Ground abnormity early warning method, system and equipment based on navigation and storage medium

Abstract

The invention relates to the technical field of electronic navigation, in particular to a navigation-based ground abnormity early warning method, system and device and a storage medium, and the method comprises the steps: obtaining vehicle historical information data, road geographic information data and historical abnormal state data; performing feature extraction on each selected area of each target road according to the data; obtaining a corresponding characteristic value, and constructing an anomaly detection library of each target road according to each characteristic value; in the vehicle driving process, real-time driving data of the vehicle are obtained, and the driving area of the vehicle in the current road and the corresponding target feature value in the anomaly detection library are determined; based on the target characteristic value and the vehicle navigation position information in the real-time driving data, generating an abnormal detection result of vehicle driving, and executing a corresponding early warning strategy; according to the invention, the ground abnormity can be accurately analyzed based on the vehicle driving track, the early warning efficiency and accuracy are improved, and the risk of accidents is reduced.

Description

Technical Field

[0001] The present invention relates to the field of electronic navigation technology, and in particular to a navigation-based ground anomaly early warning method, system, equipment and storage medium. Background Art

[0002] With the rapid development of the automobile industry, navigation equipment has been widely used in various types of vehicles and has become an important tool for drivers to obtain road condition information and traffic warnings. During vehicle driving, due to the high speed, it is necessary to obtain real-time road condition information and traffic warnings of the driving section through navigation equipment. In some cases, ground anomalies (such as landslides, ground collapse, bridge fractures, etc.) can lead to very severe chain traffic accidents. For such geological disasters, timely and correct warnings can prevent existing traffic accidents from developing into major traffic accidents.

[0003] However, the existing early warning technologies mainly include warnings of other vehicles in the blind spot of the current vehicle, warnings of lane change risks, warnings based on traffic flow, warnings of driver fatigue driving, and warnings of vehicle driving posture, etc. However, in the face of sudden and extremely harmful geological disasters such as ground anomalies, the existing early warning mechanisms are often difficult to respond efficiently and quickly. In addition, due to the lag in vehicle navigation system data and map updates, the actual road conditions after a geological disaster cannot be reflected in the navigation system in a timely manner, resulting in inaccurate route information provided by the navigation system. Under the influence of geological disasters, originally feasible roads may become impassable. The existing navigation system cannot timely warn itself and the vehicles in front and behind, resulting in the driver being unable to take effective avoidance measures against ground anomalies to avoid traffic accidents.

[0004] It can be seen that how to automatically warn of abnormal ground conditions to prevent traffic accidents has become a technical problem that technical personnel in this field need to solve urgently. Summary of the invention

[0005] The present invention provides a navigation-based ground anomaly warning method, system, device and storage medium to solve the problem of how to infer possible ground anomalies in a target area through the driving trajectory of a vehicle, so as to realize automatic warning of vehicle traffic accidents.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a ground abnormality early warning method based on navigation, comprising:

[0007] Obtain vehicle historical information data, road geographic information data and historical abnormal status data;

[0008] According to the vehicle historical information data, the road geographic information data and the historical abnormal state data, feature extraction is performed on each selected area of ​​each target road to obtain a corresponding feature value, wherein the feature value reflects the basic parameter attributes of the current road and the driving trajectory of the vehicle;

[0009] Using each of the characteristic values, construct an anomaly detection library for each of the target roads;

[0010] During the driving process of the vehicle, the real-time driving data of the vehicle is obtained, and the driving area of ​​the vehicle on the current road is determined;

[0011] Determining a corresponding target feature value in the anomaly detection library based on the driving area;

[0012] Generate a vehicle driving abnormality detection result based on the target feature value and the vehicle navigation position information in the real-time driving data;

[0013] Based on the abnormal detection result, a corresponding early warning strategy is executed.

[0014] Furthermore, the feature extraction is performed on each selected area of ​​each target road to obtain corresponding feature values, including:

[0015] Extracting basic parameter attributes of each target road according to the road geographic information data to obtain a first eigenvalue;

[0016] Calculate the characteristic values ​​of different modes respectively according to the vehicle historical information data to obtain a second characteristic value; the vehicle historical information data includes historical vehicle type data and historical vehicle position data;

[0017] The historical abnormal state data is analyzed, and the frequency, type and time data of abnormal occurrence in each selected area of ​​each target road are counted to obtain a third characteristic value.

[0018] Further, the calculating of characteristic values ​​of different modes respectively according to the vehicle historical information data to obtain the second characteristic value includes: the modes include a first mode, a second mode and a third mode;

[0019] In the first mode, a second characteristic value is obtained based on the vehicle historical information data;

[0020] In the second mode, the historical vehicle type data is classified, and characteristic values ​​are calculated based on different vehicle types to obtain second characteristic values;

[0021] In the third mode, the height data of the historical vehicle position data are classified, and characteristic values ​​are calculated based on different height data to obtain a second characteristic value.

[0022] Furthermore, during the driving process of the vehicle, obtaining the real-time driving data of the vehicle and determining the driving area of ​​the vehicle on the current road includes:

[0023] During the driving process of the vehicle, the real-time driving data is collected in real time, and the real-time driving data includes the navigation position information of the vehicle, the vehicle speed, the vehicle driving direction and the vehicle type;

[0024] The road where the vehicle is currently located and the corresponding driving area are determined according to the vehicle navigation position information and the road geographic information data.

[0025] Further, the generating of the vehicle driving abnormality detection result based on the target feature value and the vehicle navigation position information in the real-time driving data includes:

[0026] Inputting the target feature value and the vehicle navigation position information into a pre-trained anomaly detection model to determine whether the vehicle is currently in an abnormal ground state;

[0027] If the vehicle is currently in a ground abnormality state, the corresponding area is marked as a ground abnormality area, and an abnormality detection result is generated; the abnormality detection result includes the abnormality type, the abnormality impact range and the duration.

[0028] Furthermore, executing a corresponding early warning strategy based on the abnormal detection result includes:

[0029] If the vehicle is currently in a ground abnormality state, the vehicle is given a ground abnormality alarm prompt according to the generated abnormality detection result, and the ground abnormality alarm prompt includes a voice alarm and an LED flashing alarm;

[0030] After the abnormality alarm prompt is performed, a log is generated and recorded based on the abnormality detection result.

[0031] Furthermore, the executing a corresponding early warning strategy based on the abnormal detection result also includes:

[0032] If the vehicle is currently in a ground abnormality state, obtain the rear vehicle in the ground abnormality area, and calculate the distance between the target vehicle and the rear vehicle;

[0033] It is determined whether the distance is lower than a preset abnormal distance threshold. If the distance is lower than the abnormal distance threshold, an alarm is issued to the rear vehicle indicating that the ground is abnormal.

[0034] Another embodiment of the present invention provides a ground abnormality warning system based on navigation, comprising:

[0035] A historical data acquisition module is used to acquire vehicle historical information data, road geographic information data and historical abnormal status data;

[0036] A feature extraction module, used to extract features from each selected area of ​​each target road according to the vehicle historical information data, the road geographic information data and the historical abnormal state data, to obtain corresponding feature values, wherein the feature values ​​reflect basic parameter attributes of the current road and the driving trajectory of the vehicle;

[0037] A detection library construction module, used to construct an anomaly detection library for each target road using each of the feature values;

[0038] The area determination module is used to obtain the real-time driving data of the vehicle and determine the driving area of ​​the vehicle on the current road during the driving process of the vehicle;

[0039] A feature value determination module, used to determine a corresponding target feature value in the anomaly detection library based on the driving area;

[0040] An anomaly detection module, used to generate an anomaly detection result of vehicle driving based on the target feature value and the vehicle navigation position information in the real-time driving data;

[0041] The strategy execution module is used to execute the corresponding early warning strategy based on the abnormal detection result.

[0042] Yet another embodiment of the present invention provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the navigation-based ground anomaly warning method as described above when executing the computer program.

[0043] Yet another embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the navigation-based ground abnormality warning method as described above is implemented.

[0044] Compared with the prior art, the embodiments of the present invention have the following advantages:

[0045] (1) Since the real-time acquisition of geological disaster data is very critical for vehicle early warning, the present invention determines whether the vehicle is in an abnormal ground state based on the calculated characteristic values ​​of each area of ​​the target road and the acquired vehicle driving data. The real-time and detailed data of the vehicle dynamics provided to the server can enable the system to respond quickly to any potential changes or abnormal situations, and realize accurate road feature analysis, which helps to more accurately judge whether the behavior of the vehicle under different road conditions is in line with expectations, thereby improving the accuracy and pertinence of the early warning.

[0046] (2) Comprehensive judgment is made by combining regional feature values, vehicle location information and anomaly detection models. Different algorithms or machine learning models are used to identify whether the vehicle is in an abnormal ground state. This can more comprehensively consider various factors, reduce false alarms and missed alarms, and provide early warnings to vehicles behind, thereby improving the efficiency and accuracy of early warnings, and thus enabling early intervention before the vehicle is actually in danger, thereby reducing the risk of accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of a ground abnormality warning method based on navigation in one embodiment of the present invention;

[0048] Figure 2 It is a schematic diagram of the regional feature value extraction process in one embodiment of the present invention;

[0049] Figure 3 is a schematic diagram of a ground anomaly detection method in one embodiment of the present invention;

[0050] Figure 4 It is a structural schematic diagram of a ground abnormality warning system based on navigation in one embodiment of the present invention;

[0051] Figure 5 It is a structural block diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0054] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0055] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0056] An embodiment of the present invention provides a ground abnormality warning method based on navigation. For details, see Figure 1 , Figure 1 The flowchart of the ground abnormality warning method based on navigation in one embodiment of the present invention is shown, which specifically includes the following steps:

[0057] S1. Acquire vehicle historical information data, road geographic information data and historical abnormal status data. Specifically,

[0058] The embodiment of the present invention obtains the stored historical data through the historical terminal device, including vehicle historical information data, road geographic information data and historical abnormal state data; the road geographic information data includes the types of various roads where the vehicle is located, such as expressways, national roads, provincial roads and urban roads, road surface materials, road slopes, curve information, traffic signs and signal light locations, etc., while the historical abnormal state data refers to the historical data such as vehicle traffic accidents, time, weather and road conditions caused by abnormal phenomena on the ground, such as landslides, ground collapses and bridge ruptures. In the embodiment of the present invention, the vehicle historical information data can be collected through terminal devices such as vehicle-mounted sensors, such as GPS, accelerometers or gyroscopes, vehicle-mounted information systems, such as OBD data, and user behavior data (braking frequency, steering angle, etc.), the road geographic information data can be mainly obtained from the government map service system or map service terminal, and the historical abnormal state data can be obtained from channels such as historical accident records, user feedback and road maintenance records.

[0059] S2. Perform feature extraction on each selected area of ​​each target road according to the vehicle historical information data, the road geographic information data and the historical abnormal state data to obtain corresponding feature values, wherein the feature values ​​reflect the basic parameter attributes of the current road and the driving trajectory of the vehicle.

[0060] According to the above analysis, by extracting the features of each selected area of ​​each target road from the three types of data, namely, vehicle historical information data, road geographic information data, and historical abnormal status data, it is possible to comprehensively evaluate the traffic conditions of each selected area of ​​each target road from different perspectives. For example, by combining the average speed of the vehicle, the average height of the road, and the frequent accident records in the history of the area, the characteristic value is calculated, so that the abnormal ground safety hazards and traffic accidents in the area can be reflected and indicated. Such analysis results provide a scientific basis for the ground warning of the vehicle so that the driver can take corresponding measures later.

[0061] In this embodiment, the regional characteristic values ​​include: the average width of the road, the average height, the median height, the standard deviation of the height, the absolute median difference of the height, the percentiles of the height, and the frequency distribution curve of the height, etc., which can fully reflect the fluctuations in the road geographic information data after the occurrence of geological disasters, the driving trajectory of the vehicle, and the characteristic quantities of the basic parameter attributes of the current road.

[0062] The following is a detailed description of the process of obtaining the characteristic value, including steps S21-S23. Figure 2 , Figure 2 FIG. 1 is a schematic diagram of a regional feature value extraction process in one embodiment of the present invention.

[0063] S21. Measure and extract basic parameter attributes of each target road according to the road geographic information data to obtain a first eigenvalue.

[0064] Specifically, the first eigenvalue is calculated in a road measurement mode, that is, the regional eigenvalue is obtained by road measurement. In an embodiment of the present invention, the basic parameter attributes of the road refer to parameter attributes such as the length, width, slope, curvature and road intersection layout of the road.

[0065] Furthermore, the road measurement mode of this embodiment is to directly or indirectly measure the road on the spot through professional road measurement equipment and methods. For example, the basic parameters such as the length and width of the road are directly measured using measurement tools (such as steel rulers and laser rangefinders), or the complex parameters such as the slope and curvature of the road are calculated by measuring elevation points or using GPS technology in combination with professional software to achieve indirect measurement. A three-dimensional scanner can also be selected to perform a full-scale scan of the road to obtain a three-dimensional model of the road and its surrounding environment to obtain accurate characteristic values ​​of each area of ​​the road. This method is usually suitable for newly built roads or scenarios that require high-precision data. Therefore, the data obtained can effectively reflect the characteristics of each area of ​​the road, thereby improving the accuracy of the judgment.

[0066] S22. Calculate characteristic values ​​of different modes respectively according to the vehicle historical information data to obtain a second characteristic value; the vehicle historical information data includes historical vehicle type data and historical vehicle position data.

[0067] In the embodiment of the present invention, the acquisition of the second characteristic value mainly includes three modes, which are calculated through historical terminal data. Specifically, the historical terminal data mode uses the historically accumulated vehicle or terminal device reporting data to indirectly infer the characteristic values ​​of each area of ​​the road through data analysis. This method relies on a large amount of long-term data accumulation and is suitable for roads that have been built and have a certain data foundation.

[0068] Further, the modes include a first mode, a second mode and a third mode.

[0069] First, in the first mode, a second characteristic value is obtained based on the vehicle historical information data;

[0070] In this embodiment, considering that different types of vehicles react differently and suffer different damage when facing different geological disasters, and the historical vehicle location data includes the longitude, latitude and altitude of the vehicle, in this method, the reported data (including location, altitude, etc.) of all terminal devices are regarded as coming from the same type of vehicle or device, and no distinction is made between vehicle types. The characteristic values ​​of each area of ​​the road, such as the average height and median, are directly calculated based on these data. This method is simple and easy to implement, and the data processing is also very simple and convenient.

[0071] Secondly, in the second mode, the historical vehicle type data is classified, and characteristic values ​​are calculated based on different vehicle types to obtain second characteristic values;

[0072] In this method, the data is first classified into different vehicle types, such as small cars, large cars, trucks, or different internal and external structures of vehicles, based on the vehicle type information in the reported data. Then, the characteristic values ​​of each area of ​​the road are calculated for each vehicle type. This method can more accurately reflect the actual driving conditions of different types of vehicles on the road, so the calculated characteristic values ​​can reflect the different warning states of different types of vehicles when facing ground anomalies.

[0073] Furthermore, in the third mode, the height data of the historical vehicle position data is classified, and characteristic values ​​are calculated based on different height data to obtain a second characteristic value.

[0074] Among them, in this embodiment, the classification method based on different height data includes dividing different height intervals. In this method, the vehicle type is not directly distinguished, but several height intervals are artificially set according to the height information in the reported data, such as low, medium, and high, and then the data is classified according to these height intervals, and the characteristic values ​​of each area of ​​the road are calculated for the data in each height interval. This method can take into account the differences in vehicle positions to a certain extent and provide data support for the construction of the model to be carried out below.

[0075] It also includes dividing the peak and trough distribution of height data. In this method, similarly, based on the height information in the height data of historical vehicle position data, statistical methods such as histogram analysis and cluster analysis are used to automatically identify the peaks and troughs of height, thereby automatically dividing the height intervals. Based on the data of each automatically divided height interval, the characteristic values ​​of each area of ​​the road are calculated respectively. This method can more objectively reflect the distribution of vehicle heights.

[0076] S23, analyzing the historical abnormal state data, and counting the frequency, type, and time data of abnormal occurrences in each selected area of ​​each target road to obtain a third characteristic value.

[0077] This embodiment analyzes historical abnormal state data such as landslides, ground collapses, bridge fractures, etc., the duration of abnormalities, weather conditions, and road conditions, and counts the frequency, type, and time data of abnormalities in each selected area of ​​each target road, and classifies and sorts these data according to different areas of the road. Specifically, the abnormal types are the above-mentioned landslides, ground collapses, bridge fractures, etc., and according to different types, the number or proportion of abnormalities in different areas and different time periods is counted to obtain frequency data, and time data is obtained by analyzing the high-incidence period of abnormalities, seasonal changes, etc.

[0078] This embodiment forms a third eigenvalue by statistics and analysis of the above data, which provides an important basis for predicting and warning of ground anomalies that may occur in the future.

[0079] The embodiment of the present invention provides two different mode calculation methods, namely the road actual measurement mode and the historical terminal data mode. The server can flexibly and accurately calculate the characteristic values ​​of each area of ​​each road, providing strong support for the judgment of ground abnormality warning of the vehicle.

[0080] S3. Using each of the characteristic values, construct an anomaly detection library for each of the target roads.

[0081] The obtained characteristic values ​​of various types are integrated to construct an anomaly detection library, which is used to determine the characteristic values ​​of the area where the subsequent vehicle is located during real-time driving.

[0082] S4-S5, during the driving process of the vehicle, real-time driving data of the vehicle is obtained, and the driving area of ​​the vehicle on the current road is determined; the corresponding target feature value in the anomaly detection library is determined based on the driving area.

[0083] First, during the driving process, the road and area where the vehicle is currently located need to be determined through the data obtained by the historical terminal. Specifically:

[0084] During the driving process of the vehicle, the real-time driving data is collected in real time, and the real-time driving data includes the navigation position information of the vehicle, the vehicle speed, the vehicle driving direction and the vehicle type;

[0085] In this embodiment, the vehicle terminal equipment such as the vehicle-mounted GPS system is used to obtain the vehicle's precise location information and information such as speed and direction in real time, and the vehicle-mounted speed sensor can also be used to directly obtain the vehicle's speed data.

[0086] Determine the road where the vehicle is currently located and the corresponding driving area according to the vehicle navigation position information and the road geographic information data;

[0087] In this embodiment, after the vehicle's location and other data are acquired in real time, the road where the vehicle is currently located and the driving area corresponding to the road are confirmed in combination with map technology and road geographic information data.

[0088] Next, the server is responsible for receiving and processing the data from the vehicle terminal, performing comparative analysis of the target feature values ​​based on the confirmed driving area and the anomaly detection library, and obtaining the regional feature values ​​of the area where the vehicle is located at this time for anomaly detection and early warning analysis.

[0089] S6. Generate a vehicle driving abnormality detection result based on the target feature value and the vehicle navigation position information in the real-time driving data.

[0090] In this embodiment, an anomaly detection algorithm is selected to identify anomalies in real-time driving data. The algorithm determines whether there are ground anomalies based on the real-time data of vehicle driving and the target characteristic value, thereby providing a real-time warning. Based on the anomaly detection results, corresponding follow-up measures can be taken, such as notifying the driver to pay attention, adjusting the driving route, or strengthening monitoring to avoid accidents.

[0091] The following is a detailed description of the above ground anomaly detection process:

[0092] First, the target feature value and the vehicle navigation position information are input into a pre-trained anomaly detection model to determine whether the vehicle is currently in an abnormal ground state; see Figure 3 , Figure 3 FIG. 4 is a schematic diagram of a ground anomaly detection method in one embodiment of the present invention.

[0093] Specifically, in this embodiment, the ground anomaly detection method includes: a simple mode and an intelligent algorithm mode, wherein the simple mode: the height data of the vehicle and the feature value related to the height of the target area are input into a pre-trained anomaly detection model, which is trained by algorithms such as Z-score, Grubbs hypothesis test and box plot, and then determines whether the vehicle is in an abnormal state on the ground;

[0094] The intelligent algorithm mode, specifically, uses the characteristic values ​​of the target area, the type and navigation position information of the target vehicle, and the historical abnormal status data to input a pre-trained anomaly detection model. The model can be trained using algorithms such as KNN, BSCAN, and SVM, where the historical abnormal status data includes data that has been marked as abnormal.

[0095] Secondly, if the vehicle is currently in a ground abnormality state, the corresponding area is marked as a ground abnormality area, and an abnormality detection result is generated; the abnormality detection result includes the abnormality type, abnormal impact range and duration.

[0096] The choice of the two modes depends on whether there is historical data that has been calibrated to determine whether it is abnormal. If the terminal device does not have a large amount of historical data that has been calibrated to determine whether it is abnormal, you can choose the simple mode; if the terminal device has a large amount of historical data that has been calibrated to determine whether it is abnormal, you can choose the intelligent algorithm mode or the intelligent algorithm mode + simple mode to detect ground abnormalities.

[0097] S7. Execute a corresponding early warning strategy based on the abnormality detection result.

[0098] Specifically, after a detailed analysis of the abnormality detection results, the specific type, severity and cause of the ground abnormality are determined in real time, and appropriate early warning strategies are selected based on the abnormality detection results so that relevant drivers can avoid accidents.

[0099] The following is a detailed description of the above execution process:

[0100] If the vehicle is currently in a ground abnormality state, the vehicle is given a ground abnormality alarm prompt according to the generated abnormality detection result, and the ground abnormality alarm prompt includes a voice alarm and an LED flashing alarm;

[0101] The voice alarm uses the vehicle's built-in audio system to convey emergency information to the driver in the form of human voice or preset voice alarm tones. In the event of ground abnormalities, the system will issue clear and unambiguous voice prompts, and the prompt content will be fed back based on the type of abnormality, the scope of the abnormality's impact, and the duration. Such a voice alarm can directly attract the driver's attention and make him quickly aware of the current dangerous situation.

[0102] At the same time, the system will also flash the LED light groups installed on the outside and inside of the vehicle to warn. The LED light groups are usually located in conspicuous positions of the vehicle, such as the front, rear, roof and places inside the vehicle that are more conspicuous to the driver. When there is an abnormal alarm on the ground, the LED lights will flash at a specific frequency and color to visually warn surrounding vehicles, pedestrians and drivers.

[0103] After the abnormal alarm prompt is performed, a log is generated and recorded based on the abnormal detection result;

[0104] The purpose of logging in this embodiment is for subsequent analysis and tracing. By analyzing these logs, the accuracy and reliability of the anomaly detection system can be evaluated, potential problems can be discovered and optimized. At the same time, when necessary, these logs can also be provided as evidence to relevant departments or institutions to support accident investigation and responsibility determination.

[0105] Furthermore, in this embodiment, considering that if there is a ground anomaly during the driving process of the vehicle, the rear vehicle will also have an impact on the target vehicle. Therefore, timely warning of the rear vehicle can reduce the probability of accidents. Specifically,

[0106] First, if the vehicle is currently in a ground abnormality state, obtain the rear vehicle in the ground abnormality area, and calculate the distance between the target vehicle and the rear vehicle;

[0107] In this embodiment, the rear vehicles of all target vehicles within the area marked as ground anomalies are obtained, and based on the latitude and longitude of the vehicles and other information, a geospatial algorithm is used to calculate the straight-line distance between the two vehicles or the actual driving distance considering the road shape.

[0108] Next, it is determined whether the distance is lower than a preset abnormal distance threshold. If it is lower than the abnormal distance threshold, an alarm is issued to the rear vehicle indicating that the ground is abnormal.

[0109] This embodiment will preset an "abnormal distance threshold", which can be dynamically adjusted or statically set according to factors such as road type, vehicle speed, visibility, etc. The calculated distance between the rear vehicle and the current vehicle is compared with the abnormal distance threshold. Generally, the distance of a standard vehicle traffic accident requiring warning is usually set to 500m, 1000m or 2000m. The threshold is set according to this standard. If the distance is lower than this threshold, the system will issue an alarm reminder of ground abnormality to the driver of the rear vehicle through the vehicle display, sound alarm or other means. And the alarm information should include the specific location and type of the abnormality and the recommended response measures.

[0110] After the alarm is issued, the system should continuously monitor the ground conditions and vehicle position so as to update the alarm information or cancel the alarm when necessary. For example, when an abnormal situation occurs on the ground, the rear vehicle may experience abnormal driving due to unexpected influences. Therefore, the speed of the rear vehicle can be detected. If the speed of the rear vehicle is normal, the alarm can be cancelled.

[0111] In summary, the embodiment of the present invention provides an early warning method for ground abnormalities during vehicle driving. First, historical data of each area of ​​each road is collected to calculate regional characteristic values. Then, the driving trajectory of the current vehicle and the road condition information of the driving section are acquired and analyzed in real time through the navigation device to confirm the characteristic value of the target area. Then, advanced algorithms (such as SOS algorithm, DBSCAN algorithm and SVM algorithm, etc.) are used to process the collected data, identify potential ground abnormal areas and mark and warn. Through advanced algorithms and real-time data processing technology, rapid detection and early warning of ground abnormalities are achieved, the accuracy of early warning is improved, and false alarms and missed alarms are reduced. It is also determined whether the rear vehicle needs to be warned by the distance between the current vehicle and the rear vehicle. The warning range is not limited to the current vehicle location, but also covers all potentially affected vehicles on the navigation path. The embodiment of the present invention provides drivers with timely and accurate ground abnormality early warning information through the above method, which helps to avoid the occurrence and expansion of traffic accidents.

[0112] An embodiment of the present invention provides a system. For details, see Figure 4 , Figure 4 The figure shows a schematic diagram of the structure of a ground abnormality warning system based on navigation in one embodiment of the present invention;

[0113] A historical data acquisition module is used to acquire vehicle historical information data, road geographic information data and historical abnormal status data;

[0114] A feature extraction module, used to extract features from each selected area of ​​each target road according to the vehicle historical information data, the road geographic information data and the historical abnormal state data, to obtain corresponding feature values, wherein the feature values ​​reflect basic parameter attributes of the current road and the driving trajectory of the vehicle;

[0115] A detection library construction module, used to construct an anomaly detection library for each target road using each of the feature values;

[0116] The area determination module is used to obtain the real-time driving data of the vehicle and determine the driving area of ​​the vehicle on the current road during the driving process of the vehicle;

[0117] A feature value determination module, used to determine a corresponding target feature value in the anomaly detection library based on the driving area;

[0118] An anomaly detection module, used to generate an anomaly detection result of vehicle driving based on the target feature value and the vehicle navigation position information in the real-time driving data;

[0119] The strategy execution module is used to execute the corresponding early warning strategy based on the abnormal detection result.

[0120] like Figure 5 As shown, the embodiment of the present invention further provides a computer device, Figure 5 A structural block diagram of a preferred embodiment of a computer device provided by the present invention, the computer device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor implements the above-mentioned navigation-based ground anomaly warning method when executing the computer program.

[0121] Preferably, the computer program can be divided into one or more modules / units (such as computer program 1, computer program 2, ...), and the one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments that can complete specific functions, and the instruction segments are used to describe the execution process of the computer program in the computer device.

[0122] The processor may be a central processing unit (CPU), or other general-purpose processors, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor. The processor is the control center of the terminal device, and various parts of the terminal device are connected using various interfaces and lines.

[0123] The memory mainly includes a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function, etc., and the data storage area can store related data, etc. In addition, the memory can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, and a flash card (Flash Card), etc., or the memory can also be other volatile solid-state storage devices.

[0124] It should be noted that the above terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art will understand that Figure 5The structural block diagram is only an example of a terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. A person of ordinary skill in the art can understand that the implementation of all or part of the processes in the ground abnormality warning method based on navigation in the above-mentioned embodiment can be completed by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it may include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium may be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0125] Accordingly, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to perform the steps of the ground abnormality warning method based on navigation as described in the above embodiment, for example Figure 1 Steps S1 to S7 described in .

[0126] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A ground abnormality early warning method based on navigation, characterized in that: include: Obtain vehicle historical information data, road geographic information data and historical abnormal status data; According to the vehicle historical information data, the road geographic information data and the historical abnormal state data, feature extraction is performed on each selected area of ​​each target road to obtain a corresponding feature value, wherein the feature value reflects the basic parameter attributes of the current road and the driving trajectory of the vehicle; Using each of the characteristic values, construct an anomaly detection library for each of the target roads; During the driving process of the vehicle, the real-time driving data of the vehicle is obtained, and the driving area of ​​the vehicle on the current road is determined; Determining a corresponding target feature value in the anomaly detection library based on the driving area; Generate a vehicle driving abnormality detection result based on the target feature value and the vehicle navigation position information in the real-time driving data; Based on the abnormal detection result, a corresponding early warning strategy is executed.

2. The ground abnormality early warning method based on navigation according to claim 1 is characterized in that: The feature extraction is performed on each selected area of ​​each target road to obtain corresponding feature values, including: Extracting basic parameter attributes of each target road according to the road geographic information data to obtain a first eigenvalue; Calculate the characteristic values ​​of different modes respectively according to the vehicle historical information data to obtain a second characteristic value; the vehicle historical information data includes historical vehicle type data and historical vehicle position data; The historical abnormal state data is analyzed, and the frequency, type and time data of abnormal occurrence in each selected area of ​​each target road are counted to obtain a third characteristic value.

3. The ground abnormality early warning method based on navigation according to claim 2 is characterized in that: The calculating of characteristic values ​​of different modes respectively according to the vehicle historical information data to obtain the second characteristic value comprises: the modes comprise a first mode, a second mode and a third mode; In the first mode, a second characteristic value is obtained based on the vehicle historical information data; In the second mode, the historical vehicle type data is classified, and characteristic values ​​are calculated based on different vehicle types to obtain second characteristic values; In the third mode, the height data of the historical vehicle position data are classified, and characteristic values ​​are calculated based on different height data to obtain a second characteristic value.

4. The ground abnormality early warning method based on navigation according to claim 1 is characterized in that: The method of obtaining real-time driving data of the vehicle and determining the driving area of ​​the vehicle on the current road during the driving of the vehicle includes: During the driving process of the vehicle, the real-time driving data is collected in real time, and the real-time driving data includes the navigation position information of the vehicle, the vehicle speed, the vehicle driving direction and the vehicle type; The road where the vehicle is currently located and the corresponding driving area are determined according to the vehicle navigation position information and the road geographic information data.

5. The ground abnormality early warning method based on navigation according to claim 1 is characterized in that: The generating of the vehicle driving abnormality detection result based on the target feature value and the vehicle navigation position information in the real-time driving data includes: Inputting the target feature value and the vehicle navigation position information into a pre-trained anomaly detection model to determine whether the vehicle is currently in an abnormal ground state; If the vehicle is currently in a ground abnormality state, the corresponding area is marked as a ground abnormality area, and an abnormality detection result is generated; the abnormality detection result includes the abnormality type, the abnormality impact range and the duration.

6. The ground abnormality early warning method based on navigation according to claim 5 is characterized in that: The executing a corresponding early warning strategy based on the abnormal detection result includes: If the vehicle is currently in a ground abnormality state, the vehicle is given a ground abnormality alarm prompt according to the generated abnormality detection result, and the ground abnormality alarm prompt includes a voice alarm and an LED flashing alarm; After the abnormality alarm prompt is performed, a log is generated and recorded based on the abnormality detection result.

7. The ground abnormality early warning method based on navigation according to claim 5 is characterized in that: The executing a corresponding early warning strategy based on the abnormal detection result also includes: If the vehicle is currently in a ground abnormality state, obtain the rear vehicle in the ground abnormality area, and calculate the distance between the target vehicle and the rear vehicle; It is determined whether the distance is lower than a preset abnormal distance threshold. If the distance is lower than the abnormal distance threshold, an alarm is issued to the rear vehicle indicating that the ground is abnormal.

8. A ground abnormality warning system based on navigation, applied to the method according to claims 1 to 7, characterized in that: The system comprises: A historical data acquisition module is used to acquire vehicle historical information data, road geographic information data and historical abnormal status data; A feature extraction module, used to extract features from each selected area of ​​each target road according to the vehicle historical information data, the road geographic information data and the historical abnormal state data, to obtain corresponding feature values, wherein the feature values ​​reflect basic parameter attributes of the current road and the driving trajectory of the vehicle; A detection library construction module, used to construct an anomaly detection library for each target road using each of the feature values; The area determination module is used to obtain the real-time driving data of the vehicle and determine the driving area of ​​the vehicle on the current road during the driving process of the vehicle; A feature value determination module, used to determine a corresponding target feature value in the anomaly detection library based on the driving area; An anomaly detection module, used to generate an anomaly detection result of vehicle driving based on the target feature value and the vehicle navigation position information in the real-time driving data; The strategy execution module is used to execute the corresponding early warning strategy based on the abnormal detection result.

9. A computer device, characterized in that: It comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the navigation-based ground anomaly warning method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the navigation-based ground abnormality warning method as described in any one of claims 1 to 7 is implemented.

Images