A vehicle driving safety management method, system and storage medium

Abstract

The application provides a vehicle driving safety management method and system and a storage medium, relates to the technical field of vehicle driving safety management, and comprises the following steps: collecting state data of a target vehicle through a vehicle-mounted sensor set to obtain a vehicle real-time state data set; performing pretreatment to obtain a vehicle standard state data set; performing multi-risk synchronous identification according to the vehicle standard state data set to obtain a plurality of risk event identification results, wherein the plurality of risk event identification results have a plurality of risk scores; performing risk level evaluation on the plurality of risk scores according to a preset risk alarm index to obtain a plurality of risk levels; and performing risk event processing according to the plurality of risk levels according to a preset multi-level risk response mechanism. The application solves the technical problem that traditional driving safety management is highly dependent on manual observation or simple data recording, cannot realize real-time and comprehensive monitoring, causes feedback lag on the bad behaviors of drivers, and further causes insufficient safety.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle driving safety management, and in particular to a vehicle driving safety management method, system and storage medium. BACKGROUND

[0002] With the wide application of commercial vehicles in the logistics, engineering and other industries, driving safety and risk control have become the key link of enterprise management. The traditional vehicle driving safety management relies on manual observation and simple data recording, which is difficult to identify potential risks in real time and effectively, and the feedback to the bad behavior of the driver is lagging behind. This way not only reduces the driving safety, but also may lead to the increase of the operating cost of the enterprise and the rise of the accident rate.

[0003] In recent years, with the rapid development of sensor technology, Internet of Things and artificial intelligence, intelligent driving behavior monitoring systems based on real-time data collection and analysis have emerged. Such systems can monitor the driver's behavior in real time, such as smoking, fatigue driving, using mobile phones, sudden braking and sudden acceleration, and identify potential risky behavior through data analysis. However, the existing technology still has deficiencies in risk information generation and feedback mechanism, and cannot achieve comprehensive and timely risk control. SUMMARY

[0004] The present application provides a vehicle driving safety management method, system and storage medium, which aims to solve the technical problem that the traditional driving safety management relies on manual observation or simple data recording, which cannot achieve real-time and comprehensive monitoring, leading to lag feedback to the bad behavior of the driver, and further leading to insufficient safety.

[0005] The first aspect of the present application provides a vehicle driving safety management method, which comprises: collecting state data of a target vehicle through a set of vehicle-mounted sensors to obtain a set of real-time state data of the vehicle; preprocessing the set of real-time state data of the vehicle to obtain a set of standard state data of the vehicle; performing multi-risk synchronous identification according to the set of standard state data of the vehicle to obtain a plurality of risk event identification results, wherein the plurality of risk event identification results have a plurality of risk scores; performing risk level assessment on the plurality of risk scores according to a preset risk alarm index to obtain a plurality of risk levels; and performing risk event processing according to the plurality of risk levels according to a preset multi-level risk response mechanism.

[0006] In a second aspect, the application discloses a vehicle driving safety management system, which is used for the vehicle driving safety management method, and comprises a data collection module, a preprocessing module, a multi-risk synchronous identification module, a risk level assessment module and a risk event processing module.

[0007] In a third aspect, the application discloses a storage medium, which stores a computer program, and the computer program is executed by a processor to implement any step of the first aspect.

[0008] The one or more technical solutions provided in the application have at least the following technical effects or advantages:

[0009] The vehicle real-time state data set is obtained by collecting the state data of the target vehicle through the vehicle sensor set, which provides accurate data sources and provides sufficient data support for subsequent risk identification and analysis. The standardized data set is obtained by preprocessing the collected vehicle real-time state data, which guarantees the accuracy and reliability of subsequent analysis and risk assessment results. The multi-risk synchronous identification of the standard state data set can identify multiple potential risk events at the same time and assign a risk score to each event. This synchronous identification can comprehensively evaluate various potential dangers in the vehicle driving process and improve the accuracy and coverage of risk identification. The multiple risk levels are generated by evaluating the risk scores according to the preset risk alarm indicators. This evaluation can accurately distinguish which events are urgent and which events are relatively minor, thereby providing a basis for the subsequent response mechanism and guaranteeing the orderliness of risk management. According to the multiple risk levels obtained by evaluation, the risk events are processed according to the preset multi-level risk response mechanism. Different levels of response measures are automatically executed according to different risk levels. This multi-level response mechanism ensures that high-risk events are timely and effectively processed, and low-risk events can also be monitored and prevented as necessary, thereby realizing intelligent and automatic risk processing.

[0010] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0011] Figure 1 This is a schematic diagram of a vehicle driving safety management method provided in an embodiment of this application.

[0012] Figure 2 This is a schematic diagram of a vehicle driving safety management system provided in an embodiment of this application.

[0013] Figure labeling: Data acquisition module 10, preprocessing module 20, multi-risk synchronous identification module 30, risk level assessment module 40, risk event processing module 50. Detailed Implementation

[0014] This application provides a vehicle driving safety management method that solves the technical problem that traditional driving safety management relies heavily on manual observation or simple data recording, which cannot achieve real-time and comprehensive monitoring, resulting in delayed feedback on drivers' bad behavior and thus insufficient safety.

[0015] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0016] Example 1, as Figure 1 As shown in the figure, this application provides a vehicle driving safety management method, the method including:

[0017] The system collects status data of the target vehicle using a set of onboard sensors to obtain a set of real-time vehicle status data.

[0018] The vehicle sensor suite includes different types of sensors used to collect data about the vehicle and its surrounding environment. The main function of these sensors is to monitor various status parameters of the vehicle in real time, including but not limited to GPS modules, camera systems, gyroscope sensors, and radar sensors. They are used to collect vehicle location information and driving speed, monitor driver behavior and road environment, and detect dynamic attitude changes of the vehicle. The data collected by all sensors is integrated and stored into a real-time vehicle status data set, which contains various dynamic information of the vehicle as the basis for subsequent processing.

[0019] The real-time vehicle status data set is preprocessed to obtain a standard vehicle status data set.

[0020] The vehicle real-time state data set is preprocessed, wherein the preprocessing includes data cleaning and data standardization. Specifically, in the data collection stage, there may be some noise or invalid data, such as missing values, abnormal values, redundant data, etc. The purpose of data cleaning is to ensure the quality of data so that subsequent analysis can draw accurate conclusions. The specific cleaning steps include removing redundant data, correcting erroneous data, filling missing data, and detecting and processing abnormal values. After cleaning the data, the next step is to standardize the data. The purpose of standardization is to convert different types of sensor data into a comparable standard form, so that different data sources can be effectively compared and analyzed. Common standardization methods include normalization, which scales the data to a fixed range, such as between 0 and 1, to divide the data into the same scale for comparison. The standard state data set obtained after preprocessing has higher data quality and can be used for subsequent analysis such as multi-risk synchronous identification.

[0021] According to the vehicle standard state data set, multi-risk synchronous identification is performed to obtain a plurality of risk event identification results, wherein the plurality of risk event identification results have a plurality of risk scores.

[0022] A plurality of risk factors are obtained, which are key factors affecting vehicle driving safety, including driver behavior such as speeding, sudden braking, and sharp turning; vehicle status such as whether the brake system is normal, tire wear, fuel level, etc.; road environment such as weather conditions, road conditions, traffic flow, etc.; external factors such as the behavior of other vehicles, the presence of pedestrians, etc.

[0023] The plurality of risk factors are analyzed to assess their potential impact on vehicle safety. Through data mining or machine learning models, combined with historical data and existing vehicle status, the risk characteristics of these factors in different scenarios are analyzed, for example, speeding may pose a greater risk in rainy weather, and night driving may have a higher risk of fatigue driving. According to the influence degree of different risk factors, each factor is assigned a weight.

[0024] Based on the vehicle standard state data set and the weights of the plurality of risk factors, multi-risk synchronous identification is performed, which means that all identified risk factors are evaluated simultaneously, and the risk score of each risk event is calculated by considering the weights of each factor. These risk scores reflect the severity of each risk event.

[0025] According to a preset risk warning index, the plurality of risk scores are evaluated for risk level to obtain a plurality of risk levels.

[0026] The preset risk warning index includes a threshold value set in advance, which can be set according to specific industry standards or experimental data, and is used to evaluate the severity of the risk score. For example, a score below 30 is set as a low risk, and usually does not require immediate response; a score between 30 and 70 is set as a medium risk, which needs attention and may take some preventive measures; a score above 70 is set as a high risk, which needs immediate response and may start an emergency handling program.

[0027] According to different risk scores, risk level evaluation is performed according to the preset risk warning index. Each risk event is assigned a risk level according to its score. For example, an emergency brake may have a higher risk score, while other smaller events may have a lower risk score.

[0028] According to the plurality of risk levels, a multi-level risk response mechanism is preset for risk event processing.

[0029] The preset multi-level risk response mechanism defines different measures to be taken at different risk levels. For example, a low risk can be reminded by a warning to the driver, and some preventive measures are suggested, such as reminding the driver to pay attention to road conditions through a vehicle display or sound; a medium risk requires further intervention, such as issuing a more intense warning to remind the driver to slow down and maintain a safe distance; a high risk requires immediate emergency response measures, such as automatically starting emergency braking, adjusting vehicle speed, and enabling automatic obstacle avoidance functions in high-risk situations. These risk event processing measures can range from simple warnings to complex automatic interventions, ensuring the safety of vehicle travel.

[0030] Further, the method for collecting state data of a target vehicle through a set of vehicle-mounted sensors to obtain a set of real-time state data of the vehicle includes:

[0031] The set of vehicle-mounted sensors includes but is not limited to a GPS module, a camera system, a gyroscope sensor, and a radar sensor. The GPS module is used to collect vehicle location information and real-time driving speed to obtain vehicle driving state data. The camera system is used to monitor the behavior state of the driver, the road surface environment, and the front obstacles to obtain driver state data and road environment state data. The gyroscope sensor is used to detect the dynamic attitude change and direction adjustment of the vehicle to obtain vehicle attitude state data. The radar sensor is used to detect surrounding objects, measure object distance and relative speed, and generate surrounding environment state data. Data integration is performed to obtain the set of real-time state data of the vehicle.

[0032] The vehicle-mounted sensor set includes but is not limited to a GPS module, a camera system, a gyroscope sensor, and a radar sensor, wherein the GPS module is used to collect the position information and driving speed of the vehicle, the camera system is used to monitor the driver's behavior, road environment, and front obstacles, etc., the gyroscope sensor is used to detect the dynamic attitude change, steering, etc. of the vehicle, and the radar sensor is used to detect surrounding objects, measure object distance and relative speed, etc.

[0033] The GPS module calculates the specific position (latitude and longitude) and driving speed of the vehicle by receiving signals from satellites. It determines the geographical position of the vehicle by communicating with multiple satellites using the triangulation principle. The obtained vehicle driving state data includes the current position and driving speed of the vehicle. These information is very crucial for judging the driving state of the vehicle. For example, the driving trajectory, driving direction, and whether there is abnormal behavior such as overspeeding or sudden deceleration can be analyzed according to the change trend of speed and position.

[0034] The camera system monitors the driver's behavior, road environment, and front obstacles in real time through cameras installed on the front, side, or inside the vehicle. These cameras combine image recognition algorithms and machine learning techniques to analyze captured image data. For example, by monitoring the driver's facial expressions, eye movements, head positions, etc., it can identify whether the driver is focused on driving, such as whether they are dozing off, distracted (e.g., talking on the phone), or complying with traffic rules. The camera collects driver state data and road environment state data to analyze whether the driver's behavior is safe and whether the road environment is dangerous in real time. These data can help evaluate the driver's behavior pattern, attention concentration, and road safety.

[0035] The gyroscope sensor is a device used to measure the angular change of an object. It can detect the pitch angle (up and down movement), yaw angle (vehicle turning left and right), and roll angle (vehicle leaning) of the vehicle in real time. Through these measurements, the gyroscope can determine the dynamic attitude of the vehicle, including whether the vehicle has made a sharp turn, emergency braking, or other attitude changes during driving. The vehicle attitude state data of the gyroscope sensor can provide information on the dynamic stability of the vehicle, such as whether it has slipped, the body inclination or attitude abnormality when turning, etc. This information is crucial for determining whether the vehicle has dangerous driving behavior.

[0036] The radar sensor detects the surrounding objects by emitting electromagnetic waves and receiving the reflected signals. The radar signals are reflected by the surrounding objects, and the position, distance, relative speed, etc. of the objects are determined by calculating the time difference and intensity of the reflected signals. The surrounding environment state data collected by the radar sensor includes the position, distance, and speed of the objects around the vehicle, which is very important for collision warning, automatic braking, adaptive cruise control, etc. By monitoring the surrounding environment in real time, the radar can help judge the motion trend and potential risks of the surrounding objects.

[0037] The data collected by all sensors is integrated to obtain a set of vehicle real-time state data. The data of these sensors complement each other, providing comprehensive information support for real-time state monitoring, risk assessment, and safety management of the vehicle.

[0038] Further, the vehicle real-time state data set is preprocessed to obtain a vehicle standard state data set, the method comprising:

[0039] The vehicle real-time state data set is subjected to data cleaning processing to obtain a cleaned vehicle real-time state data set, wherein the data cleaning processing includes removing redundant data, correcting erroneous data, filling missing data, and detecting and processing outliers; the cleaned vehicle real-time state data set is subjected to data standardization processing to obtain the vehicle standard state data set.

[0040] The data cleaning processing includes removing redundant data, correcting erroneous data, filling missing data, and detecting and processing outliers, wherein removing redundant data is to delete repeated or multiple recorded values, for example, multiple sensors may collect the same information in a very short time, at this time, one valid record is retained and the redundancy is removed; correcting erroneous data, if the sensor fails during data collection, it may cause data errors, for example, the vehicle speed is displayed as negative, or the GPS positioning deviation is large, at this time, the algorithm is corrected or marked as an outlier; filling missing data, in some cases, some sensors may not provide data in time, resulting in missing values, interpolation or other data filling methods can be used to handle missing data to ensure data continuity; outlier detection and processing, some extreme data (for example, the vehicle speed jumps to an abnormal high value for a moment) may be caused by sensor failure or extreme conditions, and these outliers are identified and processed by statistical analysis methods such as Z-score method. After data cleaning processing, a cleaned vehicle real-time state data set is obtained to ensure the quality of the data and improve the accuracy of subsequent analysis.

[0041] The data standardization processing is performed on the real-time vehicle state data set, and the standardization method includes a normalization method, which scales the data to a fixed range, for example, between 0 and 1, which is suitable for the case of needing to compare in the same scale, or a standardization method, which converts the data into a standard normal distribution form with zero mean and unit variance, which is suitable for the case of large differences in data. After the data standardization processing, the vehicle standard state data set is obtained, and different types of sensor data are uniformly converted into a comparable standard form, so that different data sources can be effectively compared and analyzed.

[0042] Further, the multiple risk synchronous identification is performed according to the vehicle standard state data set, and multiple risk event identification results are obtained, wherein the multiple risk event identification results have multiple risk scores, and the method comprises:

[0043] The vehicle type is obtained, and a vehicle type influence coefficient is generated. The multiple risk factors are obtained, the risk characteristics of the multiple risk factors are analyzed, the weight distribution is performed according to the analysis result, and the multiple risk factor weights are generated. The vehicle standard state data set is subjected to multiple risk synchronous identification and risk score calculation according to the vehicle type influence coefficient and the multiple risk factor weights, and multiple risk event identification results are obtained, wherein the multiple risk event identification results have multiple risk scores.

[0044] Different types of vehicles, such as cars, trucks, SUVs, etc., have different behavior characteristics and risk factors in driving. For example, trucks are more likely to be affected by excessive load than cars, and SUVs are more likely to roll over due to high center of gravity. Therefore, when performing risk assessment, a vehicle type influence coefficient is first generated according to the type of vehicle. This coefficient can affect the weight distribution in subsequent risk assessment. The vehicle type influence coefficient is a coefficient generated according to the characteristics of the vehicle type for adjusting the risk identification and evaluation results. This coefficient can be obtained by analyzing historical data or expert experience.

[0045] Risk factors are key factors that affect driving safety, including but not limited to: driver behavior, such as speeding, sudden braking, sharp turning, etc.; vehicle state, such as whether the brake system is normal, tire wear degree, oil quantity, etc.; road environment, such as weather conditions, road conditions, traffic flow, etc.; external factors, such as the behavior of other vehicles, the appearance of pedestrians, etc.

[0046] The risk characteristic analysis of each risk factor focuses on the impact of each factor on vehicle safety in different situations. For example, "fatigue driving" in driver behavior may have a higher risk at night and during long driving, while it has less impact during the day and short driving; "wet road surface" in road environment has a greater impact on braking distance and vehicle stability, especially in rainy and snowy weather. The severity, frequency and impact range of each risk factor are analyzed through data mining technology, so as to assign a corresponding weight to each factor, generate multiple risk factor weights, and the purpose of weight assignment is to make high-risk, common and uncontrollable factors have a greater impact on the final risk score, while low-risk and rare factors have less impact on the score.

[0047] Through multi-risk synchronous identification, multiple possible risk events are identified at the same time. This process relies on machine learning algorithms such as classifiers, which can consider multiple factors such as vehicle state, driver behavior, road environment, etc. to identify multiple potential risk events. After identifying risk events, each risk event is scored according to the vehicle type influence coefficient and risk factor weight. Specifically, according to the weight of each risk factor, the risk degree contributed by it is weighted, and the final risk score is adjusted according to the vehicle type influence coefficient, for example, the risk of sharp turning of a large truck needs to be weighted to reflect its greater risk of rollover. The scores of multiple risk factors are integrated to obtain multiple risk scores, so that each risk event will get a risk score, which reflects the dangerous degree of each event.

[0048] Further, it also includes:

[0049] The frequency of risk events in a preset period is counted, and the multiple risk scores are compensated and adjusted according to the frequency of risk events.

[0050] The preset period is a fixed time range, which can be 12 hours, one day, one week, etc. and is set according to needs. In the preset period, the frequency of all identified risk events is counted, for example, in one day, the number of risk events such as sudden braking, overspeed, fatigue driving, etc. that have occurred can be recorded. For each risk event category, the number of occurrences is counted to obtain the risk event frequency.

[0051] The frequency of risk events affects their actual risk level. For example, some risk events, such as speeding, can occur frequently, but each occurrence may not be particularly dangerous; while other low-frequency events, such as a major collision, may be very dangerous each time they occur, but occur less frequently. If some risk events occur very frequently, their individual risk score can be reduced to avoid overemphasizing their risk due to their frequent occurrence, which can affect the system's judgment. For example, if a speeding event occurs every day, but is only a slight speeding, the score can be adjusted in some way to avoid overemphasizing its risk. Compensation adjustments can be made to multiple risk scores by assigning a decay factor to high-frequency risk events to reduce their risk scores, and assigning an amplification factor to low-frequency high-risk events to increase their scores.

[0052] Further, the risk event processing according to the plurality of risk levels and according to a preset multi-level risk response mechanism includes:

[0053] The preset multi-level risk response mechanism includes a multi-level risk event response mechanism and a common risk event response mechanism; the multi-level risk event response mechanism is used to process multi-level risk events in combination with the plurality of risk levels; and the common risk event response mechanism is used to process common risk events in combination with the plurality of risk levels.

[0054] The preset multi-level risk response mechanism is a mechanism for processing risk events in layers, responding to different levels according to the severity of the risk event, including a multi-level risk event response mechanism and a common risk event response mechanism. The multi-level risk event response mechanism includes multiple response levels, such as low-risk event response, medium-risk event response, and high-risk event response. The common risk event response mechanism is for common, low-risk events that occur frequently but generally do not cause serious consequences, so the response to these events is relatively simple.

[0055] In the multi-level risk response mechanism, risk events can be classified into low, medium, and high levels according to the risk level evaluation of the risk events in the previous steps, and different levels of response are performed according to the level of the risk event. For example, low-risk event response, such as warning the driver to pay attention but not requiring emergency response; medium-risk event response, such as prompting the driver to take certain actions, such as reducing speed, adjusting vehicle distance, or enabling auxiliary driving functions; and high-risk event response, such as immediately initiating emergency handling measures, such as automatic braking, alarm, or emergency steering. Through hierarchical processing, high-risk events are given priority and emergency response, while low-risk events only require routine warnings or auxiliary measures, which can effectively avoid waste of system resources while ensuring timely response to high-risk events.

[0056] For common risk events, such as slight speeding, frequent acceleration or braking, etc., which are relatively common but generally do not lead to serious accidents, such events are handled through a common risk response mechanism, which focuses on avoiding the evolution of events into more serious risks through prompts and preventive measures, for example, when the driver slightly exceeds the speed limit, suddenly brakes for a short time, etc., the driver can be reminded by the instrument panel, voice warning or vibration.

[0057] Further, the risk event processing according to the plurality of risk levels according to the preset multi-level risk response mechanism further comprises:

[0058] The preset multi-level risk response mechanism further comprises a preset multi-level risk uploading rule; a plurality of communication terminals are connected; and the plurality of risk levels are uploaded to the plurality of communication terminals according to the preset multi-level risk uploading rule.

[0059] The preset multi-level risk uploading rule is how to upload relevant information to different communication terminals according to the level of the risk event after the risk event is identified and graded. The basis for setting includes the level of the risk event, the type of the event, the frequency and timing of uploading, etc.

[0060] The plurality of communication terminals refers to all devices connected to the system that can receive risk data. According to the preset multi-level risk uploading rule, the plurality of risk levels are uploaded to the plurality of communication terminals. By way of example, the risk event is divided into three levels, the first level is the highest risk, and the third level is the lowest risk. When a first-level serious risk event occurs, the system will automatically dial the driver's preset emergency contact number and broadcast the current risk situation. For a second-level serious risk event, the system will generate a corresponding text reminder and convert it into a voice to deliver the reminder content by dialing the driver's phone. If a third-level risk event occurs, the system will send relevant text information to the driver's emergency contact number in the form of a short message or send a DingDing group message reminder. These responses can be set by the administrator, which is more flexible. At the same time, all serious risk events will be uploaded to the platform for the administrator to view.

[0061] Further, it further comprises:

[0062] Integrating the vehicle real-time state data set, the plurality of risk event identification results, the plurality of risk scores, and the plurality of risk levels, a vehicle driving safety management report is generated, wherein the vehicle driving safety management report comprises a first format and a second format; the first format is sent to a first user group, and the second format is sent to a second user group.

[0063] All the data obtained by the foregoing analysis, including the vehicle real-time state data set, the plurality of risk event identification results, the plurality of risk scores, the plurality of risk levels, etc., are summarized into a complete vehicle driving safety management report. According to different user needs, the content, data items and display mode in the report can be customized, and a first format and a second format are generated. Different formats are sent to corresponding user groups. Exemplarily, in the report summary, the data of the previous day is used for statistics, and two formats of reports are generated: a Word document and an H5 page. The Word document is mainly for vehicle fleet personnel to view, while the H5 page is for enterprise owners and management personnel. The report content can be accurate to the specific situation of each vehicle or can present the summary data of the entire vehicle fleet. Through these reports, the driver and the enterprise owner can intuitively and clearly understand the current risk situation, so as to take corresponding measures in time to ensure safety and efficiency.

[0064] In summary, the vehicle driving safety management method provided by the embodiments of the present application has the following technical effects:

[0065] The vehicle real-time state data set is obtained by collecting the state data of the target vehicle through the vehicle-mounted sensor set, which provides accurate data sources and provides sufficient data support for subsequent risk identification and analysis. The standardized data set is obtained by preprocessing the collected vehicle real-time state data, which ensures the accuracy and reliability of the subsequent analysis and risk assessment results. The plurality of potential risk events are identified simultaneously by performing multi-risk synchronous identification on the standardized state data set, and a risk score is assigned to each event. This synchronous identification can comprehensively evaluate various potential dangers in the vehicle driving process, improve the accuracy and coverage of risk identification. The plurality of risk levels are generated by evaluating the risk scores according to the preset risk alarm indicators. Such evaluation can accurately distinguish which events are urgent and which events are relatively minor, thereby providing a basis for the subsequent response mechanism and ensuring the orderliness of risk management. According to the plurality of risk levels obtained by evaluation, the risk events are processed according to the preset multi-level risk response mechanism. According to different risk levels, different levels of response measures are automatically executed. This multi-level response mechanism ensures that high-risk events are handled in time and effectively, while low-risk events can also be monitored and prevented as necessary, thereby realizing intelligent and automatic risk processing.

[0066] Embodiment two, based on the same inventive concept as the vehicle driving safety management method in the foregoing embodiments, as shown in Figure 2 The embodiments of the present application provide a vehicle driving safety management system, which comprises:

[0067] The data acquisition module 10 is configured to acquire vehicle real-time state data sets by using a set of vehicle-mounted sensors; the preprocessing module 20 is configured to preprocess the vehicle real-time state data sets to obtain vehicle standard state data sets; the multi-risk synchronous identification module 30 is configured to perform multi-risk synchronous identification according to the vehicle standard state data sets to obtain a plurality of risk event identification results, wherein the plurality of risk event identification results have a plurality of risk scores; the risk level evaluation module 40 is configured to perform risk level evaluation on the plurality of risk scores according to a preset risk alarm index to obtain a plurality of risk levels; and the risk event processing module 50 is configured to perform risk event processing according to the plurality of risk levels according to a preset multi-level risk response mechanism.

[0068] Further, the system further comprises a vehicle real-time state data set acquisition module to perform the following operation steps:

[0069] The set of vehicle-mounted sensors includes, but is not limited to, a GPS module, a camera system, a gyroscope sensor, and a radar sensor; the vehicle position information and the real-time driving speed are acquired by using the GPS module to collect the vehicle driving state data; the driver state data and the road environment state data are acquired by using the camera system to monitor the behavior state of the driver, the road surface environment, and the front obstacles; the vehicle attitude state data are acquired by using the gyroscope sensor to detect the dynamic attitude change and the direction adjustment of the vehicle; the surrounding environment state data are generated by using the radar sensor to detect the surrounding objects and measure the object distance and the relative speed; and the vehicle real-time state data sets are obtained by performing data integration.

[0070] Further, the system further comprises a vehicle standard state data set acquisition module to perform the following operation steps:

[0071] The cleaning vehicle real-time state data sets are obtained by performing data cleaning processing on the vehicle real-time state data sets, wherein the data cleaning processing includes removing redundant data, correcting error data, filling missing data, and detecting and processing abnormal values; and the vehicle standard state data sets are obtained by performing data standardization processing on the cleaning vehicle real-time state data sets.

[0072] Further, the system further comprises a risk score calculation module to perform the following operation steps:

[0073] Obtaining a vehicle type, generating a vehicle type influence coefficient; obtaining a plurality of risk factors, performing risk characteristic analysis on the plurality of risk factors, performing weight distribution according to the analysis result, and generating a plurality of risk factor weights; according to the vehicle type influence coefficient and the plurality of risk factor weights, performing multi-risk synchronous identification and risk score calculation on the vehicle standard state data set to obtain a plurality of risk event identification results, wherein the plurality of risk event identification results have a plurality of risk scores.

[0074] Further, the system further comprises a compensation adjustment module to perform the following operation steps:

[0075] Statistical risk event frequency in a preset period; according to the risk event frequency, the plurality of risk scores are compensated and adjusted.

[0076] Further, the system further comprises a risk event processing module to perform the following operation steps:

[0077] The preset multi-level risk response mechanism includes a multi-level risk event response mechanism and a general risk event response mechanism; according to the multi-level risk event response mechanism, combined with the plurality of risk levels, multi-level risk event processing is performed; according to the general risk event response mechanism, combined with the plurality of risk levels, general risk event processing is performed.

[0078] Further, the system further comprises a risk uploading module to perform the following operation steps:

[0079] The preset multi-level risk response mechanism further comprises a preset multi-level risk uploading rule; connecting a plurality of communication terminals; according to the preset multi-level risk uploading rule, the plurality of risk levels are uploaded to the plurality of communication terminals.

[0080] Further, the system further comprises a report sending module to perform the following operation steps:

[0081] Integrating the vehicle real-time state data set, the plurality of risk event identification results, the plurality of risk scores, and the plurality of risk levels, a vehicle driving safety management report is generated, wherein the vehicle driving safety management report includes a first format and a second format; the first format is sent to a first user group, and the second format is sent to a second user group.

[0082] Through the foregoing detailed description of the vehicle driving safety management method, those skilled in the art can clearly understand the vehicle driving safety management system in the embodiment. Since it corresponds to the method disclosed in the embodiment, it is described relatively simply, and the relevant part is referred to the method part description.

[0083] Embodiment three provides a storage medium, having stored thereon a computer program, which, when executed by a processor, implements the vehicle driving safety management method as described above.

[0084] The foregoing description of the disclosed embodiments enables a person skilled in the art to carry out or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Therefore, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vehicle driving safety management method characterized by comprising: The method comprises: Collecting state data of a target vehicle through a set of vehicle-mounted sensors to obtain a set of vehicle real-time state data; Preprocessing the set of vehicle real-time state data to obtain a set of vehicle standard state data; According to the set of vehicle standard state data, performing multi-risk synchronous identification to obtain a plurality of risk event identification results, wherein the plurality of risk event identification results have a plurality of risk scores; According to a preset risk alarm index, performing risk level evaluation on the plurality of risk scores to obtain a plurality of risk levels; According to the plurality of risk levels, performing risk event processing according to a preset multi-level risk response mechanism; Further comprising: Integrating the set of vehicle real-time state data, the plurality of risk event identification results, the plurality of risk scores, and the plurality of risk levels to generate a vehicle driving safety management report, wherein the vehicle driving safety management report comprises a first format and a second format, the first format and the second format comprise a Word document and an H5 page, the Word document is mainly for vehicle fleet personnel to view, the H5 page is for enterprise owners and management personnel, and the report content can be accurate to the specific situation of each vehicle or can present the summary data of the entire vehicle fleet; The first format is sent to a first user group, and the second format is sent to a second user group.

2. The vehicle driving safety management method according to claim 1, characterized by, The method for collecting state data of a target vehicle through a set of vehicle-mounted sensors to obtain a set of vehicle real-time state data comprises: The set of vehicle-mounted sensors comprises but is not limited to a GPS module, a camera system, a gyroscope sensor, and a radar sensor; Through the GPS module, vehicle position information and real-time driving speed are collected to obtain vehicle driving state data; Through the camera system, the behavior state of the driver, the road surface environment, and the front obstacles are monitored to obtain driver state data and road environment state data; Through the gyroscope sensor, the dynamic attitude change and direction adjustment of the vehicle are detected to obtain vehicle attitude state data; Through the radar sensor, surrounding objects, object distance, and relative speed are detected to generate surrounding environment state data; Data integration is performed to obtain the set of vehicle real-time state data.

3. The vehicle driving safety management method according to claim 1, characterized by, The method for preprocessing the set of vehicle real-time state data to obtain a set of vehicle standard state data comprises: Data cleaning processing is performed on the set of vehicle real-time state data to obtain a cleaned set of vehicle real-time state data, wherein the data cleaning processing comprises removing redundant data, correcting erroneous data, filling missing data, and detecting and processing abnormal values; Data standardization processing is performed on the cleaned set of vehicle real-time state data to obtain the set of vehicle standard state data.

4. The vehicle driving safety management method according to claim 1, characterized by, The method for performing multi-risk synchronous identification according to the set of vehicle standard state data to obtain a plurality of risk event identification results, wherein the plurality of risk event identification results have a plurality of risk scores, comprises: Obtaining a vehicle type to generate a vehicle type influence coefficient; Obtaining a plurality of risk factors, performing risk characteristic analysis on the plurality of risk factors, performing weight distribution according to the analysis results, and generating a plurality of risk factor weights; According to the vehicle type influence coefficient, the plurality of risk factor weights, a plurality of risk event identification results are obtained by performing multi-risk synchronous identification and risk score calculation on the vehicle standard state data set, wherein the plurality of risk event identification results have a plurality of risk scores.

5. The vehicle driving safety management method according to claim 4, characterized by, Also includes: Statistical risk event occurrence frequency in a preset period; According to the risk event occurrence frequency, the plurality of risk scores are compensated and adjusted.

6. The vehicle driving safety management method according to claim 1, characterized by, According to the plurality of risk levels, risk event processing is performed according to a preset multi-level risk response mechanism, including: The preset multi-level risk response mechanism includes a multi-level risk event response mechanism and a common risk event response mechanism; According to the multi-level risk event response mechanism, combined with the plurality of risk levels, multi-level risk event processing is performed; According to the common risk event response mechanism, combined with the plurality of risk levels, common risk event processing is performed.

7. The vehicle driving safety management method according to claim 1, characterized by, According to the plurality of risk levels, risk event processing is performed according to a preset multi-level risk response mechanism, and the method further includes: The preset multi-level risk response mechanism further includes a preset multi-level risk uploading rule; Connect multiple communication terminals; According to the preset multi-level risk uploading rule, the plurality of risk levels are uploaded to the plurality of communication terminals.

8. A vehicle driving safety management system characterized by comprising: A vehicle driving safety management method for implementing any one of claims 1-7, the system comprises: A data acquisition module for acquiring vehicle real-time state data set by collecting state data of target vehicle through vehicle-mounted sensor set; A preprocessing module for preprocessing the vehicle real-time state data set to obtain a vehicle standard state data set; A multi-risk synchronous identification module for performing multi-risk synchronous identification according to the vehicle standard state data set to obtain a plurality of risk event identification results, wherein the plurality of risk event identification results have a plurality of risk scores; A risk level evaluation module for evaluating the plurality of risk levels according to a preset risk alarm index to obtain a plurality of risk levels; A risk event processing module for performing risk event processing according to the plurality of risk levels according to a preset multi-level risk response mechanism.

9. A storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to realize the steps of the vehicle driving safety management method in any one of claims 1 to 7. The computer program is executed by the processor to realize the steps of the vehicle driving safety management method in any one of claims 1 to 7.

Images