managers.

[0107] In an optional embodiment, the method further includes: determining the control level of each hazard source based on its individual risk information; matching control measures corresponding to each control level from a preset control measure library based on the control level of each hazard source, generating a risk control plan for each hazard source, and sending the risk control plan for each hazard source to the terminal corresponding to the transportation system.

[0108] Control level refers to the priority or intensity of risk management for a hazard. While related to the aforementioned individual risk level, the concepts differ: the individual risk level focuses on the severity of the current risk posed by the hazard, i.e., how great the risk is, while the control level focuses on the level of control measures required for that hazard, i.e., the extent of control. The mapping between the two can be configured according to safety management strategies. For example, control levels can be divided into three levels: Level 1 control (routine control), Level 2 control (enhanced control), and Level 3 control (emergency control); or they can be divided into four levels, corresponding one-to-one with the four levels of individual risk levels.

[0109] In one implementation, the server can directly map the individual risk level of each hazard source to its corresponding control level. For example, an individual risk level of I (low risk) corresponds to Level 1 control (routine management), an individual risk level of II (general risk) corresponds to Level 2 control (enhanced management), and individual risk levels of III (significant risk) and IV (major risk) correspond to Level 3 control (emergency management). The mapping relationship can be flexibly adjusted according to actual safety management needs.

[0110] The pre-built control measure library is a collection of pre-built data containing various risk control measures and their applicable conditions. The library can be stored in a local server database or cloud storage, and its content can be regularly updated and optimized based on safety management regulations, industry standards, historical experience, and emergency plans. Each record in the control measure library can contain the following fields: measure identifier, measure name, measure description, applicable control level, applicable hazard type, applicable risk scenario, expected effect, resource requirements, and execution priority.

[0111] For example, the preset control measures library can be configured with the following control measures for different control levels: For Level 1 control (routine management), the corresponding control measures may include "increasing the frequency of operation status monitoring", "sending safety reminder notices", "routine equipment inspection", etc.; For Level 2 control (enhanced management), the corresponding control measures may include "speed limit operation", "load limit", "shortening inspection cycle", "assigning dedicated personnel for monitoring", etc.; For Level 3 control (emergency management), the corresponding control measures may include "immediately stop / shut down", "emergency evacuation of surrounding personnel", "activation of emergency plan", "notification of fire / emergency rescue departments to stand by", etc.

[0112] In one implementation, the server queries a pre-defined control measure library for all control measures matching the hazard level, generating a risk control plan for that hazard. The risk control plan can contain a combination of one or more control measures, and these measures can be prioritized. For example, for a hazardous chemical transport vehicle with a level 3 control requirement, the risk control plan might include: a primary measure "immediately pull over and activate hazard warning lights"; a secondary measure "notify the tollbooth ahead to prepare an emergency lane"; and an auxiliary measure "notify the nearest emergency response team to provide support." Logical relationships can be established between different measures, such as sequential or parallel execution, to form a complete control action chain.

[0113] It is understandable that the determination of the control level and the generation of the risk control plan are closely related to the risk assessment results and early warning information in the preceding steps. The higher the control level, the stronger the corresponding control plan, the higher the resource requirements, and the more urgent the timeliness of implementation.

[0114] The beneficial effect of this embodiment is that, firstly, by determining the control level based on the individual risk information of each hazard source, and then matching the corresponding control measures from the preset control measure library, the abstract risk assessment results are transformed into specific and executable control action instructions, thus realizing the whole-chain management from risk identification and assessment to risk control and disposal.

[0115] Figure 4 For a schematic diagram of the overall process of the early warning method for hazards in a transportation system in one embodiment, please refer to [link / reference]. Figure 4In a detailed embodiment, the server collects spatial coordinates (X, Y, Z) and operational status data of various typical hazards within the transportation system, specifically covering hazards of various physical forms such as bridge structures, tunnel facilities, vehicle transportation, rail facilities, and pipeline facilities. Further, in the individual risk assessment and quantification stage, the server, based on the currently collected operational status data, comprehensively scores the hazards from multiple preset assessment dimensions, including structural health, operational stability, environmental impact, historical failure rate, and maintenance status, as shown in the risk scoring dashboard in the figure. The example current risk score is 78. The assessment process is implemented through the following seven steps: first, extracting feature data corresponding to each assessment dimension; then, weighted fusion to obtain the current risk score; next, calculating historical risk scores and dividing the risk level range using a risk benchmark value as the center and risk fluctuation amplitude as the scale unit, thereby determining the individual risk level to which the current score falls; and finally, calculating the probability of individual risk occurrence based on the deviation of the current score from the benchmark value, ultimately generating individual risk information including the risk level (e.g., "higher" in the example) and the probability of risk occurrence (e.g., 65% as shown in the figure, with an upward trend). Furthermore, in the spatial mapping and early warning marker generation stage, the server maps each hazard source to its corresponding coordinate point in a pre-constructed 3D digital safety map and generates different early warning markers based on its individual risk level. Red, orange, yellow, light blue, and green are used to correspond to high risk, relatively high risk, medium risk, relatively low risk, and low risk, respectively, thus visualizing the spatial distribution. When multiple hazard sources cluster in space, the server identifies and comprehensively calculates the risk cluster area. Combining factors such as the number of covered hazard sources, the risk level distribution of hazard sources, the weighted probability of risk occurrence, and the spatial impact range, the server performs a risk intensity superposition analysis of the spatial area to obtain the comprehensive risk result of the risk cluster area. In the example, this is shown as a comprehensive risk level of "high" with a comprehensive risk score of 85. Based on this, the server generates early warning information for the risk cluster area. The early warning information includes the area ID (e.g., A-01), comprehensive risk level and score, radius of influence (e.g., 1.2km), number of covered hazards (e.g., 8), and recommended measures (e.g., strengthening monitoring, key inspections, restricting access). The early warning information is then visualized on a 3D digital safety map and finally displayed on multiple devices such as the command center screen, PC platform, and mobile terminals.

[0116] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0117] Based on the same inventive concept, this application also provides an early warning device for a transportation system hazard source to implement the aforementioned early warning method for a transportation system hazard source. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the early warning method device for a transportation system hazard source provided below can be found in the above-described limitations of the early warning method for a transportation system hazard source, and will not be repeated here.

[0118] In one exemplary embodiment, such as Figure 5 As shown, a warning device for hazardous sources in a transportation system is provided, comprising:

[0119] The acquisition module 501 is used to acquire the hazard sources of the transportation system and the spatial coordinates and current operating status data of each hazard source.

[0120] The assessment module 502 is used to assess the risk of each hazard source from multiple preset assessment dimensions based on the current operating status data of each hazard source, and obtain the individual risk information of each hazard source.

[0121] The mapping module 503 is used to map each hazard source to its corresponding spatial coordinate point in the three-dimensional digital safety map based on the spatial coordinate point of each hazard source, and to generate a corresponding warning mark at the corresponding spatial coordinate point in the three-dimensional digital safety map according to the individual risk information of each hazard source; the three-dimensional digital safety map is pre-constructed based on the geographic information data of the area where the transportation system is located;

[0122] The determination module 504 is used to determine the risk cluster area covering multiple hazard sources and the comprehensive risk information of the risk cluster area in the three-dimensional digital safety map based on the individual risk information of each hazard source.

[0123] The generation module 505 is used to generate early warning information for the risk cluster area based on the comprehensive risk information of the risk cluster area and the early warning marks of each hazard source covered by the risk cluster area in the three-dimensional digital safety map. The early warning information is used to visually mark the risk cluster area in the three-dimensional digital safety map for display on the corresponding terminal of the transportation system.

[0124] In an optional embodiment, the evaluation module 502 is used to:

[0125] For each hazard, feature data corresponding to multiple preset evaluation dimensions is extracted from the current operational status data of that hazard.

[0126] Based on the weight coefficients corresponding to each assessment dimension, the feature data corresponding to each assessment dimension are weighted and fused to obtain the current risk score of the hazard source.

[0127] Obtain the historical operational status data of the hazard source at multiple historical moments, and calculate the historical risk score corresponding to each historical moment based on the historical operational status data at each historical moment.

[0128] Based on the preset number of levels, multiple risk level ranges are divided with the risk benchmark value as the center and the risk fluctuation range as the scale unit; different risk level ranges correspond to different levels.

[0129] The level corresponding to the risk level range into which the current risk score of the hazard source falls is determined as the individual risk level of the hazard source;

[0130] The individual probability of occurrence of the hazard is determined based on the degree of deviation between the current risk score and the risk benchmark value; whereby the degree of deviation is positively correlated with the probability of occurrence.

[0131] Based on the individual risk level and probability of occurrence of each hazard source, the individual risk information of each hazard source is determined.

[0132] In an optional embodiment, the determining module 504 is used to:

[0133] Based on the individual risk level of each hazard source, determine the risk impact radius of each hazard source;

[0134] Using the spatial coordinates of each hazard source as the center and the corresponding risk impact radius, a risk intensity distribution for each hazard source is generated; the risk intensity distribution represents the risk intensity value of the hazard source at different spatial coordinates.

[0135] The risk intensity distribution of each hazard source is projected onto a three-dimensional digital safety map, and the risk intensity values ​​at each spatial coordinate point on the three-dimensional digital safety map are accumulated to obtain the comprehensive risk intensity value at each spatial coordinate point on the three-dimensional digital safety map.

[0136] Based on the comprehensive risk intensity value at each spatial coordinate point on the three-dimensional digital safety map, the spatial area with a comprehensive risk intensity value greater than the preset clustering threshold and covering at least two hazard sources is identified as a risk clustering area.

[0137] Based on the individual risk occurrence probability of each hazard source within the risk cluster area, the overall risk occurrence probability of the risk cluster area is determined, and based on the overall risk intensity value at each spatial coordinate point within the risk cluster area, the overall risk level of the risk cluster area is determined.

[0138] Based on the overall risk level and overall probability of occurrence of the risk cluster area, the overall risk information of the risk cluster area is determined.

[0139] In an optional embodiment, the mapping module 503 is used to:

[0140] Based on the individual risk level of each hazard, the corresponding marking color for each hazard is determined; different individual risk levels correspond to different marking colors.

[0141] Based on the individual risk occurrence probability of each hazard, the corresponding marking size for each hazard is determined; whereby the marking size is positively correlated with the risk occurrence probability.

[0142] Based on the corresponding marker color and size of each hazard, a warning marker is generated at the corresponding spatial coordinate point in the 3D digital safety map for each hazard.

[0143] In an optional embodiment, the determining module 504 is used to:

[0144] The fill color and transparency of the risk cluster areas are determined based on the overall risk level of the risk cluster areas.

[0145] The boundary line shape is determined based on the overall probability of risk occurrence in the risk cluster area, and the boundary line width is determined based on the size of the warning signs corresponding to each hazard source covered by the risk cluster area.

[0146] The boundary color of the risk cluster area is determined based on the color of the marker corresponding to the highest individual risk level among the warning markers for each hazard source covered by the risk cluster area.

[0147] In the 3D digital security map, risk cluster areas are marked by filling color and fill transparency, and the boundary lines of risk cluster areas are drawn according to boundary line type, boundary line width and boundary line color to obtain the area warning mark of risk cluster areas.

[0148] Based on the regional early warning markers of risk clusters, early warning information is generated for those risk clusters.

[0149] In an optional embodiment, it further includes:

[0150] The historical data acquisition module is used to acquire historical operational status data of each hazard source at multiple historical moments;

[0151] The fitting module is used to fit the changing trend of the operating status data of each hazard source based on the historical operating status data of each hazard source at multiple historical moments.

[0152] The prediction module is used to predict the operating status data of each hazard source within a preset future time period based on the changing trend of the operating status data of each hazard source, and obtain the predicted operating status data of each hazard source.

[0153] The assessment module is used to conduct risk assessments on each hazard source from multiple preset assessment dimensions based on the predicted operating status data of each hazard source, and obtain the predicted risk information of each hazard source.

[0154] The early warning generation module is used to generate predictive early warning information for any hazard source when the predicted risk information of any hazard source reaches the preset early warning conditions.

[0155] In an optional embodiment, it further includes:

[0156] The control level determination module is used to determine the control level of each hazard source based on its individual risk information.

[0157] The scheme generation module is used to match control measures corresponding to each control level from the preset control measure library according to the control level of each hazard source, generate risk control schemes for each hazard source, and send the risk control schemes for each hazard source to the corresponding terminal of the transportation system.

[0158] The various modules in the aforementioned early warning device for hazardous sources in a transportation system can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0159] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores hazard source data, operational status data, historical operational status data, risk assessment results data, and three-dimensional digital safety map data for the transportation system. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a method for early warning of hazard sources in a transportation system.

[0160] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0161] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0162] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0163] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0164] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0165] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0166] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0167] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for early warning of hazardous sources in a transportation system, characterized in that, include: Acquire the hazardous sources in the transportation system, as well as the spatial coordinates and current operating status data of each hazardous source; Based on the current operating status data of each of the aforementioned hazards, risk assessments are performed on each of the aforementioned hazards from multiple preset assessment dimensions to obtain individual risk information for each of the aforementioned hazards. Based on the spatial coordinates of each of the aforementioned hazards, each hazard is mapped to a corresponding spatial coordinate in the three-dimensional digital safety map, and a corresponding warning marker is generated at the corresponding spatial coordinate in the three-dimensional digital safety map according to the individual risk information of each hazard. The three-dimensional digital safety map is pre-constructed based on geographic information data of the area where the transportation system is located; Based on the individual risk information of each of the aforementioned hazards, the risk clustering areas covering multiple hazards and the comprehensive risk information of the risk clustering areas are determined in the three-dimensional digital safety map. Based on the comprehensive risk information of the risk cluster area and the warning markers of each hazard source covered by the risk cluster area in the three-dimensional digital safety map, warning information is generated for the risk cluster area. The warning information is used to visually mark the risk cluster area in the three-dimensional digital safety map for display on the terminal corresponding to the transportation system.

2. The method according to claim 1, characterized in that, Based on the current operational status data of each hazard source, risk assessments are performed on each hazard source from multiple preset evaluation dimensions to obtain individual risk information for each hazard source, including: For each hazard, feature data corresponding to multiple preset evaluation dimensions is extracted from the current operational status data of that hazard. Based on the weight coefficients corresponding to each of the assessment dimensions, the feature data corresponding to each assessment dimension are weighted and fused to obtain the current risk score of the hazard source. Obtain the historical operating status data of the hazard source at multiple historical moments, and calculate the historical risk score corresponding to each historical moment based on the historical operating status data at each historical moment. Based on the preset number of risk levels, multiple risk level intervals are divided with the risk benchmark value as the center and the risk fluctuation range as the scale unit; wherein, different risk level intervals correspond to different levels. The level corresponding to the risk level range into which the current risk score of the hazard source falls is determined as the individual risk level of the hazard source; The individual probability of occurrence of the hazard is determined based on the degree of deviation between the current risk score of the hazard and the risk benchmark value; wherein the degree of deviation is positively correlated with the probability of occurrence of the risk. Based on the individual risk level and probability of occurrence of each hazard source, the individual risk information of each hazard source is determined.

3. The method according to claim 2, characterized in that, Based on the individual risk information of each hazard source, the risk clustering area covering multiple hazard sources in the three-dimensional digital safety map and the comprehensive risk information of the risk clustering area are determined, including: Based on the individual risk level of each hazard source, determine the risk impact radius of each hazard source. Using the spatial coordinate point of each hazard source as the center and the corresponding risk impact radius, a risk intensity distribution for each hazard source is generated; the risk intensity distribution represents the risk intensity value of the hazard source at different spatial coordinate points. The risk intensity distribution of each of the aforementioned hazards is projected onto the three-dimensional digital safety map, and the risk intensity values ​​at each spatial coordinate point on the three-dimensional digital safety map are accumulated to obtain the comprehensive risk intensity value at each spatial coordinate point on the three-dimensional digital safety map. Based on the comprehensive risk intensity value at each spatial coordinate point on the three-dimensional digital safety map, the spatial area with a comprehensive risk intensity value greater than a preset clustering threshold and covered by at least two hazard sources is identified as a risk clustering area. Based on the individual risk occurrence probability of each hazard source within the risk cluster area, the overall risk occurrence probability of the risk cluster area is determined, and based on the overall risk intensity value at each spatial coordinate point within the risk cluster area, the overall risk level of the risk cluster area is determined. Based on the overall risk level and overall risk occurrence probability of the risk cluster area, the overall risk information of the risk cluster area is determined.

4. The method according to claim 2, characterized in that, Based on the individual risk information of each hazard source, corresponding warning markers are generated at the corresponding spatial coordinate points in the three-dimensional digital safety map, including: Based on the individual risk level of each hazard, the corresponding marking color for each hazard is determined; wherein, different individual risk levels correspond to different marking colors; Based on the individual risk occurrence probability of each hazard, the corresponding marking size for each hazard is determined; wherein, the marking size is positively correlated with the risk occurrence probability; Based on the corresponding marker color and size of each hazard source, a warning marker is generated at the corresponding spatial coordinate point in the three-dimensional digital safety map.

5. The method according to claim 4, characterized in that, Based on the comprehensive risk information of the risk cluster area and the warning markers of each hazard source covered by the risk cluster area in the three-dimensional digital safety map, warning information for the risk cluster area is generated, including: The fill color and fill transparency of the risk cluster area are determined based on the overall risk level of the risk cluster area. The boundary line shape is determined based on the overall risk occurrence probability of the risk cluster area, and the boundary line width is determined based on the marking size of the warning marks corresponding to each hazard source covered by the risk cluster area. The boundary color of the risk cluster area is determined based on the color of the marker corresponding to the highest individual risk level among the warning markers of each hazard source covered by the risk cluster area. In the three-dimensional digital security map, the risk cluster area is filled and marked according to the fill color and fill transparency, and the boundary line of the risk cluster area is drawn according to the boundary line type, the boundary line width and the boundary line color to obtain the area warning mark of the risk cluster area; Based on the regional early warning markers of the risk cluster areas, early warning information is generated for the risk cluster areas.

6. The method according to claim 1, characterized in that, The method further includes: Obtain historical operational status data of each of the aforementioned hazards at multiple historical moments; Based on the historical operational status data of each of the aforementioned hazards at multiple historical moments, fit the changing trend of the operational status data of each of the aforementioned hazards. Based on the changing trend of the operating status data of each of the aforementioned hazards, the operating status data of each of the aforementioned hazards in a preset future time period is predicted, thereby obtaining the predicted operating status data of each of the aforementioned hazards. Based on the predicted operating status data of each of the aforementioned hazards, risk assessments are performed on each of the aforementioned hazards from the multiple preset assessment dimensions to obtain the predicted risk information of each of the aforementioned hazards. When the predicted risk information of any hazard source reaches the preset warning conditions, a predicted warning information for that hazard source is generated.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: Based on the individual risk information of each hazard source, the control level of each hazard source is determined; Based on the control level of each hazard source, control measures corresponding to each control level are matched from a preset control measure library to generate a risk control plan for each hazard source, and the risk control plan for each hazard source is sent to the terminal corresponding to the transportation system.

8. A warning device for hazardous sources in a transportation system, characterized in that, The device includes: The acquisition module is used to acquire the hazard sources of the transportation system and the spatial coordinates and current operating status data of each hazard source. The assessment module is used to assess the risk of each hazard source from multiple preset assessment dimensions based on the current operating status data of each hazard source, and obtain the individual risk information of each hazard source. The mapping module is used to map each of the hazards to a corresponding spatial coordinate point in the three-dimensional digital safety map based on the spatial coordinate points of each hazard, and to generate a corresponding warning marker at the corresponding spatial coordinate point in the three-dimensional digital safety map according to the individual risk information of each hazard; the three-dimensional digital safety map is pre-constructed based on the geographic information data of the area where the transportation system is located; The determination module is used to determine the risk cluster area covering multiple hazard sources and the comprehensive risk information of the risk cluster area in the three-dimensional digital safety map based on the individual risk information of each hazard source. The generation module is used to generate early warning information for the risk cluster area based on the comprehensive risk information of the risk cluster area and the early warning marks of each hazard source covered by the risk cluster area in the three-dimensional digital safety map. The early warning information is used to visually mark the risk cluster area in the three-dimensional digital safety map for display on the terminal corresponding to the transportation system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images