Vehicle-mounted multi-level disaster prevention early warning method and system based on Beidou communication

Abstract

The invention belongs to the technical field of vehicle-mounted disaster prevention and early warning, and discloses a vehicle-mounted multistage disaster prevention and early warning method and system based on Beidou communication, and the method comprises the steps: obtaining vehicle position information and prediction path information, and determining a vehicle driving region; acquiring a detailed geographic information system data packet from a data service platform according to the vehicle driving area; according to the detailed geographic information system data packet, the current vehicle speed and the vehicle position information, the probability of occurrence of different types of natural disasters in the vehicle driving area and the degree of influence on vehicle safety are calculated, and a risk assessment result is obtained; according to a risk assessment result, carrying out risk grade division on the natural disaster risk; determining an early warning information presentation mode according to the risk level, the disaster type and the driver state, and generating and presenting early warning information according to the corresponding presentation mode; therefore, more accurate and more targeted natural disaster early warning can be provided, and the safety of vehicle driving is improved.

Description

Technical Field

[0001] This application relates to the technical field of on-vehicle disaster prevention and warning, and more specifically, to an on-vehicle multi-level disaster prevention and warning method and system based on Beidou communication. Background Art

[0002] When a vehicle is traveling on the road, the on-vehicle system usually relies on the Beidou satellite navigation system to obtain the vehicle's real-time position, speed, and heading information, and combines it with the basic geographic information system (GIS) data stored in the vehicle for positioning and navigation. However, in areas prone to natural disasters, relying solely on basic GIS data is not sufficient to cope with potential risks. Therefore, the system usually needs to obtain more detailed geographic information system data, including high-precision terrain, detailed geological structures, fine water system distributions, and historical disaster point records. In addition, for natural disaster warnings, real-time environmental monitoring data is crucial. These data come from meteorological, water conservancy, transportation departments, and the Internet of Things sensor network, providing key monitoring data such as real-time rainfall intensity, river water level, road water accumulation depth, slope soil moisture content, and mountain displacement.

[0003] When the on-vehicle system conducts risk assessment, it needs to be based on this data. The goal of risk assessment is to determine the types and severity of natural disaster risks that may exist at the vehicle's current position and the forward path. The assessment process needs to consider multiple factors. However, due to the superposition of multiple influencing factors and multiple risk types, accurately conducting risk assessment faces significant challenges.

[0004] After the risk assessment is completed, warnings need to be issued according to the assessment results. The warning information is usually presented to the driver through the on-vehicle terminal, and its presentation method will significantly affect the driver's acceptance and response efficiency. If, when the driver is performing driving operations that require high attention, a highly interfering warning message suddenly pops up, it may distract the driver's attention and instead increase the driving risk. In addition, the existing system lacks the ability to perceive whether the driver receives, understands, and processes the warning information, and also lacks a mechanism to further increase the warning intensity or change the warning method when the driver fails to respond or responds inappropriately.

[0005] In view of the above problems, the existing technology urgently needs to be improved. Summary of the Invention

[0006] The purpose of this application is to provide an on-vehicle multi-level disaster prevention and warning method and system based on Beidou communication, which can provide more accurate and targeted natural disaster warnings and improve the safety of vehicle driving.

[0007] In a first aspect, this application provides an on-vehicle multi-level disaster prevention and warning method based on Beidou communication, which is used to warn of natural disaster risks during vehicle driving. The steps of this method include: A1. Obtain vehicle position information and predicted path information, and determine the vehicle driving area; A2. According to the vehicle driving area, obtain a detailed geographic information system data packet from the data service platform; the detailed geographic information system data packet includes meteorological information, hydrological information, and geological information of the vehicle driving area; A3. According to the detailed geographic information system data packet, the current vehicle speed, and the vehicle position information, calculate the probability of different types of natural disasters occurring in the vehicle driving area and the degree of impact on vehicle safety, and obtain a risk assessment result; A4. According to the risk assessment result, classify the natural disaster risk levels; A5. According to the risk level, disaster type, and driver status, determine the presentation method of the warning information, and generate and present the warning information according to the corresponding presentation method.

[0008] Preferably, step A1 includes: A101. Obtain vehicle position information through the in-vehicle Beidou positioning system; A102. Obtain destination information, current navigation path information, and historical driving route data from the vehicle navigation system; A103. According to the destination information, current navigation path information, historical driving route data, and the real-time route information of the vehicle, predict the future driving route of the vehicle to obtain predicted path information; the real-time route information is the route formed by connecting the vehicle positions within a preset time window before the current moment; A104. Adopt the buffer analysis method, with the current vehicle position as the center and the predicted path as the extension direction, to construct an initial buffer; A105. According to the road type, calculate the buffer radius increment to adjust the size of the initial buffer to obtain the vehicle driving area.

[0009] Preferably, step A103 includes: When both the destination information and the current navigation path information are not empty, through the Kalman filtering algorithm, fuse the current navigation path information and the real-time route information to predict the future driving route of the vehicle to obtain predicted path information; When both the destination information and the current navigation path information are empty, adopt the Markov model, according to the historical driving route data, predict the future vehicle driving trajectory, and use the predicted trajectory as the predicted path information.

[0010] Preferably, the A3 includes: A301. Obtain a pre-constructed disaster type correlation matrix; the disaster type correlation matrix represents the correlation probability between different types of natural disasters; A302. Extract meteorological information, hydrological information, and geological information within the vehicle's driving area from the detailed geographic information system data packet, and calculate the initial occurrence probabilities of various natural disasters based on historical disaster data; A303. According to the disaster type association matrix, use the weighted average algorithm to correct the initial occurrence probabilities of various natural disasters to obtain the associated and corrected disaster occurrence probabilities; A304. Calculate the distances between the vehicle and various risk sources based on the vehicle position information, and combine the road type and meteorological information to determine the impact factors of various natural disasters on vehicle safety using the fuzzy logic algorithm; A305. According to the associated and corrected disaster occurrence probabilities, the impact factors, and the current vehicle speed, calculate the comprehensive risk values of various natural disasters on the vehicle through the weighted summation algorithm as the risk assessment results.

[0011] Preferably, step A302 includes: Extract meteorological information, hydrological information, and geological information within the vehicle's driving area from the detailed geographic information system data packet; the meteorological information includes rainfall, wind speed, temperature, and humidity; the hydrological information includes water level, flow rate, flow velocity, and water quality; the geological information includes geological structure, rock and soil type, slope, and surface coverage information; According to the extracted meteorological information, hydrological information, and geological information, and combining historical disaster data, use the Bayesian network model to calculate the initial occurrence probabilities of landslides, floods, debris flows, and waterlogging within the vehicle's driving area; the historical disaster data includes the disaster type, occurrence time, geographical location, impact range, loss degree of historical disasters, as well as the corresponding meteorological information, hydrological information, and geological information.

[0012] Preferably, step A303 includes: For each natural disaster, calculate the influence weight of other disaster types on the occurrence probability of this natural disaster according to the disaster type association matrix and the preset association probability threshold; According to the initial occurrence probabilities and influence weights of various natural disasters, correct the occurrence probabilities of various natural disasters through the weighted average algorithm to obtain the associated and corrected disaster occurrence probabilities.

[0013] Preferably, step A305 includes: Determine the weight coefficients of various natural disasters according to the associated and corrected disaster occurrence probabilities; Query the speed - impact factor adjustment coefficient table according to the current vehicle speed to obtain the impact factor adjustment coefficient corresponding to the current vehicle speed; Calculate the adjusted impact factors of various natural disasters through multiplication according to the impact factors and the impact factor adjustment coefficients; According to the weight coefficient corresponding to the probability of disaster occurrence corrected by the association and the adjusted impact factor, calculate the comprehensive risk value of various natural disasters on the vehicle through the weighted summation algorithm as the risk assessment result.

[0014] Preferably, step A5 includes: A501. Obtain the facial image, eye movement data and vehicle operation data of the driver to evaluate the driver's state; the driver's state includes the fatigue level and the degree of distraction. A502. Determine the combination of the basic warning intensity and the presentation method according to the risk level; the presentation method combination includes at least one of the three methods of vision, audition and touch. A503. According to the driver's state, query the preset driver state-warning intensity adjustment coefficient table to obtain the corresponding warning intensity adjustment coefficient for adjusting the basic warning intensity to obtain the adjusted warning intensity. A504. Generate a warning message according to the adjusted warning intensity, the presentation method combination and the disaster type, and present the warning message according to the corresponding presentation method.

[0015] Preferably, after step A504, it further includes the step of: A505. Monitor the eye movement data and vehicle operation data of the driver to judge whether the driver responds to the warning message. If no response is detected within the preset time, increase the warning message presentation intensity and / or switch the presentation method until the driver makes a response.

[0016] In a second aspect, the present application provides an in-vehicle multi-level disaster prevention warning system based on Beidou communication for warning of natural disaster risks during vehicle driving. The system includes: A region determination module for obtaining vehicle position information and predicted path information to determine the vehicle driving region. A data acquisition module for obtaining a detailed geographic information system data packet from a data service platform according to the vehicle driving region; the detailed geographic information system data packet includes meteorological information, hydrological information and geological information of the vehicle driving region. A risk assessment module for calculating the probability of occurrence of different types of natural disasters in the vehicle driving region and the degree of impact on vehicle safety according to the detailed geographic information system data packet, the current vehicle speed and the vehicle position information to obtain a risk assessment result. A risk grading module for grading the natural disaster risk according to the risk assessment result. A warning module for determining the warning message presentation method according to the risk level, the disaster type and the driver's state, and generating and presenting the warning message according to the corresponding presentation method.

[0017] Beneficial effects: A vehicle multi-level disaster prevention and warning method and system based on Beidou communication provided by the present application can provide more accurate and targeted natural disaster warnings and improve the driving safety of vehicles by obtaining detailed GIS data, conducting risk assessments, and multi-level risk classification, compared with the prior art that only relies on basic GIS data and simple warnings. Description of the Drawings

[0018] Figure 1 It is a flowchart of the vehicle multi-level disaster prevention and warning method based on Beidou communication provided by the embodiment of the present application.

[0019] Figure 2 It is a schematic structural diagram of the vehicle multi-level disaster prevention and warning system based on Beidou communication provided by the embodiment of the present application.

[0020] Label description: 1. Region determination module; 2. Data acquisition module; 3. Risk assessment module; 4. Risk classification module; 5. Warning module. Detailed Embodiments

[0021] Next, the technical solutions in the present application will be clearly and completely described in conjunction with the drawings in the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Usually, the components of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application to be protected, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0022] It should be noted that: Similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of the present application, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0023] Reference Figure 1 , the present application proposes a vehicle multi-level disaster prevention and warning method based on Beidou communication, which is used to warn of natural disaster risks during vehicle driving. The steps of the method include: A1. Obtain the vehicle position information and predicted path information to determine the vehicle driving area; A2. According to the vehicle driving area, obtain a detailed geographic information system data packet (detailed GIS data packet) from the data service platform; the detailed geographic information system data packet includes meteorological information, hydrological information, and geological information of the vehicle driving area; A3. Calculate the probabilities of different types of natural disasters occurring within the vehicle's driving area and the degree of impact on vehicle safety based on the detailed geographic information system data packet, the vehicle's current speed, and the vehicle position information, to obtain a risk assessment result; A4. Classify the natural disaster risks according to the risk assessment result; A5. Determine the presentation method of the warning information based on the risk level, the type of disaster, and the driver's state, and generate and present the warning information according to the corresponding presentation method.

[0024] Among them, in step A1, by obtaining the vehicle's current geographic location information and predicting the vehicle's future driving trajectory, a geographic scope related to the vehicle's future driving is defined. The vehicle position information can be provided by a satellite positioning system, an inertial navigation system, or a vehicle odometer. The predicted path information can be obtained based on the planned route of the in-vehicle navigation system, historical driving data, or real-time trajectory analysis. The vehicle's driving area can be determined by methods such as buffer analysis, which is constructed based on the vehicle position or the predicted path. This feature is used to limit the scope of subsequent data acquisition and risk assessment, improving the processing efficiency.

[0025] Among them, in step A2, after determining the area where the vehicle may drive, the system obtains geographic data containing meteorological, hydrological, and geological information, etc. within this area from external data sources. These data are more refined and comprehensive than the basic geographic information. For example, they can include high-precision terrain data, detailed geological structure information, real-time rainfall data, and river water level data. This feature is used to provide environmental background information for subsequent risk assessment.

[0026] Among them, in step A3, by comprehensively using the obtained detailed environmental data (detailed geographic information system data packet) and the vehicle's own real-time status information (the vehicle's current speed and vehicle position information), the possibility of various natural disasters that may occur within the vehicle's driving area and the degree of impact that these disasters may cause to vehicle safety are evaluated through calculation methods. The calculation methods can adopt probability models, fuzzy logic algorithms, or weighted summation algorithms. This feature is used to quantify potential natural disaster risks.

[0027] Among them, in step A4, the quantified risk assessment result is mapped to several preset discrete levels, such as low risk, medium risk, and high risk; the risk level classification result can be obtained by querying the risk assessment result - risk level mapping table, which records the risk levels corresponding to different risk assessment result ranges. This feature is used to convert the risk assessment result into an identifier.

[0028] Among them, in step A5, according to the evaluated risk level, specific disaster types, and the judgment of the driver's current physiological or behavioral state, select the form (such as a combination of visual, auditory, and tactile) and intensity of the warning signal, generate the warning content, and send it to the driver. The driver's state may include the degree of fatigue and the degree of concentration. This feature is used to ensure that the warning information is effectively conveyed to the driver and to consider the driver's reception ability.

[0029] The core innovation of this application lies in combining the acquisition of detailed environmental data based on the predicted path with the risk assessment that combines the vehicle's own state, and dynamically adjusting the presentation method of the warning information according to the risk level, disaster type, and driver state, thereby solving the problems existing in data acquisition, risk assessment, and warning information transmission in the prior art and realizing in-vehicle disaster prevention warning.

[0030] Specifically, the method of this application first obtains the current geographical location information of the vehicle and predicts the future driving path of the vehicle, and determines a geographical area where the vehicle may drive based on this information. Then, the system obtains a detailed geographical information system data packet containing information such as meteorology, hydrology, and geology in this area from an external data service platform according to the determined driving area of the vehicle. Then, using the obtained detailed geographical information system data packet, the current driving speed of the vehicle, and the vehicle position information, calculate the possibility of different types of natural disasters occurring in the vehicle driving area and the degree of impact that these disasters may cause to vehicle safety, and obtain the risk assessment result. After obtaining the risk assessment result, the system classifies the natural disaster risk according to this result. Finally, according to the obtained risk level, specific disaster type, and the judgment of the driver's current state, determine the presentation method of the warning information, and generate the warning information according to the selected method and send it to the driver. By sequentially executing the steps, this method realizes a complete process from environmental data acquisition to risk assessment and then to warning information output, and combines the vehicle's own state and the driver's state to improve the pertinence and adaptability of the warning.

[0031] Through the above solution, this application determines the driving area by obtaining the vehicle position and predicted path, specifically obtains detailed environmental data, combines the vehicle's own state for risk assessment and grading, and dynamically adjusts the warning presentation method according to the risk level, disaster type, and driver state, realizing the accurate assessment, timely warning, and effective transmission of natural disaster risks.

[0032] In some embodiments, step A1 includes: A101. Obtain the vehicle position information through the in-vehicle Beidou positioning system; A102. Obtain the destination information, current navigation path information, and historical driving route data from the vehicle navigation system; A103. Predict the future driving route of the vehicle based on the destination information, current navigation route information, historical driving route data, and real-time route information of the vehicle, and obtain the predicted route information; the real-time route information is the route formed by connecting the vehicle positions within a preset time window before the current moment. A104. Adopt the buffer analysis method to construct an initial buffer with the current position of the vehicle as the center and the predicted route as the extension direction. A105. Calculate the buffer radius increment according to the road type to adjust the size of the initial buffer and obtain the vehicle driving area.

[0033] Among them, predicting the future driving route of the vehicle means inferring the geographical path that the vehicle may pass through in a future period according to the existing vehicle driving-related information, which can be realized by technologies such as historical data statistics-based, navigation planning information-based correction, or machine learning model-based prediction.

[0034] Among them, the buffer analysis method refers to a method in a geographic information system that expands a certain distance around a geographic feature (such as a point, line, or surface) to form a region with a specific width.

[0035] Among them, the buffer radius increment refers to the adjusted value of the basic buffer distance used in buffer analysis according to specific geographic or environmental factors (such as road type) to change the size of the final buffer area.

[0036] Through the synergistic effect of the above steps, the method of this application realizes the following working principle: First, the accurate position of the vehicle is obtained through the in-vehicle Beidou positioning system, providing an accurate geographical starting point for subsequent path prediction and area determination. Next, the system obtains multi-source information from the vehicle navigation system, including the destination planned by the driver, the current navigation path, and the historical driving route data of the vehicle. Combining these information with the recent real-time driving trajectory of the vehicle, they jointly serve as the basis for predicting the future driving route of the vehicle. Based on this multi-source information, the system can predict a future path that better conforms to the actual driving intention and habit of the vehicle. Subsequently, using the buffer analysis technology in the geographic information system, starting from the current position of the vehicle and extending along the direction of the predicted future path, an initial buffer is constructed that initially covers the possible driving range of the vehicle. To make the determined area more accurate and reasonable, the system further considers the type of the road where the vehicle is currently located. Different road types correspond to different driving speeds, safety margins, and distribution characteristics of potential risks. Therefore, the system calculates an adjustment amount for the buffer radius according to the road type and uses this adjustment amount to correct the size of the initial buffer. For example, a larger buffer may be required on highways to cover a farther predicted distance and potential risk range, while a smaller buffer may be required on urban roads to focus on a closer area. Through this dynamic adjustment based on the road type, the finally determined vehicle driving area can more accurately reflect the actual geographical range of the risks that the vehicle may face, avoiding the problems of being too large or too small in range. This accurate and reasonable area determination provides a reliable basis for subsequently obtaining the detailed geographic information system data packet within this area from the data service platform, ensuring that the obtained data can effectively cover the potential risk area, while reducing the acquisition and processing of redundant data, thereby improving the efficiency and accuracy of the entire early warning system.

[0037] The method of the present application will be described below in conjunction with a specific embodiment: In a specific vehicle-mounted system, vehicle position information is obtained through a positioning module that supports Beidou signal reception. The vehicle navigation system can provide the destination set by the user, the current navigation route plan, and the historical driving trajectory data stored in the local memory. The real-time route information can be obtained by continuously recording the position points output by the positioning module and connecting them to form a trajectory segment within a preset time window. When predicting the future driving route of the vehicle, if the navigation system is working and there is a clear destination and path, the system can preferably refer to the navigation path, and in combination with the real-time route information, correct the navigation path through a fusion algorithm (for example, a weighted average or filtering method can be adopted) to obtain the predicted path. If the navigation system is not working or there is no clear destination, the system can analyze the historical driving route data, identify the most likely driving pattern of the vehicle at the current position and direction, and predict the future driving trajectory segment based on this as the predicted path. When determining the vehicle driving area, the system calls the buffer analysis function in the vehicle-mounted GIS software library, takes the current position of the vehicle as the starting point, and generates an initial strip-shaped buffer along the direction of the predicted path based on a preset initial width. The system reads the type information of the current road from the navigation map data, for example, identifies that the current road is a highway. According to the preset rules or look-up table, the highway corresponds to a relatively large buffer radius increment. The system applies this increment to the width of the initial buffer, for example, increases the initial width by a specific value, so as to obtain a wider vehicle driving area. For other types of roads, the adjustment method of the initial buffer width is similar to that of the highway, but its buffer radius increment is different from that of the highway and may be negative (specifically set according to the initial width).

[0038] Through the above technical solutions, the present application can achieve the following technical effects: The vehicle position information is obtained through the vehicle-mounted Beidou positioning system, improving the accuracy of the position information. By comprehensively using the destination information, the current navigation path information, the historical driving route data, and the real-time route information of the vehicle to predict the future driving route of the vehicle, the reliability of the predicted path is improved. The buffer analysis method is adopted and the buffer size is adjusted in combination with the road type to determine a vehicle driving area that is more in line with the actual driving situation, avoiding the irrationality of the area range. This enables the subsequent obtained detailed geographic information system data packets to effectively cover the areas where the vehicle may face risks, while reducing the acquisition and processing of redundant data, and improving the efficiency and accuracy of subsequent data acquisition and risk assessment.

[0039] Preferably, step A103 may include: When both the destination information and the current navigation path information are not empty, through the Kalman filtering algorithm, fuse the current navigation path information and the real-time route information to predict the future driving route of the vehicle and obtain the predicted path information; When both the destination information and the current navigation path information are empty, a Markov model is adopted. Based on the historical driving route data, the future vehicle driving trajectory is predicted, and the predicted trajectory is used as the predicted path information.

[0040] In this prediction method, the Kalman filter algorithm and the Markov model are introduced. The Kalman filter algorithm is a recursive algorithm for optimal estimation of a dynamic system with noise. It can fuse data from different sources to predict and update the state of the system. The Markov model is a statistical model used to describe the transition probabilities between a series of possible states and can learn from historical data and predict the future state sequence.

[0041] This solution aims at the problem of predicting the future driving route of a vehicle. According to two different driving scenarios of whether there is destination information and current navigation path information, different prediction algorithms are adopted respectively to improve the accuracy and adaptability of the prediction.

[0042] Specifically, when both the destination information and the current navigation path information are not empty, it indicates that the vehicle is using the navigation system and has a clear driving goal and planned path. In this scenario, the future driving route of the vehicle will largely follow the navigation path, but there may be positioning errors or driver fine-tuning during the actual driving process. Therefore, by using the Kalman filter algorithm to fuse the current navigation path information (as the desired trajectory) and the real-time route information (reflecting the actual driving situation), the advantage of the Kalman filter for optimal estimation of a dynamic system with noise can be utilized to more accurately predict the future driving trajectory of the vehicle under navigation guidance. Fusing the navigation path information helps correct the deviation that may occur in the prediction based only on the real-time route, while fusing the real-time route information can reflect the actual execution of the driver on the navigation path, making the prediction result closer to the reality. The Kalman filter algorithm can use the current navigation path information as the desired state or reference input of the system, and the real-time position and motion information as the observed values. Through the prediction and update steps, the optimal position sequence of the vehicle in the future period of time is estimated to form the predicted path information.

[0043] When both the destination information and the current navigation path information are empty, it indicates that the vehicle is not using the navigation system and the driver may be driving freely. In this scenario, the future driving behavior of the vehicle depends more on the driver's habits and historical behavior patterns. Therefore, using a Markov model, based on the historical driving route data, the driving habits and path selection preferences of the driver at different locations and under different road conditions can be learned. Through the Markov model, according to the current real-time route information of the vehicle, the most likely future driving trajectory without navigation constraints can be predicted. This method can capture the driver's personalized driving style and the tendency to choose familiar routes, filling the prediction gap when there is no navigation information. Specifically, a historical driving route database is stored in the in-vehicle system. This database records the driving trajectories of the vehicle at different times and on different road sections. The Markov model can be pre-trained based on these historical data to learn the transition probabilities between different road sections or different location points. When predicting, according to the current real-time position of the vehicle and the driving trajectory in the recent period (real-time route information), it is used as the current state, and the trained Markov model is used to predict a series of road sections or location points that are most likely to be passed in the future, thereby generating prediction path information.

[0044] By distinguishing scenarios with and without navigation information and respectively using two different prediction algorithms, namely the Kalman filter and the Markov model, which are applicable to their respective scenarios, this solution can predict the future driving path of the vehicle in different driving states more accurately and robustly. Thus, the obtained prediction path information is more reliable, providing a more solid foundation for subsequent determination of the vehicle driving area, acquisition of detailed geographic information system data packets, risk assessment, and generation of warning information, thereby enhancing the effectiveness of the entire disaster prevention and warning method.

[0045] In some embodiments, the A3 includes: A301. Obtain a pre-constructed disaster type association matrix; the disaster type association matrix represents the association probabilities between different types of natural disasters; A302. Extract meteorological information, hydrological information, and geological information within the vehicle driving area from the detailed geographic information system data packet, and calculate the initial occurrence probabilities of various natural disasters based on historical disaster data; A303. According to the disaster type association matrix, through a weighted average algorithm, correct the initial occurrence probabilities of various natural disasters to obtain the associated and corrected disaster occurrence probabilities; A304. According to the vehicle position information, calculate the distances between the vehicle and various risk sources, and combine the road type and meteorological information to determine the influence factors of various natural disasters on vehicle safety using a fuzzy logic algorithm; According to the probability of disaster occurrence corrected based on the association, the influencing factors, and the current speed of the vehicle, calculate the comprehensive risk value of various natural disasters to the vehicle through the weighted summation algorithm as the risk assessment result.

[0046] Among them, the disaster type association matrix refers to a two-dimensional data structure used to quantify the probability of mutual influence between different types of natural disasters (i.e., the probability of one natural disaster triggering another natural disaster). It can be implemented using a matrix constructed based on statistical analysis of historical disaster data or expert experience. The rows and columns of this matrix both represent different types of natural disasters, and the elements of the matrix represent the probability of mutual influence between the corresponding two natural disasters.

[0047] Among them, the weighted average algorithm refers to a method for calculating the average value, where each value is multiplied by a weight factor, and then the results are added and divided by the sum of the weights. It can be implemented by assigning weights according to the importance of different factors for calculation.

[0048] Among them, the fuzzy logic algorithm refers to a method for reasoning and decision-making based on fuzzy set theory, which can handle imprecise or uncertain information. It can be implemented by constructing a fuzzy rule base and membership functions.

[0049] Among them, the weighted summation algorithm refers to a calculation method that adds the products of multiple values multiplied by their corresponding weights to obtain the total sum. It can be implemented by assigning weights according to the influence degree of different input items on the result for calculation.

[0050] This solution refines the risk assessment process, aiming to address the challenges of data uncertainty, multiple risks superposition, and how to comprehensively consider various factors for accurate assessment during risk assessment. By introducing a disaster type association matrix, comprehensively considering various environmental and vehicle status information, and adopting corresponding algorithms, the accuracy and reliability of risk assessment are improved. Specifically, by obtaining the pre-constructed disaster type association matrix, it provides basic data for subsequent consideration of the mutual influence and correlation probability between different types of natural disasters, which helps to solve the problem of how to conduct assessment when multiple risk types coexist. Extract meteorological information, hydrological information, and geological information within the vehicle's driving area from the detailed geographic information system data packet, and calculate the initial occurrence probability of various natural disasters based on historical disaster data. This is the basis for risk assessment, and using the existing environmental information and historical experience, a preliminary judgment on the likelihood of various disasters occurring is made. According to the disaster type association matrix, through the weighted average algorithm, the initial occurrence probability of various natural disasters calculated is corrected to obtain the disaster occurrence probability after association correction. This step considers the correlation between different disasters. For example, a certain meteorological condition may increase the risks of landslides and mudslides simultaneously. By correcting through the association matrix, the probability assessment is more in line with the actual situation, reflecting the impact of risk superposition. According to the vehicle position information, calculate the distance between the vehicle and various risk sources, and combine the road type and meteorological information to determine the impact factor of various natural disasters on vehicle safety using the fuzzy logic algorithm. This step assesses the degree of impact on vehicle safety after a disaster occurs. By considering various factors such as the distance between the vehicle and the risk source, road type, and meteorological conditions, and using the fuzzy logic algorithm to process these potentially uncertain inputs, the potential impact of disasters on the vehicle can be more accurately quantified, rather than just judging whether a disaster occurs. According to the disaster occurrence probability after association correction, the calculated impact factor, and the current vehicle speed, calculate the comprehensive risk value of various natural disasters on the vehicle through the weighted summation algorithm as the risk assessment result. This step comprehensively evaluates the likelihood of a disaster occurring, the potential impact degree of the disaster on the vehicle, and the vehicle's own status. The faster the vehicle speed, the shorter the driver's reaction and evasion time, and the higher the risk. Through weighted summation, a comprehensive risk value is obtained, comprehensively reflecting the threat degree of various natural disasters to vehicle safety in the current situation, providing a quantitative basis for subsequent risk grading. This solution is carried out on the basis of determining the vehicle's driving area and obtaining the detailed geographic information system data packet, enabling the risk assessment to target the areas and environmental conditions that the vehicle may actually face, improving the pertinence of the assessment.

[0051] Through the above technical means, this solution can calculate the probabilities of different types of natural disasters occurring within the vehicle's driving area and the degree of impact on vehicle safety more accurately, overcome the challenges brought by the uncertainty of input data, the superposition of multiple risk types, and insufficient consideration of comprehensive factors, improve the accuracy and reliability of risk assessment, and provide a more solid foundation for subsequent risk early warning.

[0052] Preferably, step A302 may include: Extract meteorological information, hydrological information, and geological information within the vehicle's driving area from the detailed geographic information system data packet; the meteorological information includes rainfall, wind speed, temperature, and humidity; the hydrological information includes water level, flow rate, flow velocity, and water quality; the geological information includes geological structure, rock and soil type, slope, and surface coverage information; According to the extracted meteorological information, hydrological information, and geological information, combined with historical disaster data, use the Bayesian network model to calculate the initial occurrence probabilities of landslides, floods, debris flows, and waterlogging within the vehicle's driving area; the historical disaster data includes the disaster type, occurrence time, geographical location, impact range, loss degree of historical disasters, as well as the corresponding meteorological information, hydrological information, and geological information.

[0053] Among them, the detailed geographic information system data packet can be stored in formats such as Shapefile, GeoJSON, or GeoPackage.

[0054] Among them, the Bayesian network model refers to a directed acyclic graph model, where nodes represent random variables, edges represent the conditional dependence relationship between variables, and this dependence strength is described by the conditional probability distribution, which is used for probability inference and uncertainty modeling. Its network structure can be determined by the structure learning algorithm, and the conditional probability distribution can be determined by the parameter learning algorithm.

[0055] This application extracts meteorological information, hydrological information, and geological information within the vehicle driving area from a detailed geographic information system data packet, which serves as the key input for calculating the initial occurrence probability. Meteorological information, hydrological information, and geological information are environmental factors closely related to the occurrence of natural disasters such as landslides, floods, debris flows, and waterlogging. At the same time, combined with historical disaster data, which includes the environmental conditions and disaster characteristics during past disasters, it provides a basis for understanding the relationship between environmental factors and the occurrence of disasters. Using a Bayesian network model, a probability model between environmental factors and the occurrence of specific disasters is constructed. The Bayesian network model can effectively represent and handle the complex dependencies between variables and the uncertainty of data. By taking the extracted current environmental information as the evidence input of the Bayesian network, the model can perform probability inference to calculate the initial probabilities of the occurrence of four specific disasters, namely landslides, floods, debris flows, and waterlogging, within the vehicle driving area under the current environmental conditions. The ability of the Bayesian network model to handle uncertainty enables reasonable probability inference even in the case of missing or noisy input data, thus overcoming the difficulties of traditional methods in effectively dealing with uncertain data and complex associations. The calculated initial occurrence probabilities serve as the basic input for subsequent risk assessment steps, such as for correlation correction and comprehensive risk value calculation, improving the accuracy and reliability of the overall risk assessment.

[0056] In one embodiment, the detailed geographic information system data packet is in GeoPackage format and includes layers such as elevation data, soil type distribution maps, river and lake boundaries, historical landslide points, and historical flood inundation areas. Meteorological information, hydrological information, and geological information are extracted from the corresponding layers or attribute tables in this data packet. For example, the average rainfall, water levels of major rivers, soil types, and slope information within the vehicle driving area are obtained through spatial queries. Historical disaster data is stored in a relational database, containing detailed records of each historical disaster event. The Bayesian network model is pre-constructed and stored in the in-vehicle terminal, and its nodes include variables such as meteorological information (such as rainfall), hydrological information (such as water level), geological information (such as slope, soil type, etc.), and historical disaster events (such as historical landslide events, historical flood events, debris flow events, waterlogging events, etc.). By performing statistical analysis and machine learning training on historical disaster data, the network structure and conditional probability table are determined. During operation, the extracted current meteorological, hydrological, and geological information is used as the evidence input for the corresponding nodes in the Bayesian network, and the belief propagation algorithm is used to calculate the posterior probabilities of the landslide, flood, debris flow, and waterlogging nodes, that is, the initial occurrence probabilities.

[0057] By extracting meteorological, hydrological, and geological information closely related to specific natural disasters from a detailed geographic information system data packet, combining historical disaster data, and using a Bayesian network model to calculate the initial occurrence probability, it is possible to more accurately capture the complex probability relationship between environmental factors and the occurrence of disasters, effectively handle data uncertainty, and improve the accuracy and robustness of calculating the initial occurrence probabilities of landslides, floods, debris flows, and waterlogging in the vehicle driving area.

[0058] Preferably, step A303 may include: For each type of natural disaster, according to the disaster type association matrix and a preset association probability threshold, calculate the influence weight of other disaster types on the occurrence probability of this type of natural disaster; According to the initial occurrence probabilities and influence weights of various natural disasters, correct the occurrence probabilities of various natural disasters through a weighted average algorithm to obtain the associated and corrected disaster occurrence probabilities.

[0059] Among them, the association probability threshold is a preset value used to filter out weakly associated disaster types to ensure that only associated disasters with a significant impact on the occurrence probability of the target disaster are considered. The influence weight is a value quantifying the degree of influence of other disaster types on the occurrence probability of the target disaster, and its calculation method can be determined based on the values in the association probability matrix and the association probability threshold. For example, the influence weight can be simply set as the association probability itself, or the value obtained by subtracting the association probability threshold from the association probability. For other disaster types with an association probability less than the association probability threshold, their corresponding influence weights can be set to 0.

[0060] This solution provides a more refined method for using disaster correlation to correct the initial occurrence probability by introducing the concept of influence weights and detailing how to calculate and apply these weights. Specifically, for each natural disaster, the system first consults a pre-constructed disaster type correlation matrix that stores the correlation probabilities between different types of natural disasters. Combining with a preset correlation probability threshold, the system identifies other disaster types whose correlation probabilities with the current target disaster type are higher than the threshold. Based on the correlation probabilities in the correlation matrix and the set threshold, the system calculates the specific influence weights of these correlated disaster types on the occurrence probability of the target disaster. This weight quantifies the enhancement or weakening effect of the correlated disaster on the occurrence likelihood of the target disaster. After calculating the influence weights of each correlated disaster on the target disaster, the system combines these weights with the initial occurrence probabilities of various natural disasters. The initial occurrence probability is calculated independently based on historical data and current environmental information, reflecting the occurrence likelihood without considering the correlation influence. Through a weighted average algorithm, using the initial probability as the basis and adjusting the initial probability according to the calculated influence weights. The correlated disasters with larger weights have a more significant correction effect on the target disaster probability. For example, the correction amount can be obtained by multiplying the initial probabilities of other disaster types by their weighted sum and dividing by the sum of their weights, and then adding this correction amount to the initial occurrence probability of the target natural disaster to obtain the correlated corrected disaster occurrence probability of the target natural disaster. This weighted average method can comprehensively consider the occurrence basis of the target disaster itself and the influence of other correlated disasters on its occurrence likelihood, thereby obtaining a more comprehensive and accurate correlated corrected disaster occurrence probability.

[0061] Through the above technical means, this application can more precisely quantify the specific influence degree of different correlated disasters on the occurrence probability of the target disaster, making the correction process more accurate. Weighted average correction of the initial occurrence probability based on the calculated influence weights can more comprehensively reflect the occurrence likelihood of a specific natural disaster in an environment where multiple disasters may interact with each other, thereby improving the accuracy of the final probability assessment.

[0062] Preferably, step A305 may include: Determine the weight coefficients of various natural disasters according to the correlated corrected disaster occurrence probability; Query the speed-influence factor adjustment coefficient table according to the current speed of the vehicle to obtain the influence factor adjustment coefficient corresponding to the current speed of the vehicle; Calculate the adjusted influence factors of various natural disasters by multiplication according to the influence factor and the influence factor adjustment coefficient; Calculate the comprehensive risk value of various natural disasters on the vehicle through a weighted summation algorithm according to the weight coefficients corresponding to the correlated corrected disaster occurrence probability and the adjusted influence factors as the risk assessment result.

[0063] Among them, the weight coefficient refers to a measure of the relative importance of various natural disasters in the calculation of the comprehensive risk value, which can be determined proportionally according to the disaster occurrence probability after correlation correction. For example, the higher the occurrence probability, the greater the weight coefficient.

[0064] Among them, the speed - impact factor adjustment coefficient table refers to a preset data structure that stores the mapping relationship between different vehicle speed ranges or specific speed values and the corresponding impact factor adjustment coefficients, which can be implemented using a table, a function, or a lookup table. The impact factor adjustment coefficient refers to a numerical factor used to dynamically correct the degree of influence of natural disasters on vehicle safety, and its value depends on the current speed of the vehicle, reflecting the influence of speed changes on the driver's reaction time, vehicle controllability, braking distance, etc., and thus changing the actual threat level of the disaster.

[0065] Among them, the adjusted impact factor refers to the value obtained by multiplying the original impact factor by the impact factor adjustment coefficient, which can better reflect the actual degree of influence of natural disasters on vehicle safety at the current speed of the vehicle.

[0066] Among them, the comprehensive risk value refers to the value calculated by weighted summation by comprehensively considering the occurrence probability of natural disasters and the adjusted impact factor, which is used to quantify the overall risk level of various natural disasters to vehicles.

[0067] Based on the above technical features, the working principle of the comprehensive risk value calculation method of the present application is as follows: The solution is based on the disaster occurrence probability and impact factors obtained after correlation correction in the foregoing steps. First, the occurrence probability after correlation correction is converted into a weight coefficient, so that disasters with a high occurrence probability have a greater weight in subsequent calculations. At the same time, the current speed of the vehicle is obtained, and the preset speed-impact factor adjustment coefficient table is used to find the adjustment coefficient corresponding to the current speed. This adjustment coefficient reflects the dynamic impact of speed on the vehicle's ability to cope with disasters. Then, the impact factor calculated in the foregoing steps is multiplied by the found adjustment coefficient to obtain the adjusted impact factor. This adjusted impact factor dynamically reflects the actual impact degree of the disaster on the vehicle at the current speed. Finally, the weight coefficient determined based on the occurrence probability and the adjusted impact factor are weighted and summed. The weight coefficient corresponding to the occurrence probability is used as the weight, and the adjusted impact factor is used as the item to be weighted. This calculation method comprehensively considers the possibility of disaster occurrence and the actual impact degree of the disaster at the current speed, so as to obtain a more comprehensive and accurate comprehensive risk value. This solution is combined with the foregoing steps. On the basis of calculating the occurrence probability considering relevance and the impact factors based on factors such as distance, road type, and meteorology in the foregoing steps, the dynamic impact of vehicle speed is further introduced, and the occurrence probability is used as the weight for weighting, so that the final risk assessment result not only considers the characteristics of the disaster itself and environmental factors, but also considers the dynamic state of the vehicle itself, improving the accuracy and practicality of the risk assessment.

[0068] Through the above method, the present application can achieve the following technical effects: By determining the weight coefficient according to the disaster occurrence probability after correlation correction, disasters with a higher occurrence probability have a greater weight in the comprehensive risk value calculation, more reasonably reflecting the contribution of the possibility of different disasters occurring to the overall risk. By querying the speed-impact factor adjustment coefficient table according to the current speed of the vehicle to obtain the adjustment coefficient and using it to adjust the impact factor, the impact factor can dynamically reflect the impact of vehicle speed on driver reaction, vehicle control, etc., so as to more accurately evaluate the actual threat degree of the disaster in the current driving state. By weighted summing the weight based on the occurrence probability and the impact factor adjusted based on speed, the obtained comprehensive risk value is more comprehensive, more dynamic, and more accurate, improving the reliability of the risk assessment result and providing a more solid foundation for subsequent risk level division and early warning.

[0069] In some embodiments, step A5 includes: A501. Obtain the facial image and eye movement data of the driver and the vehicle operation data to evaluate the driver's state; the driver's state includes the fatigue level and the degree of attention dispersion; A502. Determine the combination of the basic warning intensity and the presentation mode according to the risk level; the presentation mode combination includes at least one of the three modes of vision, audition, and touch; A503. Query the preset driver state-warning intensity adjustment coefficient table according to the driver state, obtain the corresponding warning intensity adjustment coefficient, and use it to adjust the basic warning intensity to obtain the adjusted warning intensity; A504. Generate a warning message according to the adjusted warning intensity, the presentation mode combination, and the disaster type, and present the warning message according to the corresponding presentation mode.

[0070] Among them, the driver state refers to the current physiological and psychological state of the driver, reflecting his perception and processing ability of information, which may include fatigue level, attention concentration level, etc. The fatigue level refers to the fatigue degree of the driver, which can be evaluated according to facial features, eye movement data, and vehicle operation data, and can be divided into different levels. The degree of attention dispersion refers to the concentration of the driver's attention, which can be evaluated according to eye movement data, facial orientation, and vehicle operation data, and can be quantified into different degrees. The fatigue level and the degree of attention dispersion can be identified using their respective pre-trained recognition models, and these recognition models are trained using historical facial images, historical eye movement data, and historical vehicle operation data as training data.

[0071] Among them, the basic warning intensity refers to the initial intensity level of the warning message determined according to the risk level, and the intensity can be reflected in aspects such as visual brightness, flicker frequency, auditory volume, tone, tactile vibration frequency, amplitude, etc.

[0072] Among them, the presentation mode combination refers to the combination of sensory channels used to present the warning message to the driver, which may include at least one of vision, audition, and touch.

[0073] Among them, the preset driver state-warning intensity adjustment coefficient table refers to a lookup table that stores the relationship between different driver states and the corresponding warning intensity adjustment coefficients, and this table can be preset according to experimental data or expert experience. The warning intensity adjustment coefficient refers to a multiplicative or additive coefficient used to adjust the basic warning intensity, and this coefficient reflects the degree to which the warning intensity needs to be enhanced or weakened in a specific driver state. The adjusted warning intensity refers to the final warning intensity obtained by adjusting the basic warning intensity according to the warning intensity adjustment coefficient.

[0074] Through the above steps, the present application realizes a technical solution for dynamically adjusting the warning intensity and presentation mode according to the driver's real-time state. The system first obtains the driver's real-time state data and evaluates their fatigue level and distraction situation. At the same time, according to the risk level obtained from the foregoing steps, a standard warning intensity and presentation mode combination is determined. Then, using the evaluated driver state, a adjustment coefficient is obtained by querying a preset adjustment table. This adjustment coefficient is used to correct the standard warning intensity to obtain an adjusted warning intensity adapted to the driver's current state. Finally, combining this adjusted intensity, the predetermined presentation mode combination, and the specific disaster type, a warning message is generated and presented to the driver. The whole process forms a closed loop, from perceiving the driver's state to dynamically adjusting the warning output, ensuring that the warning message can be delivered in the most likely way to be perceived and understood by the driver. By combining the risk level and disaster type determined in the foregoing steps with the driver's real-time state, the warning message issued by the system not only reflects the risks of the external environment but also takes into account the driver's individual reception ability, thereby improving the pertinence and effectiveness of the warning.

[0075] Through the above technical solution, the present application can dynamically adjust the warning intensity and presentation mode according to the driver's real-time state. When the driver is fatigued or distracted, the warning intensity is enhanced, increasing the likelihood that the warning message is perceived and noticed. When the driver is in a good state, the warning intensity can be appropriately adjusted to avoid excessive interference. This adaptive adjustment according to the driver's state enables the warning message to reach the driver more effectively, attracting their sufficient attention, thereby improving the effectiveness of the warning and reducing the risks caused by the driver's failure to respond to the warning in a timely manner.

[0076] Preferably, after step A504, the following steps may further be included: A505. Monitor the driver's eye movement data and vehicle operation data, determine whether the driver responds to the warning message. If no response is detected within the preset time, increase the warning message presentation intensity and / or switch the presentation mode until the driver makes a response.

[0077] Among them, the eye movement data refers to the data reflecting the physiological states of the driver's eye movement, fixation point, pupil size, etc., which can be obtained by using an eye movement tracking device or an eye movement analysis algorithm integrated in the in-vehicle camera. The vehicle operation data refers to the data reflecting the control operations of the driver on the vehicle, which may include information such as steering angle, accelerator pedal position, brake pedal position, vehicle speed, gear, etc., and can usually be obtained through the vehicle's CAN bus system.

[0078] Among them, determining whether the driver responds to the warning information means analyzing whether the driver shows attention to the warning information or takes driving behaviors related to the warning information based on the monitored eye movement data and vehicle operation data, which can use preset rules or machine learning models to identify specific eye movement patterns (such as gazing at the warning display screen) or vehicle operation changes (such as decelerating, changing lanes). The preset time refers to a configurable time interval that the system waits for the driver to respond after sending the warning information (which can be set according to actual needs).

[0079] Among them, increasing the presentation intensity of the warning information means improving the perceptibility of the warning signal, which can be achieved by increasing the warning volume, enhancing the visual flicker frequency or brightness, increasing the amplitude of the tactile vibration, etc. Switching the presentation mode means changing the modal combination of the warning information transmission, which can be achieved by switching from a single visual cue to a visual and auditory combined cue, or adding a tactile cue, etc.

[0080] Based on generating and presenting the warning information, this solution further adds a monitoring and feedback mechanism for the driver's response. After the system generates and presents the warning information according to the risk level, disaster type and driver status, the system will continuously monitor the driver's eye movement data and vehicle operation data. By analyzing these data, the system can determine whether the driver has paid attention to the sent warning information or taken corresponding driving behaviors within the preset time window. This monitoring and judgment mechanism is a key link to ensure the effectiveness of the warning. If the system fails to detect the driver's response within the preset time, it indicates that the driver may not have noticed the warning or failed to understand and take actions in time. At this time, the system will not stop the warning but actively take enhancement measures. By increasing the presentation intensity of the warning information, such as increasing the loudness of the sound, enhancing the prominence of the visual signal or increasing the intensity of the tactile feedback, and / or switching the presentation mode of the warning information, such as adding an auditory or tactile cue from a single visual cue, the system can more powerfully attract the driver's attention and break through the possible perceptual barriers or distraction states. This mechanism of dynamically adjusting and enhancing the warning can significantly improve the coerciveness and perceptibility of the warning information until the system detects that the driver has taken a response behavior related to the warning information. This feedback loop of monitoring after sending the warning and dynamically adjusting the warning intensity and mode according to the driver's status enables the warning information to be more effectively received and processed by the driver, thus prompting the driver to take timely risk avoidance measures and effectively respond to natural disaster risks.

[0081] Reference Figure 2 , this application provides a vehicle-mounted multi-level disaster prevention warning system based on Beidou communication, which is used to warn of natural disaster risks during vehicle driving. The system includes: The area determination module 1 is used to obtain the vehicle position information and the predicted path information and determine the vehicle driving area (the specific process can refer to step A1 in the foregoing text). The data acquisition module 2 is used to obtain a detailed geographic information system data packet from the data service platform according to the vehicle driving area; the detailed geographic information system data packet includes meteorological information, hydrological information, and geological information of the vehicle driving area (the specific process can refer to step A2 in the foregoing text). The risk assessment module 3 is used to calculate the probability of different types of natural disasters occurring in the vehicle driving area and the degree of impact on vehicle safety based on the detailed geographic information system data packet, the current vehicle speed, and the vehicle position information, and obtain a risk assessment result (the specific process can refer to step A3 in the foregoing text). The risk classification module 4 is used to classify the natural disaster risk according to the risk assessment result (the specific process can refer to step A4 in the foregoing text). The warning module 5 is used to determine the presentation method of the warning information according to the risk level, the type of disaster, and the driver's state, and generate and present the warning information according to the corresponding presentation method (the specific process can refer to step A5 in the foregoing text).

[0082] The above are only the embodiments of the present application and are not used to limit the protection scope of the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A vehicle-mounted multi-level disaster prevention and warning method based on Beidou communication, which is used to give early warnings of natural disaster risks during vehicle driving, and is characterized in that The steps of the method include: A1. Obtain vehicle position information and predicted path information, and determine the vehicle driving area; A2. According to the vehicle driving area, obtain a detailed geographic information system data packet from the data service platform; the detailed geographic information system data packet includes meteorological information, hydrological information, and geological information of the vehicle driving area; A3. According to the detailed geographic information system data packet, the current vehicle speed, and the vehicle position information, calculate the probabilities of different types of natural disasters occurring within the vehicle driving area and the degree of impact on vehicle safety, to obtain a risk assessment result; A4. According to the risk assessment result, conduct a risk level classification for natural disaster risks; A5. According to the risk level, disaster type, and driver status, determine the presentation method of the warning information, and generate and present the warning information according to the corresponding presentation method.

2. The vehicle-mounted multi-level disaster prevention and warning method based on Beidou communication according to claim 1, characterized in that Step A1 includes: A101. Obtain vehicle position information through the in-vehicle Beidou positioning system; A102. Obtain destination information, current navigation path information, and historical driving route data from the vehicle navigation system; A103. According to the destination information, current navigation path information, historical driving route data, and the real-time route information of the vehicle, predict the future driving route of the vehicle to obtain predicted path information; the real-time route information is the route formed by connecting the vehicle positions within a preset time window before the current moment; A104. Adopt the buffer analysis method, with the current vehicle position as the center and the predicted path as the extension direction, to construct an initial buffer; A105. According to the road type, calculate the buffer radius increment to adjust the size of the initial buffer to obtain the vehicle driving area.

3. The vehicle-mounted multi-level disaster prevention and warning method based on Beidou communication according to claim 2, characterized in that, Step A103 includes: When both the destination information and the current navigation path information are not empty, through the Kalman filtering algorithm, fuse the current navigation path information and the real-time route information, and predict the future driving route of the vehicle to obtain predicted path information; When both the destination information and the current navigation path information are empty, adopt the Markov model, according to the historical driving route data, predict the future vehicle driving trajectory, and use the predicted trajectory as the predicted path information.

4. A vehicle-mounted multi-level disaster prevention and warning method based on Beidou communication according to claim 1, characterized in that, The said A3 includes: A301. Obtain a pre-constructed disaster type correlation matrix; the disaster type correlation matrix represents the correlation probabilities between different types of natural disasters; A302. Extract meteorological information, hydrological information, and geological information within the vehicle driving area from the detailed geographic information system data packet, and calculate the initial occurrence probabilities of various natural disasters based on historical disaster data; A303. According to the disaster type correlation matrix, through the weighted average algorithm, correct the initial occurrence probabilities of various natural disasters to obtain the disaster occurrence probabilities after correlation correction; A304. According to the vehicle position information, calculate the distances between the vehicle and various risk sources, and combine the road type and meteorological information, and use the fuzzy logic algorithm to determine the impact factors of various natural disasters on vehicle safety; A305. According to the disaster occurrence probabilities after correlation correction, the impact factors, and the current vehicle speed, through the weighted summation algorithm, calculate the comprehensive risk values of various natural disasters on the vehicle as the risk assessment result.

5. A vehicle-mounted multi-level disaster prevention and warning method based on Beidou communication according to claim 4, characterized in that, Step A302 includes: Extract meteorological information, hydrological information, and geological information within the vehicle's driving area from the detailed geographic information system data packet; the meteorological information includes rainfall, wind speed, temperature, and humidity; the hydrological information includes water level, flow rate, flow velocity, and water quality; the geological information includes geological structure, rock and soil type, slope, and surface coverage information; Based on the extracted meteorological information, hydrological information, and geological information, combined with historical disaster data, use the Bayesian network model to calculate the initial occurrence probabilities of landslides, floods, debris flows, and waterlogging within the vehicle's driving area; the historical disaster data includes the disaster type, occurrence time, geographical location, influence range, loss degree of historical disasters, as well as the corresponding meteorological information, hydrological information, and geological information.

6. A vehicle-mounted multi-level disaster prevention and warning method based on Beidou communication according to claim 4, characterized in that, Step A303 includes: For each type of natural disaster, calculate the influence weight of other disaster types on the occurrence probability of this type of natural disaster according to the disaster type association matrix and the preset association probability threshold; According to the initial occurrence probabilities and influence weights of various natural disasters, correct the occurrence probabilities of various natural disasters through the weighted average algorithm to obtain the associated corrected disaster occurrence probabilities.

7. A vehicle-mounted multi-level disaster prevention and warning method based on Beidou communication according to claim 4, characterized in that, Step A305 includes: Determine the weight coefficients of various natural disasters according to the associated corrected disaster occurrence probabilities; According to the current vehicle speed, query the speed-influence factor adjustment coefficient table to obtain the influence factor adjustment coefficient corresponding to the current vehicle speed; According to the influence factor and the influence factor adjustment coefficient, use multiplication operation to calculate the adjusted influence factors of various natural disasters; According to the weight coefficients corresponding to the associated corrected disaster occurrence probabilities and the adjusted influence factors, calculate the comprehensive risk values of various natural disasters on the vehicle through the weighted summation algorithm as the risk assessment result.

8. A vehicle-mounted multi-level disaster prevention and warning method based on Beidou communication according to claim 1, characterized in that, Step A5 includes: A501. Obtain the driver's facial image, eye movement data, and vehicle operation data to evaluate the driver's state; the driver's state includes fatigue level and degree of attention dispersion; A502. Determine the basic warning intensity and presentation mode combination according to the risk level; the presentation mode combination includes at least one of the three modes of vision, hearing, and touch; A503. According to the driver's state, query the preset driver state-warning intensity adjustment coefficient table to obtain the corresponding warning intensity adjustment coefficient to adjust the basic warning intensity to obtain the adjusted warning intensity; A504. Generate warning information according to the adjusted warning intensity, the presentation mode combination, and the disaster type, and present the warning information according to the corresponding presentation mode.

9. The vehicle-mounted multi-level disaster prevention and warning method based on Beidou communication according to claim 8, characterized in that, After step A504, it further includes the step: A505. Monitor the driver's eye movement data and vehicle operation data to determine whether the driver responds to the warning information. If no response is detected within the preset time, increase the warning information presentation intensity and / or switch the presentation mode until the driver makes a response.

10. A vehicle-mounted multi-level disaster prevention warning system based on Beidou communication, which is used to warn of natural disaster risks during vehicle driving, is characterized in that The system includes: A region determination module for obtaining vehicle position information and predicted path information to determine the vehicle's driving area; A data acquisition module, configured to obtain a detailed geographic information system data packet from a data service platform according to the vehicle driving area; the detailed geographic information system data packet includes meteorological information, hydrological information, and geological information of the vehicle driving area; A risk assessment module, configured to calculate the probability of occurrence of different types of natural disasters in the vehicle driving area and the degree of impact on vehicle safety according to the detailed geographic information system data packet, the current vehicle speed, and the vehicle position information, so as to obtain a risk assessment result; A risk grading module, configured to classify the natural disaster risk according to the risk assessment result; An early warning module, configured to determine the presentation mode of the early warning information according to the risk level, the type of disaster, and the driver state, and generate and present the early warning information according to the corresponding presentation mode.

Images