Traffic safety early warning method and device and computer equipment

Abstract

The embodiment of the invention provides a traffic safety early warning method and device and computer equipment, and the method comprises the steps: carrying out the superposition of a known weather monitoring network and a known rail traffic network, and displaying the weather state data of a first target area after the superposition; determining a second target area with a disaster weather risk in the first target area according to the weather state data; determining a rail transit network operation safety factor association relationship and strength thereof in the second target area; and constructing a disaster weather and second target area rail transit network operation safety factor influence association view, forming a disaster weather influence knowledge graph, and based on the weather influence knowledge graph, combining the rail transit network operation safety factor association relationship and the strength thereof to obtain a second target area rail transit network operation safety factor influence association view. The grade of the evaluation result of the operation safety toughness of the rail transit network in the disaster weather is comprehensively determined so as to trigger combined early warning, and the coping requirements of the sudden severe weather in the local area or part of stations of the network can be met.

Description

Technical Field

[0001] The present application relates to the technical field of rail transit safety and emergency management, and in particular, to a traffic safety early warning method, device and computer equipment. Background Art

[0002] Rail transit lines and stations are divided into various forms such as above-ground and underground according to their locations. The underground sections are greatly affected by leakage and precipitation due to their closed space, and the above-ground sections are greatly affected by the external weather environment. Heavy rain, heavy snow, strong winds, heavy fog, sandstorms, high temperatures, lightning, hail, frost, cold waves, haze and other severe weather and natural conditions have a significant impact on rail transit operations, especially on viaducts and ground sections. Operation management faces huge pressure to ensure service operations. The current train operation organization has approached the design limit, and any factors that affect the order of train reception and dispatch will have a great impact. In addition, the rail transit network covers a large area, and the system disturbances it brings about have gradually become more and more obvious in terms of the impact on the network operation. Usually, the chaos in the operation order of a "single point" will quickly spread to other stations, and even the entire line, and even affect the operation of the entire network. Specifically, the impact of bad weather on underground lines and trains is mainly due to the large amount of rainwater backflowing into stations and tunnels, as well as the surge in passenger flow caused by extreme weather, which leads to the need to improve the line capacity in a short period of time and quickly adjust the train operation diagram, which poses a great challenge to the existing operation organization management and driving command of rail transit; in the ground or viaduct sections, bad weather directly affects the line's ground equipment, infrastructure and running trains, deteriorating the train's traction and braking performance, deteriorating the performance of facilities and equipment, reducing the service quality of mobile equipment and infrastructure, and having a great impact on driving safety and efficiency, thereby increasing the risk of train accidents. Among them, the elevated lines and ground lines are the most affected by weather. Under the action of strong side winds, the aerodynamic performance of the train deteriorates, and the air resistance, lift, and lateral force of the train increase rapidly, affecting the lateral stability of the train, and in severe cases, causing the train to overturn. Strong winds may also cause damage to urban rail infrastructure, such as sweeping away urban rail transit operating equipment, blowing billboards and temporary buildings around the line into the track area and even the contact network, affecting driving safety.

[0003] Urban rail transit generally adopts a single-line construction model. Professional systems such as the professional monitoring system and risk management system of the same line operate independently. Daily safety monitoring and risk prevention and control are usually managed by the relevant professional departments. As the lines are opened one after another and become increasingly large, some urban rail transit lines even cross cities to connect urban areas and metropolitan areas, extending to provincial areas. The operation and management of lines and stations by transportation companies are becoming more and more refined, shifting from city line-level management to regional management, and even grid management. In recent years, with the increasing number of rare and severe weather, traditional weather warnings are issued to the entire network, which is difficult to meet the needs of responding to sudden severe weather in local areas or some stations of the network, especially in the process of severe weather changes. The different sections of the huge rail transit network have different locations, ground or underground environments, and completely different prevention and control measures. The current monitoring and early warning technology has coarse granularity, a large information release range for weather warnings, and no correlation with professional equipment systems, risk hazards, passenger flow and risk locations. It lacks the ability to comprehensively analyze multiple safety risks, the structure and integration mutual recognition of dynamic monitoring and early warning data are insufficient, and the synchronization and consistency of data updates are lacking, resulting in a lag in the information needed to quickly respond to severe weather, weak prevention capabilities for secondary disasters, and a lack of comprehensive decision-making support for technical means. Summary of the invention

[0004] The embodiments of the present application provide a traffic safety warning method, device and computer equipment.

[0005] A first aspect of an embodiment of the present application provides a traffic safety warning method, comprising:

[0006] Overlaying a known weather monitoring network and a rail transit network, and displaying weather status data of a first target area after the overlay, wherein the first target area is determined based on a rail transit line in the rail transit network;

[0007] Determine, based on the weather status data of the first target area, a second target area having a disaster weather risk in the first target area;

[0008] Determine the correlation relationship and strength of the rail transit network operation safety factors of the second target area according to the rail transit network operation safety factors of the second target area, wherein the rail transit network operation safety factors include infrastructure, equipment system, risk source and passenger flow;

[0009] Construct a correlation view of the impact of disastrous weather and safety factors of rail transit network operation in the second target area, form a knowledge graph of disastrous weather impact, and based on the weather impact knowledge graph, combine the correlation and intensity of rail transit network operation safety factors, comprehensively determine the level of the impact of disastrous weather on the rail transit network operation safety resilience assessment results, so as to trigger a joint warning.

[0010] In an optional embodiment of the present application, superimposing the known weather monitoring network and the rail transit network includes:

[0011] The grid cells within a preset range where the rail transit lines in the known rail transit network are located are defined as rail grids;

[0012] Overlaying a known weather monitoring network with all orbital grids, wherein the weather monitoring network includes a plurality of weather grids;

[0013] Determine weather status data of the track line in each track grid according to the overlap between the track grid and the weather grid;

[0014] The first target area is the belt-shaped influence area centered on the center line of the track line with meteorological attributes in the track grid.

[0015] In an optional embodiment of the present application, determining the weather status data of the track line in each track grid according to the overlap between the track grid and the weather grid includes:

[0016] For the rail lines in each rail grid, the actual weather conditions, weather forecasts and severe weather warnings of the city grid where the current rail line is located are represented as weather status data of the rail lines in each rail grid.

[0017] In an optional embodiment of the present application, the displaying of weather status data of the first target area includes:

[0018] A color band of the first target area in each track grid is drawn according to the weather status data of the first target area in each track grid, wherein:

[0019] The color band of the first target area in each track grid is drawn by a variable rectangular unit. The length of the variable rectangular unit If two adjacent unit color strip rectangles overlap, the width of the unit color strip rectangle is halved until there is no overlap between the two adjacent unit color strip rectangles. X1(i) is the x-axis coordinate value of the starting point of the center line coordinate of the uplink line of the i-th line in the track grid, X2(i) is the x-axis coordinate value of the starting point of the center line coordinate of the downlink line, Y1(i) is the y-axis coordinate value of the end point of the center line coordinate of the uplink line, Y2(i) is the y-axis coordinate value of the end point of the center line coordinate of the downlink line, R l′ is the ribbon extension width, and R l′ >0.

[0020] In an optional embodiment of the present application, determining the rail transit network operation safety factor association relationship and its strength of the second target area according to the rail transit network operation safety factor of the second target area includes:

[0021] Obtain the attributes and features N of the infrastructure in the second target area, N = {O i , T i , γ i}, where O i = {0, 1}, if the second target area track grid belongs to the uplink section of the traffic line section range, then O i =0, it belongs to the downward interval, then O i =1; T i = {0, 1}, if the second target area track grid belongs to the station range and is a ground station, then T i =0, if it is an underground station T i =1;γ i = {1, 2, 3}, the reliability level is divided into level 1, level 2, and level 3 from low to high according to the degree of weather impact on the infrastructure, the configuration of supporting rescue resources, and the convenience of obtaining them;

[0022] Obtain the fault alarm information E of the equipment system in the second target area, E={F i , Y i , L i}, F i = {1,2}, if there is an alarm of equipment system affected by weather in the second target area, then the alarm type F i =1; if there is no equipment system alarm affected by weather in the second target area, the alarm type F i =2; if the fault alarm does not affect traffic operations, then Y i =0; if the fault alarm affects traffic operations, then Y i =1; Alarm level L i ={1,2,3}, the alarm level is divided into three levels from low to high;

[0023] Get the risk source information R of the second target area i , R i ={1,2,3}, R i =1 means the risk level of the dangerous source affected by weather in the second target area is below medium, R i =2 means the risk level is above moderate, R i =3 means the risk level is a major risk;

[0024] Get the passenger flow information P of the second target area, P = {S i , V i},S i =0 means the weather impact time and space range of the second target area is at the station, S i =1 means the weather influence time and space range is within the interval; V i represents the impact of passenger flow, V i={I, II, III, IV}, set thresholds as warning levels according to the size of passenger flow, from low to high corresponding to IV warning, III warning, II warning, and I warning;

[0025] The rail transit network operation safety factors G={N, E, R, P} of the second target area are gathered, and the influencing factors of each rail transit network operation safety factor are set as the weight of each rail transit network operation safety factor, so as to determine the correlation and intensity of the rail transit network operation safety elements of the second target area according to each rail transit network operation safety factor and its weight.

[0026] In an optional embodiment of the present application, the construction of the disaster weather and the second target area rail transit network operation safety factor impact association view to form the disaster weather impact knowledge graph includes:

[0027] Entities and relationships are defined, where entity element types at least include the second target area's transportation routes, stations, sections, units, departments, positions, weather, equipment, systems, risk hidden danger lists, passenger flow, response processing types and indicators; relationship types at least include the second target area's geographical location, disposal positions, affiliation, responsibility, warning, degree, cause and time series;

[0028] The entities and relationships in the data layer are associated and mapped according to the preset method of the pattern layer to obtain a knowledge graph of the impact of weather events on traffic operation safety. The pattern layer and data layer are constructed in a top-down and bottom-up manner respectively.

[0029] The semantic association relationship between emergency data is divided into association relationship at the spatiotemporal level and the correlation between data. Among them, the association relationship at the spatiotemporal level unifies the emergency data into the same measurement unit. According to the time span and spatial range of the target data, the time overlap and spatial overlap between the data sets represented by each factor are calculated. The correlation between data is determined by calculating the support and confidence, and the frequent data item sets that appear simultaneously in the operational emergency data set caused by disaster weather are determined. The association rules between data are mined, the potential connections between hidden data are determined, and the optimized knowledge graph is obtained as the weather impact knowledge graph.

[0030] In an optional embodiment of the present application, the method further includes:

[0031] The following expression is used to determine the association strength coefficient of the entity elements according to the degree of association between the entity elements:

[0032] θ=X(k)×δ / Σ x∈{N,E,R,P} X(k),θ∈[0,1]

[0033] Among them, θ is the association strength coefficient of the entity element, X(k) is the association strength of the kth entity element in the knowledge graph, that is, the cumulative number of association relationships, and δ is the weight of one factor among infrastructure, equipment system, risk source and passenger flow.

[0034] In an optional embodiment of the present application, based on the weather impact knowledge graph, combined with the correlation relationship and intensity of rail transit network operation safety elements, the level of disaster weather on the rail transit network operation safety resilience assessment result is comprehensively determined to trigger a joint warning, including:

[0035] According to the influence intensity of the correlation intensity coefficient of the entity elements, the F(θ, KN(), t) data set is sorted, and the data set ranked first is output. When the result data set of F(θ, KN(), t) contains elements that affect train operation, Tr=1, otherwise it is 0; when it contains elements that affect the passenger service level, Ps=1, otherwise it is 0; when it contains elements that damage the infrastructure or equipment system and affect the operation, Da=1, otherwise it is 0; when it contains elements that cause losses due to equipment system failures, Ls=1, otherwise it is 0; where F(θ, KN(), t) is the composition of the regional risk influencing elements of urban rail under the influence of the corresponding correlation intensity θ of each entity element X in the five-tuple KN data set under the influence of the current severe weather over a certain time range t;

[0036] Based on the calculation of the impact of the dataset of influencing factors in the knowledge graph on resilience and the reliability of its impact intensity B, combined with the weather warning status of the current track grid, the comprehensive evaluation value of the safety resilience assessment is calculated as the result of the joint warning, expressed as B∩PH R(i) , where B is defined as (δ t Tr+δ p Ps+δ d Da+δ l Ls) represents the comprehensive reliability, where train operation Tr, passenger service level Ps, track system Da, casualties and losses Ls correspond to the reliability impact of four indicators respectively, δ t ,δ p ,δ d and δ l Respectively represent the weight coefficients of the corresponding indicators, PH R(i) Indicates the weather warning for the area where the i-th track line segment in the track grid is located; when PH R(i) =1 indicates that there is a weather warning in this section. R(i) =0 means no weather warning; when a weather warning occurs, a joint safety warning is issued; when no weather warning occurs but B≠0, only a weather risk warning is issued;

[0037] The result of the joint warning is marked as the resilience assessment value under the influence of the current severe weather, and used as the basis for the warning level. Three levels are set, and the resilience level decreases in turn, and the corresponding three-level warning is issued;

[0038] The above calibration process is iterated to traverse the track line segment in each track grid until the calibration of the warning information is completed.

[0039] The level of the safety resilience assessment results is determined based on the safety resilience assessment results of the rail transit network operation to trigger a joint early warning.

[0040] A third aspect of the embodiments of the present application provides a traffic safety warning device, including:

[0041] An overlay model is used to overlay a known weather monitoring network and a rail transit network to display weather status data of a first target area after overlay, wherein the first target area is determined based on a rail transit line in the rail transit network;

[0042] A first determination module is used to determine a second target area with a disaster weather risk in the first target area according to the weather status data of the first target area;

[0043] A second determination module is used to determine the correlation relationship and strength of the rail transit network operation safety factors of the second target area according to the rail transit network operation safety factors of the second target area, wherein the rail transit network operation safety factors include infrastructure, equipment system, risk source and passenger flow;

[0044] A construction module is used to construct a correlation view of the impact of disaster weather and safety factors of rail transit network operation in the second target area, forming a knowledge graph of disaster weather impact. Based on the weather impact knowledge graph and combined with the correlation and intensity of rail transit network operation safety factors, the level of disaster weather on rail transit network operation safety resilience assessment results is comprehensively determined to trigger a joint warning.

[0045] According to a third aspect of an embodiment of the present application, a computer device is provided, comprising: a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any of the above traffic safety warning methods are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0047] Figure 1 A flow chart of a traffic safety warning method provided for one embodiment of the present application;

[0048] Figure 2 A flow chart of a traffic safety warning method provided by another embodiment of the present application;

[0049] Figure 3 A track grid mark is superimposed on a track line of an electronic map provided in one embodiment of the present application;

[0050] Figure 4 The position coordinates of the track line section in the grid provided by one embodiment of the present application;

[0051] Figure 5 A method for drawing color bands for traditional density maps;

[0052] Figure 6 A rectangular unit segmentation method is provided in one embodiment of the present application to draw a color band diagram;

[0053] Figure 7 A schematic diagram of the structure of a traffic safety warning device provided in one embodiment of the present application;

[0054] Figure 8 A schematic diagram of the computer device structure provided for one embodiment of the present application. DETAILED DESCRIPTION

[0055] In the process of implementing this application, the inventors found that the current weather warnings issued to the entire rail transit network are difficult to meet the needs of responding to sudden severe weather in local areas or some stations of the network.

[0056] In response to the above problems, a traffic safety warning method is provided in an embodiment of the present application, which can meet the needs of responding to sudden severe weather in local areas or some stations of the network.

[0057] The solutions in the embodiments of the present application can be implemented using various computer languages, for example, the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0058] In order to make the technical solutions and advantages in the embodiments of the present application more clearly understood, the exemplary embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than an exhaustive list of all the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0059] See also Figure 1 and Figure 2 The traffic safety warning method provided in the embodiment of the present application includes:

[0060] S1, superimposing a known weather monitoring network and a rail transit network to display weather status data of a first target area after superposition, wherein the first target area is determined based on a rail transit line in the rail transit network.

[0061] In an optional embodiment of the present application, superimposing the known weather monitoring network and the rail transit network includes:

[0062] The grid cells within a preset range where the rail transit lines in the known rail transit network are located are defined as rail grids;

[0063] Overlaying a known weather monitoring network with all orbital grids, wherein the weather monitoring network includes a plurality of weather grids;

[0064] Determine weather status data of the track line in each track grid according to the overlap between the track grid and the weather grid;

[0065] The first target area is the belt-shaped influence area centered on the center line of the track line with meteorological attributes in the track grid.

[0066] In an optional embodiment of the present application, determining the weather status data of the track line in each track grid according to the overlap between the track grid and the weather grid includes:

[0067] For the rail lines in each rail grid, the actual weather conditions, weather forecasts and severe weather warnings of the city grid where the current rail line is located are represented as weather status data of the rail lines in each rail grid.

[0068] In an optional embodiment of the present application, the displaying of weather status data of the first target area includes:

[0069] A color band of the first target area in each track grid is drawn according to the weather status data of the first target area in each track grid, wherein:

[0070] The color band of the first target area in each track grid is drawn by a variable rectangular unit. The length of the variable rectangular unit If two adjacent unit color strip rectangles overlap, the width of the unit color strip rectangle is halved until there is no overlap between the two adjacent unit color strip rectangles. X1(i) is the x-axis coordinate value of the starting point of the center line coordinate of the uplink line of the i-th line in the track grid, X2(i) is the x-axis coordinate value of the starting point of the center line coordinate of the downlink line, Y1(i) is the y-axis coordinate value of the end point of the center line coordinate of the uplink line, Y2(i) is the y-axis coordinate value of the end point of the center line coordinate of the downlink line, R l′ is the ribbon extension width, and R l′>0. In an optional embodiment of the present application, based on China's meteorological data, the evolution law of severe weather is obtained according to the characteristics of the data structure, and the personalized weather evolution data prediction results of large-scale and small-scale spatial and temporal scales with different characteristics of severe weather are used. Based on machine learning algorithms, combined with the distance, curve, mileage, station scale and other attributes of rail transit lines, a severe weather warning algorithm suitable for urban rail transit is constructed to forecast and warn of weather changes with a spatial resolution of not less than 500m at different spatial and temporal scales such as ten minutes, one hour and three hours in the future. Based on real-time meteorological information, accurate monitoring and real-time warning of severe weather suitable for the characteristics of rail transit lines are constructed.

[0071] In an optional embodiment of the present application, when the rail transit is urban rail transit, before superimposing the known weather monitoring network and the rail transit line network to display the weather status data of the first target area after superimposition, the method further includes:

[0072] The first step is to grid the distribution range of meteorological monitoring and urban rail network distribution

[0073] Based on the electronic map of the city where the rail transit network is located, grid processing is carried out, and the grid is divided into the smallest unit. Since the direct passenger attraction area of ​​urban rail transit is 1km in radius with the station as the center, and the emergency resource connection area is 500m in radius with the station entrance and exit as the center, the default minimum unit grid range of rail transit weather monitoring calibration is set to 500m*500m to improve the granularity and accuracy of monitoring. Based on real-time meteorological big data, subway monitoring focus points are set according to the characteristics of the monitoring lines to monitor different types of severe weather such as heavy rain, heavy snow, strong wind, heavy fog, sandstorm, high temperature, lightning, hail, frost, cold wave, haze, etc.

[0074] The longitude and latitude coordinates (X i , Y i ), the longitude and latitude coordinates (X j , Y j ), the maximum range of the overlapping area is determined as the target range of rail transit network weather monitoring, that is, (Max(X i，j ), Min(Y i，j )),(Max(X i，j ), Max(Y i，j )),(Min(X i，j ),Min(Y i，j )),(Min(X i，j),Max(Y i，j )), four coordinate points are used as boundaries to match the track network with the longitude and latitude of meteorological monitoring to build a weather monitoring network where the track network is located.

[0075] In addition, according to the density of measuring points within the urban meteorological monitoring range, the grid unit with a range of 1km*1km is defined as the "urban grid", and the grid unit with a range of 500m*500m where the rail transit line is located is defined as the "track grid". The principle of meteorological monitoring values ​​within the urban grid is as follows: the temperature is taken as the average temperature of one or more measuring points; the meteorological warning is graded as the warning peak value of one or more measuring points. The track grid is usually manifested as the irregular shape of the track line, straight sections, curved sections, stations, etc. According to the principle of representing the same track grid as a unified meteorological value, the actual weather conditions and severe weather warnings of the stations and intervals within it are represented as the meteorological values ​​of the current urban grid. The meteorological monitoring values ​​are calibrated into three categories: actual weather conditions, weather forecasts, and weather warnings. The minimum unit range of the weather warning is not less than the urban administrative division.

[0076] In order to improve the computational processing efficiency of system operation and visualization display, the track grid is identified on the basis of the urban grid, and the belt-shaped influence range area centered on the center line of the track line with meteorological attributes in the track grid is used as the first target area for the background operation of dynamic visualization and early warning of meteorological conditions along the line, which greatly reduces the invalid operation of non-track areas and significantly saves computing power. There are three forms of representing meteorological conditions in the track grid area: displaying the actual temperature along the track area based on the electronic map; forecasts for the next day; and displaying early warning marks on the track segment with the track grid as the unit.

[0077] The second step is to share and predict meteorological data and rail transit weather warning data

[0078] Since the update frequencies of actual weather conditions, weather forecasts, and weather warnings in urban meteorological data are different, the frequencies of weather conditions displayed in the track grid are different and need to be processed separately. Set different types of interfaces, set independent interface channels for the actual temperature conditions, weather forecasts, and warnings along the track, collect different data accordingly and update and display them separately. Weather warning data is used as the basic data for joint warning of resilience assessment. The business warning information of resilience assessment based on knowledge graph is comprehensively evaluated to obtain the joint warning results, which are displayed accordingly on the track line segments within the track grid. By classifying the interface for same-frequency updates and asynchronous analysis and updates, computing power can be effectively saved.

[0079] By establishing a data interface with the city weather monitoring system, the use of meteorological data complies with the interface protocol of the relevant service provider. The interface types for obtaining meteorological data are divided into real-time weather, forecast weather, warning, etc., and the GET request method of the standard HTTP protocol is used to obtain the latest weather data. According to the data type of the meteorological interface, the update frequency of the real-time weather is defined, which defaults to 10 minutes; the update frequency of the weather forecast is 1 hour by default; the weather warning is divided into normal / abnormal (when severe weather occurs), the normal update frequency is 2 hours by default, and the abnormal update frequency is 30 minutes by default. According to the rail transit weather real-time and forecast warning functions corresponding to different types of meteorological data types, formulate scheduled tasks that meet the data update frequency, and save the acquired meteorological data in the database. The data timeliness of meteorological data access and rail transit business scenario applications is defined as:

[0080] Data timeliness: 10-30-40 automatic stations - 100-1000 are collected to the center, processed (maybe 15min delay), and background exception processing (1-2 times / y);

[0081] Data anomalies (data processing of 9999 abnormal values, correction prompts for data in non-agreed formats);

[0082] The spatiotemporal definition of meteorological elements (actual data → within 1 minute; forecast → 9:00-10:00 - update frequency is 30 minutes;) warning data is updated within 15 minutes.

[0083] Step 3: Determine the color band area of ​​the track line within the nested grid and refine the collision color

[0084] In an optional embodiment of the present application, when the rail transit is urban rail transit, superimposing the known weather monitoring network and the rail transit line network to display the weather status data of the first target area after superposition includes:

[0085] Obtain weather monitoring information, combine it with the operation status of the area where the subway operates, and rely on electronic maps to overlay the affected areas on the rail transit line map for a comprehensive dynamic display.

[0086] First, the basic weather information content is displayed based on the rail transit line network topology map. According to the meteorological data located near the station, click on the line between the two stations to query the regional weather, call the electronic map engine, and create a new weather display layer based on the basic line layer to display the real-time temperature, sunny and rainy conditions, humidity and current wind speed, etc. The actual weather conditions, the temperature forecast for the next 3 hours or the day, and the predicted weather conditions are displayed at intervals of hours according to the time dimensions of "hour, week, month". According to different weather conditions, the corresponding weather icons are used. In the event of severe weather events, an alarm is automatically triggered, and the rail line section within the outline of the district and county-level administrative area where the warning exists is highlighted, and the details of the warning can be viewed;

[0087] Secondly, the collision treatment of the color band in the overlapping area of ​​the track line and the meteorological information drawing unit

[0088] When displaying weather information based on the rail transit line layer in the electronic map, the weather information of the city grid is used as the weather information of the rail grid area and as the basis for judging weather warnings. Figure 3 , corresponding to the division of meteorological information in the track grid area. The temperature within a certain range along the line is displayed in a color band manner. With the temperature changing from low to high, the color is defined to gradually change from blue to red. The higher the temperature, the redder the color. Blue indicates low temperature and red indicates high temperature. The five colors of blue, green, yellow, orange and red are used as color temperature identifiers, and the transition area is displayed in gradient colors. In the track grid area under the urban grid, the track line is divided into multiple irregular lines. However, due to the irregularity of the linear direction of the track line due to the geographical location, when the track arc is located at different grids, different colors overlap and composite colors appear, such as yellow and blue superimposed to appear green, instead of presenting a gradient color. This is called the "color collision" problem and needs to be refined. The present application proposes a "variable rectangular unit drawing method" to infinitely minimize the color band of the collision area based on the minimum rectangle, thereby shielding the effect of superimposed color change. There are straight line segments and curve segments. Taking a typical curve segment as an example, such as Figure 4 .

[0089] The coordinate starting point of the center line of the up line of the i-th line in the track grid is A1 (X1 (i), Y0), the coordinate starting point of the center line of the down line is A2 (X2 (i), Y0), the coordinate end point of the center line of the up line is B1 (X0, Y1 (i)), and the coordinate end point of the center line of the down line is B2 (X0, Y2 (i)). The traditional color band marking method along the line is mostly used to express the density of aggregation. It adopts the method of drawing a circular area with the center point as the center and the width of the color band coverage area as the diameter. However, since the meteorological data is the average of the measurement points in grid units, it does not belong to the relationship of aggregation density. Therefore, if it is drawn according to this method, there will be color collision problems in the overlapping areas covered by multiple circles, resulting in the inability to display the gradient color of the original color temperature value normally, but showing the superimposed color of two colors, and there are some areas along the line that cannot cover the weather information, such as Figure 5 Therefore, the "variable rectangular unit drawing method" is designed. The principle is as follows Figure 6 .

[0090] Define the unit ribbon rectangle R, length R l Adjustable, R l The default value is not less than 3m. When Y2(i)-Y1(i)=0, R l ≥(X2(i)-X1(i)); when X2(i)-X1(i)=0, R l ≥(Y2(i)-Y1(i)); width R w The default value is 0.5m and can be adjusted. According to the center point of the line where the color strip is currently drawn, the inclination angle of the line direction is defined as α. The unit color strip rectangle is perpendicular to the line, and its inclination angle is Should meet When α=0°orα=180°, the line type is vertical and the color ribbon rectangle is drawn horizontally; when α=90°, the color ribbon rectangle is drawn vertically; when 0°<α<90°or90°<α<v180°, the unit color ribbon rectangle has an inclination, and its center point should be located on the center line of the track line. The step length of the unit color ribbon drawing is R w If overlap occurs, the width of the unit color ribbon rectangle is halved, that is, R w / 2, then the step length of drawing is R w / 2. If overlap still occurs, it is halved again, and the algorithm is iterated successively, t=t+1, until there is no overlap, a rectangle is drawn according to the calculated width, and this algorithm is repeated.

[0091] Finally, the deduction of weather forecast based on the time axis. Draw a time axis below the map, click on the time node, set the weather warning layer (temperature, precipitation, wind speed), and display the weather forecast value within the next 24 hours of the day according to the weather forecast value and the time node value of the time axis, with the hour as the time axis unit node, consistent with the forecast period, and display the temperature and meteorological changes in the form of a color band cloud map to form a deduction effect of weather forecast.

[0092] S2: Determine a second target area in the first target area that has a risk of disastrous weather based on the weather status data of the first target area.

[0093] In an optional embodiment of the present application, the disaster weather is severe weather, including heavy rain, heavy snow, strong wind, heavy fog, sandstorm, high temperature, lightning, hail, frost, cold wave, haze, etc.

[0094] S3, determining the correlation and strength of the rail transit network operation safety factors of the second target area according to the rail transit network operation safety factors of the second target area, wherein the rail transit network operation safety factors include infrastructure, equipment system, risk sources and passenger flow.

[0095] In an optional embodiment of the present application, in the above step S3, determining the correlation relationship and strength of the rail transit network operation safety factors of the second target area according to the rail transit network operation safety factors of the second target area includes:

[0096] Obtain the attributes and features N of the infrastructure in the second target area, N = {O i , T i , γ i}, where O i = {0, 1}, if the second target area track grid belongs to the uplink section of the traffic line section range, then O i =0, it belongs to the downward interval, then O i =1; T i = {0, 1}, if the second target area track grid belongs to the station range and is a ground station, then T i =0, if it is an underground station T i =1;γ i = {1, 2, 3}, the reliability level is divided into level 1, level 2, and level 3 from low to high according to the degree of weather impact on the infrastructure, the configuration of supporting rescue resources, and the convenience of obtaining them;

[0097] Obtain the fault alarm information E of the equipment system in the second target area, E={F i , Y i , L i}, F i= {1, 2}, if there is an alarm of equipment system affected by weather in the second target area, then the alarm type F i =1; if there is no equipment system alarm affected by weather in the second target area, the alarm type F i =2; if the fault alarm does not affect traffic operations, then Y i =0; if the fault alarm affects traffic operations, then Y i =1; Alarm level L i ={1, 2, 3}, the alarm level is divided into three levels from low to high;

[0098] Get the risk source information R of the second target area i , R i ={1, 2, 3}, R i =1 means the risk level of the dangerous source affected by weather in the second target area is below medium, R i =2 means the risk level is above moderate, R i =3 means the risk level is a major risk;

[0099] Get the passenger flow information P of the second target area, P = {S i , V i},S i =0 means the weather impact time and space range of the second target area is at the station, S i =1 means the weather influence time and space range is within the interval; V i represents the impact of passenger flow, V i ={I, II, III, IV}, set thresholds as warning levels according to the size of passenger flow, from low to high corresponding to IV warning, III warning, II warning, I warning, among which the threshold of passenger flow can be customized according to the average daily passenger flow of different cities;

[0100] The rail transit network operation safety factors G={N, E, R, P} of the second target area are gathered, and the influencing factors of each rail transit network operation safety factor are set as the weight of each rail transit network operation safety factor, so as to determine the correlation and intensity of the rail transit network operation safety elements of the second target area according to each rail transit network operation safety factor and its weight.

[0101] S4, construct a correlation view of the impact of disastrous weather and safety factors of rail transit network operation in the second target area, form a knowledge graph of disastrous weather impact, and based on the weather impact knowledge graph, combined with the correlation and intensity of rail transit network operation safety factors, comprehensively determine the level of the impact of disastrous weather on the rail transit network operation safety resilience assessment results to trigger a joint warning.

[0102] In an optional embodiment of the present application, in the above step S4, the construction of the association view of the impact of disaster weather and the safety factors of rail transit network operation in the second target area to form a knowledge graph of the impact of disaster weather includes:

[0103] Entities and relationships are defined, where entity element types at least include the second target area's transportation routes, stations, sections, units, departments, positions, weather, equipment, systems, risk hidden danger lists, passenger flow, response processing types and indicators; relationship types at least include the second target area's geographical location, disposal positions, affiliation, responsibility, warning, degree, cause and time series;

[0104] The entities and relationships in the data layer are associated and mapped according to the preset method of the pattern layer to obtain a knowledge graph of the impact of weather events on traffic operation safety. The pattern layer and data layer are constructed in a top-down and bottom-up manner respectively.

[0105] The semantic association relationship between emergency data is divided into association relationship at the spatiotemporal level and the correlation between data. Among them, the association relationship at the spatiotemporal level unifies the emergency data into the same measurement unit. According to the time span and spatial range of the target data, the time overlap and spatial overlap between the data sets represented by each factor are calculated. The correlation between data is determined by calculating the support and confidence, and the frequent data item sets that appear simultaneously in the operational emergency data set caused by disaster weather are determined. The association rules between data are mined, the potential connections between hidden data are determined, and the optimized knowledge graph is obtained as the weather impact knowledge graph.

[0106] In an optional embodiment of the present application, entities and relationships in the data layer are associated and mapped according to the preset method of the mode layer, including:

[0107] The five-tuple KN={W, A, D, O, I} is defined to represent the five themes of severe weather type (W), emergency type (A), dispatching position (D), operation adjustment measures (O), and safety incident and processing information (I). The entity element types are classified according to the five-tuple and their correlation is mapped through relationships. The W data set includes natural disasters, public health, social security, large passenger flow, and various professional equipment system failures; the D data set includes positions such as driving dispatch, power dispatch, equipment dispatch, information dispatch, and maintenance dispatch; the O data set includes driving, equipment, passenger flow, customer service, stations, and external collaboration; the data set includes various types of information related to the event, such as event conditions, plans, emergency materials, and disposal measures. The relationship types between entities are summarized as: responsible, caused, included, subordinate, and disposal position.

[0108] In an optional embodiment of the present application, according to a certain severe weather event as a trigger, the entity elements and relationships are pointed to each other with arrows to form a knowledge graph diagram. The constructed knowledge graph can store the extracted entities and relationships, and visually represent the "node-relationship-node" triple knowledge.

[0109] In an optional embodiment of the present application, the association strength coefficient of the entity elements is determined according to the degree of association between the entity elements:

[0110] θ=X(k)×δ / Σ x∈{N，E，R，P} X(k),θ∈[0,1]

[0111] Among them, θ is the correlation strength coefficient of the entity element, X(k) is the correlation strength of the kth entity element in the knowledge graph, that is, the cumulative number of associations, and δ is the weight of a factor in infrastructure, equipment system, risk source and passenger flow. According to the correlation strength network of each element in the knowledge graph, the four types of elements are ranked in echelons according to the correlation strength. Among them, in order to absorb the knowledge of the emergency case library and optimize the knowledge graph, by absorbing the prior knowledge under similar events, the elements of the association relationship in the acquired knowledge graph are further compared with the target cases of the emergency case library, and the deconstruction and data set transformation of the four types of entity elements in the case events are extracted, such as flood control events caused by heavy rain weather, infrastructure class N is lines, sections, stations, etc.; equipment system E will be the same as the environmental control system, risk hidden danger class R according to the geographical environment of the corresponding location and the risk list record hidden danger situation calibrate the risk level, passenger flow P is based on the passenger flow situation in the same period of working days / non-working days / holidays as a reference. Filter the main influencing factors in the case, and filter out the factors that are not available in the generated knowledge graph in the same scenario, add them to the existing data set, and merge them into the subsequent data set according to the echelon series, and assign the correlation strength coefficient to a single correlation degree, so as to include the possible influencing factors extracted from the case, thereby further optimizing the optimized knowledge graph.

[0112] In an optional embodiment of the present application, in the above step S4, based on the weather impact knowledge graph, combined with the correlation relationship and intensity of the rail transit network operation safety elements, the level of the disaster weather on the rail transit network operation safety resilience assessment result is comprehensively determined to trigger a joint warning, including:

[0113] According to the influence intensity of the correlation intensity coefficient of the entity elements, the F(θ, KN(), t) data set is sorted, and the data set ranked first is output. When the result data set of F(θ, KN(), t) contains elements that affect train operation, Tr=1, otherwise it is 0; when it contains elements that affect the passenger service level, Ps=1, otherwise it is 0; when it contains elements that damage the infrastructure or equipment system and affect the operation, Da=1, otherwise it is 0; when it contains elements that cause losses due to equipment system failures, Ls=1, otherwise it is 0; where F(θ, KN(), t) is the composition of the regional risk influencing elements of urban rail under the influence of the corresponding correlation intensity θ of each entity element X in the five-tuple KN data set under the influence of the current severe weather over a certain time range t;

[0114] Based on the calculation of the impact of the dataset of influencing factors in the knowledge graph on resilience and the reliability of its impact intensity B, combined with the weather warning status of the current track grid, the comprehensive evaluation value of the safety resilience assessment is calculated as the result of the joint warning, expressed as B∩PH R(i) , where B is defined as (δ t Tr+δ p Ps+δ d Da+δ l Ls) represents the comprehensive reliability, where train operation Tr, passenger service level Ps, track system Da, casualties and losses Ls correspond to the reliability impact of four indicators respectively, δ t , δ p , δ d and δ l Respectively represent the weight coefficients of the corresponding indicators, PH R(i) Indicates the weather warning for the area where the i-th track line segment in the track grid is located; when PH R(i) =1 indicates that there is a weather warning in this section. R(i) =0 means no weather warning; when a weather warning occurs, a joint safety warning is issued; when no weather warning occurs but B≠0, only a weather risk warning is issued;

[0115] The result of the joint warning is marked as the resilience assessment value under the influence of the current severe weather, and used as the basis for the warning level. Three levels are set, and the resilience level decreases in turn, and the corresponding three-level warning is issued;

[0116] The above calibration process is iterated to traverse the track line segment in each track grid until the calibration of the warning information is completed.

[0117] In an optional embodiment of the present application, in the above step S3, before determining the rail transit network operation safety factor association relationship and its strength in the second target area according to the rail transit network operation safety factor in the second target area, the method further includes:

[0118] The safety and reliability of rail transit network operation are characterized by resilience. In order to express various factors affecting resilience in a unified dimension, the multivariate data is normalized and expressed in a unified way, and multiple types of warning information are integrated and analyzed. The indicators are calculated and evaluated for resilience in qualitative and quantitative ways. The main factors affecting resilience can be summarized into four categories: attribute characteristics of infrastructure, equipment system reliability, risk distribution, and passenger flow.

[0119] First, the data structure should be normalized, and unified data standards should be followed in data integration and data sharing to provide a unified standard data interface for comprehensive early warning analysis.

[0120] The key information extraction table of the infrastructure table is Table 1 below.

[0121] Table 1

[0122]

[0123] The equipment failure attributes and details are shown in Table 2 below.

[0124] Table 2

[0125]

[0126]

[0127] The data structure of the warning information table is shown in Table 3 below.

[0128] Table 3

[0129]

[0130]

[0131] The relationship between data table normalization and standardized data structure: The three main types of data tables are based on infrastructure indexes to achieve the optimal analysis plan for fault alarms and severe weather warning results based on the location and time factors of the infrastructure.

[0132] Secondly, the resilience assessment of rail transit weather impact

[0133] Due to the different degrees of weather impact, combined with the rail transit system and its safety factors, the resilience of the rail transit system under the influence of weather factors is judged. The design mainly focuses on the relevant elements of the infrastructure, the reliability changes of the equipment system, the risk situation of the time and space location, and the passenger flow.

[0134] Among them, the attributes and characteristics of infrastructure are as follows:

[0135] Focusing on the lines, sections and stations in the road network area affected by severe weather, the sections are located in the up / down direction, the station type is ground station / underground station, etc., and the degree of weather impact is judged according to the specific conditions of the infrastructure. Different station types are divided, and different levels of warnings are given to stations and sections that may be affected. For directly affected stations, the influencing factors also include the available rescue supplies, municipal drainage, and flood control related knowledge base resource retrieval content, and the equipment, quantity, and adjustment methods that may be used in conjunction with the relevant stations can be obtained. The above and the infrastructure attributes and their operation conditions are all used as one of the factors for resilience assessment. Define N = {O i , T i , γ i}, where O i ={0, 1}, if the track grid belongs to the line section, the up section is O i =0, the downward interval is O i =1; where T i = {0, 1}, if the track grid belongs to the station area, if it is an above-ground station, then T i =0, if it is an underground station T i =1;γ i ={1, 2, 3}. The reliability level is divided into three levels from low to high: level one, level two, and level three, according to the degree of weather impact, the configuration of supporting rescue resources, and the convenience of obtaining them.

[0136] The reliability of the equipment system is as follows:

[0137] According to the fault alarm of the equipment or system of the professional monitoring system in the track grid where the current weather-affected area is located, the analysis results of the equipment impact are used as one of the factors for judging resilience. Under the influence of severe weather, whether the current track grid contains the impact range of subway facilities and equipment, whether there is an alarm, according to the type of severe weather, the type of equipment that may be affected, the location, supporting protection measures, and data acquisition of monitoring methods, the degree of interference of the main equipment to the entire system, and the level of emergency warning information issued to the affected area. Define E = {F i , Y i , L i}, where F i = {1, 2}, if there is a weather-affected device alarm within the track grid, the alarm type F i =1; if there is no system alarm affected by weather within the track grid, the alarm type F i =2; if the fault alarm does not affect the operation, then Y i =0; if the fault alarm affects the operation, then Y i =1; define the alarm level L according to the alarm level and security level i={1, 2, 3}, the alarm level is divided into three levels from low to high.

[0138] The risks are as follows:

[0139] According to the relevant hazard source management measures for rail transit operating lines, operating companies are listed as the main target objects for hazard source identification and risk assessment. When they exist within the rail grid, this factor should also be used as one of the elements of resilience assessment. Production safety accident hazards are divided into general accident hazards and major accident hazards. General accident hazards refer to hazards that are not very dangerous and can be immediately rectified and eliminated after discovery. Major accident hazards refer to hazards that are highly dangerous, difficult to rectify after discovery, and need to be included in the treatment plan or partially suspended for treatment, as well as hazards that are difficult to rectify by the company's own strength due to external factors. Under the influence of severe weather, for the hazards and risks on the risk list within the assessed line section, a risk impact level is defined, R i ={1, 2, 3}, when R i =1 means the risk level is below moderate. i =2 means the risk level is above medium. i =3 means the risk level is a major risk.

[0140] The impact on passenger flow is as follows:

[0141] For the line sections or stations in the area affected by severe weather, short-term passenger flow forecast analysis is carried out based on the in-and-out passenger flow data and the section passenger flow data. The passenger flow changes affected by the area and the possibility of other related areas of the road network being affected will have an impact on passenger transportation organization. Therefore, passenger flow is also considered as one of the influencing factors of resilience assessment. Definition P = {S i , V i}, where S i =0 means the weather influence time and space range is at the station, S i =1 means in the interval; V i represents the impact of passenger flow, V i ={I, II, III, IV}, set the threshold as the warning range according to the size of the passenger flow, and divide it into four levels, corresponding to level IV warning, level III warning, level II warning, and level I warning respectively. The threshold of passenger flow can be customized according to the average daily passenger flow in different cities.

[0142] Finally, resilience assessment under severe weather conditions

[0143] Under the influence of severe weather, the four factors of infrastructure, equipment system reliability, risk source distribution, and passenger flow are unified in the standardized data format to achieve the correspondence between the integrity of business knowledge expression and data structure. The resilience assessment is expressed as a quaternion: G = {N, E, R, P}, and the impact factor δ is set as the weight of each influencing factor. Since different regions are affected by different types of severe weather to different degrees, the importance of the four types of factors in different ranges of the network varies, which can be flexibly adjusted by setting the impact factor.

[0144] Among them, the knowledge expression and relationship inference of the influencing factors are as follows:

[0145] Based on the mutual relationship between the four types of elements in the time and space scope of the track grid, the association and triggering rules between severe weather and the knowledge graph are established. Since emergencies occurring in severe weather are often not single events, there are multiple related types of events that occur and develop in association. The spatial regions where events occur also have certain characteristics, and the types of events that occur more frequently in different spatial locations are also different. Therefore, in severe weather, the types and locations of events, infrastructure characteristics, whether the equipment system is in a faulty state, whether there are risk areas, and whether the dynamic changes in passenger flow cause the weather to impose a huge load on operations. The relationship between these implicit knowledge structures is complex. The implicit association between emergency event types and spatial locations is mined from historical data, and the deductive severity and spatial association of event types facing different severe weather conditions are inferred as a comprehensive impact analysis for resilience assessment.

[0146] The construction process of the knowledge graph is as follows:

[0147] It mainly includes equipment failure ontology structure definition, knowledge extraction and knowledge alignment. Take equipment system failure as an example. Based on the failure of the rail transit system caused by severe weather events, the ontology structure of equipment failure is first defined. Through a comprehensive analysis of the structured and unstructured data of equipment failure, the knowledge units, knowledge unit relationships and knowledge hierarchical structures of equipment failure are defined, and the equipment failure data is orderly organized into a knowledge graph structure. Secondly, based on the ontology structure of equipment failure, the knowledge of equipment failure is extracted. For the unstructured text data of equipment failure stored in the subjective description data of equipment failure, the equipment phenomenon, the measures taken for the equipment phenomenon, and the processing results of the equipment failure are defined as named entities. The relationships such as cause, occurrence, and result between entities are taken as entity relationships. The methods of named entity recognition and entity relationship extraction are used to obtain the knowledge in the text. Finally, the knowledge of equipment failure is aligned. Due to the randomness of the subjective description data of equipment failure, the descriptions of the same equipment, fault phenomenon, and processing measures are different, which may lead to a large amount of knowledge duplication in the extracted knowledge. For example, "turnout loses representation" and "turnout has no representation" are actually the same equipment failure phenomenon. The knowledge alignment technology is used to solve the problem of equipment failure knowledge redundancy. The knowledge alignment process can effectively refine the equipment failure knowledge graph.

[0148] The entity relationships related to severe weather events are defined as follows:

[0149] A knowledge framework is constructed for the entity relationship between the impact of severe weather and resilience-related influencing factors. The data layer construction is to select appropriate methods to extract entities and relationships from weather event knowledge. The knowledge of resilience impact is analyzed and the entities and relationships are defined. The entity element types mainly include: lines, stations, sections, units, departments, positions, weather, equipment, systems, risk hidden danger lists, passenger flow, response processing types, important indicators, etc. Relationship types: geographical location within the network range, disposal positions, affiliation, responsibility, warning, degree, cause, time series, etc.

[0150] Again, knowledge extraction

[0151] The entities and relationships in the data layer are associated and mapped according to the preset method of the pattern layer, so as to obtain the knowledge graph of the impact of weather events on operational resilience. The pattern layer and data layer are constructed in a top-down and bottom-up manner respectively.

[0152] The knowledge extraction model is still based on Bert's "half-pointer-half-annotation" approach for extraction.

[0153] Finally, the correlation between elements is explored and integrated with joint warning knowledge.

[0154] Due to the complexity of the elements of rail transit operations affected by severe weather, it is necessary to refine the knowledge graph of equipment failures. The semantic association relationship between emergency data is divided into the association relationship at the spatiotemporal level and the correlation between data. The spatiotemporal semantic relationship calculation unifies the description of emergency data in terms of location, scope, date, etc. to the same measurement unit, and calculates the time overlap and spatial overlap between the data sets represented by each element according to the time span and spatial scope of the target data. The data association calculation adopts the association analysis algorithm. Through the calculation of support and confidence, it finds the frequent data item sets that often appear simultaneously in the operational emergency data set caused by severe weather, mines the association rules between data, and discovers the potential connections in the actual application of hidden data.

[0155] Furthermore, the impact of severe weather on resilience assessment is defined as three levels, namely G i ={low, medium, high}. According to the operational impact event data caused by severe weather within a certain period, the same type of severe weather that has a significant impact on the same line, section or station is marked as high, and the knowledge reasoning of weather impact is marked as low if there is no obvious correlation. According to the degree of weather impact and the results of knowledge reasoning data analysis of historical events, the impact level of severe weather on resilience assessment is calibrated, and a joint warning is issued in the corresponding line network area. Among them, the resilience assessment process is based on the Monte Carlo method and the probability of association of knowledge graphs. A severe weather event is used as a trigger condition, and one or more variable factors in the four types of elements of infrastructure, equipment system, risk source, and passenger flow are used as random variables. The specific area of ​​the selected rail transit area, such as the station and section, is used as the target area to simulate the reliability of rail transit operation under the influence of uncertainty of multiple factors. The factor influence coefficient output by the knowledge graph is used as the intervention condition. The higher the impact correlation and the more associated element entities, the greater the impact on resilience. The impact degree and warning level of the four types of factors are used as the input of resilience assessment, and resilience assessment indicators are established to quantify the safety and reliability of the corresponding station area of ​​urban rail transit from four aspects: "whether it affects train operation, whether it reduces the level of passenger service, whether it causes damage to the rail system and its degree, and whether it causes casualties and major economic losses." The overall operational risk impact data set F of severe weather on urban rail safety is expressed as F(θ, KN(), t), which is the regional risk impact factor composition of urban rail under the influence of the corresponding correlation strength θ of each entity element X in the five-tuple KN data set under the influence of the current severe weather over a certain time range t. Define B = (δ t Tr+δ p Ps+δ d Da+δ lLs) represents the comprehensive reliability, where train operation Tr, passenger service level Ps, track system Da, casualties and losses Ls correspond to the reliability influence of the four indicators respectively, and δ represents the weight coefficient of the corresponding indicator. The entropy weight method is used to determine the subjective and objective weight coefficients of the four indicators of δ. Furthermore, according to the influence intensity of the association intensity coefficient of the entity element, the F data set is sorted, and the data set ranked first is output. When the result data set of F contains factors that affect train operation, Tr=1, otherwise it is 0; when it contains factors that affect passenger service level, Ps=1, otherwise it is 0; when it contains factors that damage the infrastructure or equipment system and affect operation, Da=1, otherwise it is 0; when it contains factors that cause losses due to equipment system failures, Ls=1, otherwise it is 0. Based on the calculation of the impact of the data set of influencing factors on resilience in the knowledge graph and the reliability B of its influence intensity, combined with the weather warning status of the current track grid, the comprehensive evaluation value of the safety resilience assessment is calculated as the result of the joint warning, expressed as B∩PH R(i) , where PH R(i) Indicates the weather warning for the area where the i-th track line segment in the track grid is located. R(i) =1 indicates that there is a weather warning in this section. R(i) =0 means no weather warning. When a weather warning occurs, a joint safety warning is issued. When there is no weather warning but B≠0, only a weather risk warning is issued. In addition, the results of the comprehensive safety resilience assessment are marked with the resilience assessment value under the influence of the current severe weather, and used as the basis for the warning level. Three levels are set, and the resilience level decreases in sequence, corresponding to the issuance of three levels of warning. The above calibration process is iterated, traversing the track line segment in each track grid until the calibration of the warning information is completed.

[0156] The traffic safety warning method of this application integrates real-time meteorological, geographic information and equipment status, provides refined weather warnings and grid monitoring, evaluates line safety, and supports emergency decision-making. Grid weather forecast and risk warning technology is used to update weather information in real time, identify key areas, and construct a precise monitoring method for severe weather that is suitable for local conditions of rail transit lines. Weather analysis and emergency warnings at different spatial and temporal granularities are achieved, and timely security and rectification measures are organized to reduce the damage that sudden severe weather may cause to rail transit operations. By constructing a method for identifying key protection areas of lines for severe weather and a graded assessment of operational resilience, we can find the main disaster-causing hidden dangers and key targets for pre-emptive prevention and control, explore the identification methods and laws of line areas that cause major weather disasters, form targeted protection strategies, enhance the operational safety and emergency response capabilities of rail transit in severe weather, and improve operational safety in severe weather.

[0157] The traffic safety warning method of this application integrates urban meteorological data, electronic maps and rail line information to build a dynamic weather monitoring system along the line and station areas. Combined with weather forecasts, it uses the timeline synchronization method to achieve regional weather assessment, design a graded warning mechanism, and use data fusion and knowledge graph technology to evaluate rail transit resilience, determine targeted weather warnings, and improve safety prevention and control capabilities. Custom configuration is used to flexibly adapt to different rail transit network structures and improve the efficiency of multi-dimensional data fusion. Using weather forecast results, analyze the impact of severe weather on operations, quickly form emergency strategy recommendations, dynamically adjust emergency responses, provide scientific decision-making support for operations and scheduling, and reduce the impact and losses of natural disasters on operations.

[0158] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0159] See also Figure 7 , an embodiment of the present application provides a traffic safety warning device, including:

[0160] The superposition model 11 is used to superimpose the known weather monitoring network and the rail transit network to display the weather status data of the first target area after superposition, wherein the first target area is determined based on the rail transit lines in the rail transit network;

[0161] A first determination module 12 is used to determine a second target area with a disaster weather risk in the first target area according to the weather status data of the first target area;

[0162] A second determination module 13 is used to determine the correlation relationship and strength of the rail transit network operation safety factors of the second target area according to the rail transit network operation safety factors of the second target area, wherein the rail transit network operation safety factors include infrastructure, equipment system, risk source and passenger flow;

[0163] Construction module 14 is used to construct a correlation view of the impact of disaster weather and safety factors of rail transit network operation in the second target area, form a knowledge graph of disaster weather impact, and based on the weather impact knowledge graph, combined with the correlation and intensity of rail transit network operation safety factors, comprehensively determine the level of disaster weather on rail transit network operation safety resilience assessment results to trigger a joint warning.

[0164] The traffic safety warning device of the present application also includes:

[0165] Data source acquisition interface and management module: including electronic map data, urban meteorological measurement point grids, rail grids, dynamic meteorological monitoring data; data source data for resilience assessment, data extraction of fault alarms of various monitoring systems such as infrastructure, traffic signal systems, power supply systems, and electromechanical equipment monitoring systems, risk hidden danger business data, real-time passenger flow and forecasted volume, and ensuring the data quality of input computing service systems through data cleaning and governance;

[0166] Real-time dynamic weather visualization: Track lines are marked in a grid format with color bands consistent with meteorological data.

[0167] Severe weather simulation module: Based on the timeline, severe weather and its forecast for meteorology are displayed in hours to show the effect of changes and form trend simulation;

[0168] Resilience assessment decision support module: Based on various statistical analysis queries such as infrastructure in a certain area according to weather forecasts, equipment system fault alarm data, key objects for risk source identification, passenger flow in relevant areas or stations, etc., the resilience assessment results are formed through interactive setting of parameters such as accounting and influencing factors;

[0169] Joint warning derivation and release module: Input the current severe weather event type, generate a knowledge graph, store the extracted entities and relationships, and visualize the "node-relationship-node" triple knowledge, which has the characteristics of good visualization and efficient search. Through query statements, find the knowledge nodes and relationships where the constituent relationships of each influencing factor related to resilience are located, and infer the joint warning results according to the resilience assessment classification principle.

[0170] In summary, based on the disturbance impact on rail transit stations, lines, and networks under the influence of severe weather, combined with meteorological monitoring and forecast data, the resilience indicators before, during, and after severe weather are calculated, the impact on driving safety is analyzed, and the resilience results are output. This can also serve as a technical system to avoid disasters and reduce the scope of disaster impact.

[0171] The traffic safety warning device of this application performs real-time calculation and warning analysis, allowing users to retrieve data and input parameters, adopt grid monitoring, and simultaneously push weather warnings in the rail area to achieve data sharing. By integrating electronic maps with line information, it provides accurate display of weather information for irregular lines. Further evaluate key factors such as infrastructure, equipment status, risks, and passenger flow, build a knowledge graph, and accurately judge operational safety resilience, ensuring applicability to different scenarios and scientific decision-making.

[0172] The traffic safety warning device of this application integrates severe weather warning information, optimizes the resilience assessment of the track area, issues joint warnings for low-resilience areas, and supports severe weather response decisions. Combined with meteorological monitoring, accurate warning and intuitive display of rail transit meteorological information can be achieved, assisting operators to quickly locate key prevention and control areas and respond in advance. Further use of big data and intelligent analysis can identify important factors and correlations that affect the resilience of rail transit in severe weather, assess the degree of impact, provide targeted warnings, reduce the uncertainty of manual inspections, fully grasp the safety of the line network, support local area weather disaster response, and provide strong support for refined management.

[0173] For the specific definition of the above-mentioned traffic safety warning device, please refer to the definition of the traffic safety warning method above, which will not be repeated here. Each module in the above-mentioned traffic safety warning device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0174] In one embodiment, a computer device is provided, the internal structure diagram of which can be as follows: Figure 8 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a traffic safety warning method as described above is implemented. It includes: a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, any step in the traffic safety warning method as described above is implemented.

[0175] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any step in the above traffic safety warning method can be implemented.

[0176] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0177] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0178] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0179] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0180] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0181] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A traffic safety early warning method, characterized in that: include: Overlaying a known weather monitoring network and a rail transit network, and displaying weather status data of a first target area after the overlay, wherein the first target area is determined based on a rail transit line in the rail transit network; Determine, based on the weather status data of the first target area, a second target area having a disaster weather risk in the first target area; Determine the correlation relationship and strength of the rail transit network operation safety factors of the second target area according to the rail transit network operation safety factors of the second target area, wherein the rail transit network operation safety factors include infrastructure, equipment system, risk source and passenger flow; Construct a correlation view of the impact of disastrous weather and safety factors of rail transit network operation in the second target area, form a knowledge graph of disastrous weather impact, and based on the weather impact knowledge graph, combine the correlation and intensity of rail transit network operation safety factors, comprehensively determine the level of the impact of disastrous weather on the rail transit network operation safety resilience assessment results, so as to trigger a joint warning.

2. The method according to claim 1, characterized in that The superposition of the known weather monitoring network and rail transit network includes: The grid cells within a preset range where the rail transit lines in the known rail transit network are located are defined as rail grids; Overlaying a known weather monitoring network with all orbital grids, wherein the weather monitoring network includes a plurality of weather grids; Determine weather status data of the track line in each track grid according to the overlap between the track grid and the weather grid; The first target area is the belt-shaped influence area centered on the center line of the track line with meteorological attributes in the track grid.

3. The method according to claim 2, characterized in that The step of determining the weather status data of the track line in each track grid according to the overlap between the track grid and the weather grid includes: For the rail lines in each rail grid, the actual weather conditions, weather forecasts and severe weather warnings of the city grid where the current rail line is located are represented as weather status data of the rail lines in each rail grid.

4. The method according to claim 3, characterized in that The displaying of weather status data of the first target area includes: A color band of the first target area in each track grid is drawn according to the weather status data of the first target area in each track grid, wherein: The color band of the first target area in each track grid is drawn by a variable rectangular unit. The length of the variable rectangular unit If two adjacent unit color strip rectangles overlap, the width of the unit color strip rectangle is halved until there is no overlap between the two adjacent unit color strip rectangles. X1(i) is the x-axis coordinate value of the starting point of the center line coordinate of the uplink line of the i-th line in the track grid, X2(i) is the x-axis coordinate value of the starting point of the center line coordinate of the downlink line, Y1(i) is the y-axis coordinate value of the end point of the center line coordinate of the uplink line, Y2(i) is the y-axis coordinate value of the end point of the center line coordinate of the downlink line, R l′ is the ribbon extension width, and R l′ >0.

5. The method according to claim 1, characterized in that The determining the correlation relationship and strength of the rail transit network operation safety factors of the second target area according to the rail transit network operation safety factors of the second target area includes: Obtain the attributes and features N of the infrastructure in the second target area, N = {O i , T i , γ i }, where O i = {0, 1}, if the second target area track grid belongs to the uplink section of the traffic line section range, then O i =0, it belongs to the downward interval, then O i =1; T i = {0, 1}, if the second target area track grid belongs to the station range and is a ground station, then T i =0, if it is an underground station T i =1;γ i = {1, 2, 3}, the reliability level is divided into level 1, level 2, and level 3 from low to high according to the degree of weather impact on the infrastructure, the configuration of supporting rescue resources, and the convenience of obtaining them; Obtain the fault alarm information E of the equipment system in the second target area, E={F i , Y i , L i }, F i = {1, 2}, if there is an alarm of equipment system affected by weather in the second target area, then the alarm type F i =1; if there is no equipment system alarm affected by weather in the second target area, the alarm type F i =2; if the fault alarm does not affect traffic operations, then Y i =0; if the fault alarm affects traffic operations, then Y i =1; Alarm level L i ={1, 2, 3}, the alarm level is divided into three levels from low to high; Get the risk source information R of the second target area i , R i ={1, 2, 3}, R i =1 means the risk level of the dangerous sources affected by weather in the second target area is below medium. i =2 means the risk level is above moderate, R i =3 means the risk level is a major risk; Get the passenger flow information P of the second target area, P = {S i , V i },S i =0 means the weather impact time and space range of the second target area is at the station, S i =1 means the weather influence time and space range is within the interval; V i represents the impact of passenger flow, V i ={I, II, III, IV}, set thresholds as warning levels according to the size of passenger flow, from low to high corresponding to IV warning, III warning, II warning, and I warning; The rail transit network operation safety factors G={N, E, R, P} of the second target area are gathered, and the influencing factors of each rail transit network operation safety factor are set as the weight of each rail transit network operation safety factor, so as to determine the correlation and intensity of the rail transit network operation safety elements of the second target area according to each rail transit network operation safety factor and its weight.

6. The method according to claim 1, characterized in that The construction of the association view of the impact of disaster weather and the safety factors of rail transit network operation in the second target area to form a knowledge graph of the impact of disaster weather includes: Entities and relationships are defined, where entity element types at least include the second target area's transportation routes, stations, sections, units, departments, positions, weather, equipment, systems, risk hidden danger lists, passenger flow, response processing types and indicators; relationship types at least include the second target area's geographical location, disposal positions, affiliation, responsibility, warning, degree, cause and time series; The entities and relationships in the data layer are associated and mapped according to the preset method of the pattern layer to obtain a knowledge graph of the impact of weather events on traffic operation safety. The pattern layer and data layer are constructed in a top-down and bottom-up manner respectively. The semantic association relationship between emergency data is divided into association relationship at the spatiotemporal level and the correlation between data. Among them, the association relationship at the spatiotemporal level unifies the emergency data into the same measurement unit. According to the time span and spatial range of the target data, the time overlap and spatial overlap between the data sets represented by each factor are calculated. The correlation between data is determined by calculating the support and confidence, and the frequent data item sets that appear simultaneously in the operational emergency data set caused by disaster weather are determined. The association rules between data are mined, the potential connections between hidden data are determined, and the optimized knowledge graph is obtained as the weather impact knowledge graph.

7. The method according to claim 6, characterized in that The method further comprises: The following expression is used to determine the association strength coefficient of the entity elements according to the degree of association between the entity elements: θ=X(k)×δ / ∑ x∈{N，E，R，P} X(k),θ∈[0,1] Among them, θ is the association strength coefficient of the entity element, X(k) is the association strength of the kth entity element in the knowledge graph, that is, the cumulative number of association relationships, and δ is the weight of one factor among infrastructure, equipment system, risk source and passenger flow.

8. The method according to claim 7, characterized in that Based on the weather impact knowledge graph, combined with the correlation and intensity of rail transit network operation safety factors, the level of disaster weather on the rail transit network operation safety resilience assessment results is comprehensively determined to trigger a joint warning, including: According to the influence intensity of the correlation intensity coefficient of the entity elements, the F(θ, KN(), t) data set is sorted, and the data set ranked first is output. When the result data set of F(θ, KN(), t) contains elements that affect train operation, Tr=1, otherwise it is 0; when it contains elements that affect the passenger service level, Ps=l, otherwise it is 0; when it contains elements that damage the infrastructure or equipment system and affect the operation, Da=1, otherwise it is 0; when it contains elements that cause losses due to equipment system failures, Ls=1, otherwise it is 0; where F(θ, KN(), t) is the composition of the regional risk influencing elements of urban rail under the influence of the corresponding correlation intensity θ of each entity element X in the five-tuple KN data set under the influence of the current severe weather over a certain time range t; Based on the calculation of the impact of the dataset of influencing factors in the knowledge graph on resilience and the reliability of its impact intensity B, combined with the weather warning status of the current track grid, the comprehensive evaluation value of the safety resilience assessment is calculated as the result of the joint warning, expressed as B∩PH R(i) , where B is defined as (δ t Tr+δ p Ps+δ d Da+δ l Ls) represents the comprehensive reliability, where train operation Tr, passenger service level Ps, track system Da, casualties and losses Ls correspond to the reliability impact of four indicators respectively, δ t , δ p , δ d and δ l Respectively represent the weight coefficients of the corresponding indicators, PH R(i) Indicates the weather warning for the area where the i-th track line segment in the track grid is located; when PH R(i) =1 indicates that there is a weather warning in this section. R(i) =0 means no weather warning; when a weather warning occurs, a joint safety warning is issued; when no weather warning occurs but B≠0, only a weather risk warning is issued; The result of the joint warning is marked as the resilience assessment value under the influence of the current severe weather, and used as the basis for the warning level. Three levels are set, and the resilience level decreases in turn, and the corresponding three-level warning is issued; The above calibration process is iterated to traverse the track line segment in each track grid until the calibration of the warning information is completed.

9. A traffic safety warning device, characterized in that: include: An overlay model is used to overlay a known weather monitoring network and a rail transit network to display weather status data of a first target area after overlay, wherein the first target area is determined based on a rail transit line in the rail transit network; A first determination module is used to determine a second target area with a disaster weather risk in the first target area according to the weather status data of the first target area; A second determination module is used to determine the correlation relationship and strength of the rail transit network operation safety factors of the second target area according to the rail transit network operation safety factors of the second target area, wherein the rail transit network operation safety factors include infrastructure, equipment system, risk source and passenger flow; A construction module is used to construct a correlation view of the impact of disaster weather and safety factors of rail transit network operation in the second target area, forming a knowledge graph of disaster weather impact. Based on the weather impact knowledge graph and combined with the correlation and intensity of rail transit network operation safety factors, the level of disaster weather on rail transit network operation safety resilience assessment results is comprehensively determined to trigger a joint warning.

10. A computer device comprising: It comprises a memory and a processor, wherein the memory stores a computer program, and is characterized in that the processor implements the steps of the traffic safety warning method according to any one of claims 1 to 8 when executing the computer program.

Images