Risk intervention method, device and equipment for commercial vehicle and storage medium

Abstract

The invention discloses a risk intervention method, device and equipment for a commercial vehicle and a storage medium, and relates to the technical field of commercial vehicles, and the method comprises the steps: obtaining a multi-dimensional risk factor of the commercial vehicle, the risk factor being derived from multi-source data, the multi-source data comprises vehicle data of the commercial vehicle, external environment data of the vehicle and state data of a driver; predicting a risk type and a risk level of the commercial vehicle based on the multi-dimensional risk factors; and executing a corresponding intervention strategy based on the risk type and the risk level. Namely, according to the multi-dimensional risk factors, the driving risk of the commercial vehicle is predicted so as to accurately determine the risk type and the risk level of the commercial vehicle, the intervention strategy needing to be executed is determined according to the risk type and the risk level, effective intervention aiming at the driving risk is achieved, and therefore the driving safety of the commercial vehicle is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of commercial vehicles, in particular to a risk intervention method, device and equipment of a commercial vehicle and a storage medium. BACKGROUND

[0002] With the rapid development of new energy technology, commercial vehicles are widely used in public transportation. Since the working conditions of commercial vehicles are complex during driving, the driving risk is high, therefore, it is necessary to intervene in the driving of the commercial vehicle when there is a driving risk.

[0003] At present, most of the driving risk interventions for commercial vehicles are designed for fuel vehicles, and the basis for risk identification and intervention measures is usually single. Since the working conditions of commercial vehicles are complex during driving, the driving risk of commercial vehicles cannot be effectively intervened according to the single intervention measures or risk identification basis, thereby reducing the driving safety of commercial vehicles.

[0004] The above content is only used to assist in understanding the technical solutions of the present application and does not represent the acknowledgement of the above content as prior art. SUMMARY

[0005] The main purpose of the present application is to provide a risk intervention method for a commercial vehicle, which aims to solve the technical problem that the driving risk of a commercial vehicle cannot be effectively intervened according to a single intervention measure or risk identification basis, thereby reducing the driving safety of the commercial vehicle.

[0006] To achieve the above purpose, the present application provides a risk intervention method for a commercial vehicle, applied to the cloud, which comprises:

[0007] Obtaining multi-dimensional risk factors of a commercial vehicle, wherein the risk factors are derived from multi-source data, and the multi-source data includes vehicle data, external environment data and state data of the driver of the commercial vehicle;

[0008] Based on the multi-dimensional risk factors, predicting the risk type and risk level of the commercial vehicle;

[0009] Based on the risk type and risk level, executing a corresponding intervention strategy.

[0010] In an embodiment, the prediction of the risk type of the commercial vehicle further comprises:

[0011] Receiving a preliminary prediction result of the commercial vehicle based on the multi-dimensional risk factors after preliminary prediction by an edge computing unit;

[0012] If the preliminary prediction result is that there is a driving risk, the risk type of the vehicle is obtained from the preliminary prediction result.

[0013] In an embodiment, the step of predicting the risk level of the commercial vehicle based on the multi-dimensional risk factors comprises:

[0014] determining whether there is distracted driving or fatigue driving of the driver in the risk types;

[0015] if so, determining the number of risks associated with the distracted driving or the fatigue driving from the risk types;

[0016] if the number of risks does not exceed a preset number, obtaining the driving speed of the vehicle from the multi-dimensional risk factors;

[0017] determining the risk level of the vehicle based on the interval to which the driving speed belongs.

[0018] In an embodiment, the step of obtaining the multi-dimensional risk factors of the commercial vehicle further comprises:

[0019] when it is necessary to score the driving state of the driver, obtaining multi-source data recorded in a preset period;

[0020] determining the driving coordination, mental state, driving smoothness, and work intensity of the driver in the preset period based on the multi-source data in the preset period, and obtaining the violation record of the driver;

[0021] based on the driving coordination, the mental state, the driving smoothness, the work intensity, and the violation data, evaluating the risk driving of the driver to obtain a driving analysis report of the driver.

[0022] In an embodiment, the step of determining the driving coordination, the driving smoothness, and the work intensity of the driver in the preset period based on the multi-source data in the preset period comprises:

[0023] based on the environmental data of the vehicle in the recorded multi-source data, analyzing the violation and management compliance of the driver to determine the driving coordination of the driver in the preset period;

[0024] based on the operating state data of the vehicle in the recorded multi-source data, analyzing the smoothness of the driver's operation to determine the driving smoothness of the driver in the preset period, the operating state data including acceleration and deceleration behavior data, steering operation data, braking behavior data, speed control data, and energy management data;

[0025] based on the log information of the vehicle in the recorded multi-source data, analyzing the work load and fatigue accumulation degree of the driver to determine the work intensity of the driver in the preset period.

[0026] In an embodiment, the step of performing the violation and management compliance analysis on the driver based on the recorded multi-source data of the environment of the vehicle, and determining the driving cooperation degree of the driver in the preset period includes:

[0027] Obtaining the traffic rule compliance record, instruction execution, cooperative driving behavior and cargo safety management of the driver from the recorded multi-source data of the environment of the vehicle;

[0028] Determining the driving cooperation degree of the driver in the preset period based on the traffic rule compliance record, the instruction execution, the cooperative driving behavior and the cargo safety management.

[0029] In an embodiment, after the step of performing the risk driving evaluation on the driver based on the driving cooperation degree, the mental state, the driving stability, the work intensity and the violation data, and obtaining the driving analysis report of the driver, the step further includes:

[0030] Obtaining the training measures required for improving the driving behavior of the driver based on the driving analysis report.

[0031] In addition, to achieve the above-mentioned purpose, the present application also proposes a risk intervention device for a commercial vehicle, which comprises:

[0032] An acquisition module is configured to acquire multi-dimensional risk factors of a commercial vehicle, wherein the risk factors are derived from multi-source data, and the multi-source data includes vehicle data, off-vehicle environment data and state data of a driver of the commercial vehicle;

[0033] A risk prediction module is configured to predict a risk type and a risk level of the commercial vehicle based on the multi-dimensional risk factors;

[0034] An execution module is configured to execute a corresponding intervention strategy based on the risk type and the risk level.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a risk intervention device for a commercial vehicle, which comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the risk intervention method for a commercial vehicle as described above.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and the storage medium stores a computer program, wherein the computer program is executed by a processor to implement the steps of the risk intervention method for a commercial vehicle as described above.

[0037] In addition, to achieve the above object, the application further provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the risk intervention method for a commercial vehicle as described above.

[0038] The one or more technical solutions provided by the application have at least the following technical effects:

[0039] The cloud obtains multi-dimensional risk factors of the commercial vehicle, the risk factors are derived from multi-source data, and the multi-source data includes vehicle data, off-vehicle environment data and state data of the driver of the commercial vehicle; based on the multi-dimensional risk factors, the risk type and risk level of the commercial vehicle are predicted; and based on the risk type and risk level, a corresponding intervention strategy is executed. That is, according to the multi-dimensional risk factors, the driving risk of the commercial vehicle is predicted to accurately determine the risk type and risk level of the commercial vehicle, and the intervention strategy to be executed is determined according to the risk type and risk level, so as to effectively intervene in the driving risk and improve the driving safety of the commercial vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0040] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and serve to explain the principles of the application together with the specification.

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, for those skilled in the art, other drawings can also be obtained based on these drawings without creative labor.

[0042] Figure 1 A flowchart is provided for the first embodiment of the risk intervention method for a commercial vehicle of the application;

[0043] Figure 2 A logic diagram of the aggregation algorithm model is provided for the risk intervention method for a commercial vehicle of the application;

[0044] Figure 3 A flowchart is provided for the second embodiment of the risk intervention method for a commercial vehicle of the application;

[0045] Figure 4 A flowchart is provided for the second embodiment of the risk intervention method for a commercial vehicle of the application;

[0046] Figure 5 A module structure diagram of the risk intervention device for a commercial vehicle of the embodiment of the application is provided;

[0047] Figure 6 A device structure schematic diagram of a hardware operating environment involved in a risk intervention method for a commercial vehicle in an embodiment of the present application.

[0048] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are merely intended to explain the technical solutions of the present application, and are not intended to limit the present application.

[0050] In order to better understand the technical solutions of the present application, the specific embodiments will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0051] The main solution of the embodiment of the present application is that the cloud server obtains multi-dimensional risk factors of the commercial vehicle, the risk factors are derived from multi-source data, and the multi-source data includes vehicle data, off-road environment data and state data of the driver of the commercial vehicle; based on the multi-dimensional risk factors, the risk type and risk level of the commercial vehicle are predicted; based on the risk type and the risk level, the corresponding intervention strategy is executed.

[0052] In the present embodiment, for the sake of description, the cloud server is described as the main body of execution.

[0053] Since the existing technology for driving risk intervention of commercial vehicles is mostly designed for fuel vehicles, the basis for risk identification and intervention measures is usually single, and since the working conditions of commercial vehicles during driving are complex, the driving risk of commercial vehicles cannot be effectively intervened according to the single intervention measures or risk identification basis, thereby reducing the driving safety of commercial vehicles.

[0054] The present application provides a solution, the cloud server obtains multi-dimensional risk factors of the commercial vehicle, the risk factors are derived from multi-source data, and the multi-source data includes vehicle data, off-road environment data and state data of the driver of the commercial vehicle; based on the multi-dimensional risk factors, the risk type and risk level of the commercial vehicle are predicted; based on the risk type and the risk level, the corresponding intervention strategy is executed. That is, according to the multi-dimensional risk factors as the basis, the driving risk of the commercial vehicle is predicted to accurately determine the risk type and risk level of the commercial vehicle, and the intervention strategy to be executed is determined according to the risk type and risk level, effective intervention is realized for the driving risk, thereby improving the driving safety of the commercial vehicle.

[0055] It should be noted that the execution subject of the embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a cloud server, etc. capable of realizing the above functions. The cloud server is taken as an example to describe the embodiment and the following embodiments.

[0056] Based on this, the application provides a risk intervention method for a commercial vehicle, referring to Figure 1 , Figure 1 The flowchart of the first embodiment of the risk intervention method for the commercial vehicle of the application is shown in the figure.

[0057] In the embodiment, the risk intervention method for the commercial vehicle is applied to a cloud server and includes steps S10-S30:

[0058] In step S10, multi-dimensional risk factors of the commercial vehicle are acquired, and the risk factors are derived from multi-source data including vehicle data, external environment data and state data of the driver of the commercial vehicle.

[0059] It should be noted that the multi-dimensional risk factors are various factors reflecting the running risks of the commercial vehicle from different angles and levels, which can include the running state of the vehicle itself, the external environmental conditions and the behavior state of the driver, etc. The multi-source data is data from different sources, including vehicle data, external environment data and state data of the driver. The vehicle data is related to the running state of the commercial vehicle itself, such as speed, acceleration, steering angle, battery capacity and motor speed, etc. The external environment data is related to the external environment during the driving of the commercial vehicle, such as the distance from the front vehicle, the position of the lane line, the position and speed of the surrounding pedestrians and vehicles, etc. The state data of the driver is related to the behavior and physiological state of the driver, such as the facial expression, eye state, head posture of the driver, and whether there is a dangerous behavior such as making a phone call or smoking, etc.

[0060] It can be understood that by acquiring multi-dimensional risk factors, various potential risk factors of the commercial vehicle during the running process can be comprehensively acquired to accurately reflect the actual running state of the vehicle and the risk level.

[0061] In specific implementation, the vehicle data can reflect the mechanical performance and power system state of the vehicle; the external environment data can reveal the influence of the road and nearby vehicles on the driving of the vehicle; and the state data of the driver can evaluate whether the behavior and physiological state of the driver will threaten the safe driving.

[0062] In a specific implementation, the external environment information can be collected by using the camera, millimeter wave radar, and laser radar of the commercial vehicle; the driver monitoring system can be used to monitor the facial expression, eye state, head posture, and dangerous behaviors such as making a phone call or smoking of the driver; and the vehicle state monitoring system can be used to obtain the running state data such as the speed, acceleration, steering angle, and battery power of the vehicle in real time.

[0063] In step S20, the risk type and risk level of the commercial vehicle are predicted based on the multi-dimensional risk factors.

[0064] It should be noted that the risk type is a risk category that may affect the safe operation of the commercial vehicle, which is obtained by analyzing the risk factors, and the risk type can include inattentive driving, fatigue driving, forward collision, lane deviation, and too close distance.

[0065] It should be noted that the risk level is a level division after quantitative evaluation of the risk type, and can be divided into three levels of low, medium, and high according to the correlation and urgency of the risk type.

[0066] It can be understood that by comprehensively analyzing the multi-dimensional risk factors and avoiding using a single factor for prediction, the risk type and risk level of the commercial vehicle can be accurately predicted, so as to realize the prediction of the risk level of the driving risk of the commercial vehicle in combination with the possible risk factors of the whole vehicle, and improve the accuracy and reliability of the risk prediction.

[0067] In a specific implementation, when the driver shows signs of fatigue and the vehicle travels at a high speed and is close to the front vehicle, it is determined as a high-risk state.

[0068] Optionally, the prediction of the risk type of the commercial vehicle in step S20 further includes:

[0069] receiving a preliminary prediction result of the commercial vehicle based on the multi-dimensional risk factors and preliminary prediction by the edge computing unit;

[0070] If the preliminary prediction result is that there is a driving risk, the risk type of the vehicle is obtained from the preliminary prediction result.

[0071] It should be noted that the edge computing unit is a computing node deployed close to the data source or on the vehicle side, which is used for local processing and preliminary analysis of the collected data, can quickly filter and process the data and make a preliminary prediction before the data is transmitted to the cloud, thereby reducing the data transmission amount and improving the real-time performance and response speed of the system.

[0072] It should be noted that the preliminary prediction result is a prediction conclusion obtained by the edge computing unit based on the preliminary analysis of the multi-dimensional risk factors of the commercial vehicle.

[0073] It should be noted that the driving risk is a potential dangerous situation related to the driving process of the vehicle, which can cause the vehicle to lose control, collide, and accidents and other adverse consequences. The driving risk can be caused by many factors, such as improper operation of the driver, vehicle failure, poor road environment, etc.

[0074] It can be understood that the edge computing unit only sends the key preliminary prediction results to the cloud after preliminary processing of the data, avoiding the cloud from processing a large amount of useless data, thereby reducing the amount of data that the cloud needs to process.

[0075] It can be understood that, since the preliminary screening by the edge computing unit can quickly exclude a large amount of risk-free data, and the detailed analysis by the cloud can further accurately determine the risk type in combination with more comprehensive data and complex algorithms. Therefore, first performing preliminary prediction on the multi-dimensional risk factors by the edge computing unit, and then performing detailed analysis by the cloud, can more accurately determine the risk type and reduce the possibility of false positives and false negatives.

[0076] Step S30, based on the risk type and the risk level, performing a corresponding intervention strategy.

[0077] It should be noted that the intervention strategy is a specific response measure formulated according to the risk type and the risk level, such as issuing a warning message, adjusting the vehicle driving parameters, limiting the vehicle functions, etc.

[0078] It can be understood that performing the corresponding intervention strategy according to the risk type and the risk level realizes dynamic management and precise intervention of the risk.

[0079] It can be understood that through real-time data monitoring of the vehicle data of the commercial vehicle, the off-vehicle environment data, and the state data of the driver, etc. dimensions, early warning of high-risk behaviors (such as excessively high frequency of sudden acceleration, signs of fatigue driving), combined with automatic intervention of the vehicle system (such as speed limit, sound and light reminder) or remote dispatch intervention, the rate of traffic accidents caused by human errors is reduced.

[0080] It can be understood that through the analysis and intervention of the driver state data, it can also help the driver to improve the driving behavior and reduce the risk caused by adverse behaviors such as fatigue driving and distracted driving.

[0081] In specific implementation, the cloud server can also establish a risk aggregation model according to the obtained multi-source data, the risk aggregation model including a real-time aggregation risk assessment module for real-time risk identification and intervention of the commercial vehicle (the algorithm logic of the aggregation risk assessment module is referred to as Figure 2), also includes a decision module for making corresponding intervention decisions according to the risk level. For low-risk cases, only a slight reminder can be given through the TTS voice reminder device in the vehicle; for medium-risk cases, in addition to reminding the driver, the background customer service will intervene through voice communication with two-way communication to remind the driver of the bad driving behavior and drive the driver to correct it in time; for high-risk cases, automatic deceleration, emergency braking, and turning on the hazard warning light are required.

[0082] The embodiment provides a risk intervention method for a commercial vehicle. A cloud server is used to obtain multi-dimensional risk factors of the commercial vehicle, the risk factors are derived from multi-source data, and the multi-source data includes vehicle data, external environment data and state data of a driver of the commercial vehicle. Based on the multi-dimensional risk factors, a risk type and a risk level of the commercial vehicle are predicted. Based on the risk type and the risk level, a corresponding intervention strategy is executed. That is, the driving risk of the commercial vehicle is predicted based on the multi-dimensional risk factors, so as to accurately determine the risk type and the risk level of the commercial vehicle, and determine the intervention strategy to be executed according to the risk type and the risk level, effectively intervene in the driving risk, and improve the driving safety of the commercial vehicle.

[0083] Based on the first and second embodiments, in the third embodiment, the same or similar contents as the above embodiments can be referred to the above description, and will not be repeated hereinafter. On this basis, please refer to Figure 3 , the step S20 of predicting the risk level of the commercial vehicle based on the multi-dimensional risk factors further includes steps S01-S04:

[0084] Step S01, determining whether there is distracted driving or fatigue driving of the driver in the risk type;

[0085] Step S02, if there is, determining the number of risks associated with the distracted driving or the fatigue driving from the risk type;

[0086] Step S03, if the number of risks does not exceed a preset number, obtaining the driving speed of the vehicle from the multi-dimensional risk factors;

[0087] Step S04, determining the risk level of the vehicle based on the interval to which the driving speed belongs.

[0088] It should be noted that distracted driving is the behavior of the driver during driving due to the distraction of attention and cannot focus on the driving task. Distracted driving can be caused by many factors, such as using a mobile phone, talking with passengers, operating a vehicle-mounted device, etc. Fatigue driving is the driving behavior of the driver due to long-time driving or lack of sleep, etc. leading to physical fatigue, thereby affecting the driving ability and reaction speed. Fatigue driving can cause the driver to lose concentration, slow reaction, and even appear to be unconscious for a short time. The number of risks is the number of the remaining types of risks required to jointly determine the risk level with distracted driving or fatigue driving. The preset number is a threshold value preset for judging the severity of the risk. When the number of risks associated with distracted driving or fatigue driving exceeds the preset number, it can be considered that there are too many risk categories, which also increases the probability of safe driving of the vehicle. In this case, it can be determined that the risk level is high.

[0089] It should be noted that the driving speed is the actual speed of the vehicle during driving. The driving speed is one of the important parameters for evaluating the risk of the vehicle, and a higher driving speed usually means a higher risk. The driving speed belongs to the interval is to divide the driving speed into different interval ranges, such as a low-speed interval (0-30km / h), a medium-speed interval (30-49km / h), and a high-speed interval (50-69km / h). By dividing the driving speed into different intervals, the risk level can be more finely evaluated.

[0090] It can be understood that since distracted driving and fatigue driving are one of the main reasons leading to traffic accidents, by prioritizing the identification of distracted driving and fatigue driving from the risk types, more effective and targeted intervention measures can be taken.

[0091] It can be understood that by comprehensively considering multiple risk factors, the cloud server can more accurately judge the risk level and reduce false positives or false negatives caused by misjudgment of a single factor. For example, if the vehicle only has the driver's distracted driving behavior, but other risk factors are less and the driving speed is slow, the cloud server can judge the risk level as "low", thereby avoiding unnecessary intervention.

[0092] It can be understood that by comprehensively evaluating the risk level, the cloud server can take corresponding intervention measures according to different risk situations. For example, for high-risk situations, the cloud server can take emergency braking or automatic avoidance measures; for low-risk situations, the cloud server can issue a warning reminder, thereby effectively reducing the probability of accidents and improving the effectiveness of intervention measures.

[0093] Based on the first and second embodiments of the present application, in the third embodiment of the present application, the same or similar contents as the above embodiments can be referred to the above introduction, and will not be repeated hereinafter. On this basis, please refer to Figure 4After step S10, the risk intervention method for the commercial vehicle further comprises steps S1-S3:

[0094] Step S1, when it is necessary to score the driving state of the driver, multi-source data recorded in a preset period is acquired;

[0095] Step S2, based on the multi-source data in the preset period, driving coordination, mental state, driving stability, and work intensity of the driver in the preset period are determined, and a violation record of the driver is acquired;

[0096] Step S3, based on the driving coordination, the mental state, the driving stability, the work intensity, and the violation data, a risk driving evaluation is performed on the driver, and a driving analysis report of the driver is obtained.

[0097] It should be noted that the driving state score is a process of comprehensively evaluating the driving behavior and state of the driver within a certain period of time. By quantifying the behavior and physiological state of the driver, a score reflecting the driving safety and standardization is generated. The preset period is a time range set in advance in the driving state scoring process, which is used to collect and analyze the driving data of the driver. The preset period can be flexibly set according to actual needs, for example, one day, one week, or one month, to ensure the timeliness and representativeness of the score.

[0098] It should be noted that the driving coordination is the adaptability of the driver to the vehicle operating environment and the degree of compliance with traffic rules. The risk factors of driving coordination include compliance with traffic rules, command execution, cooperative driving behavior, and cargo safety management. Specifically, the specific data indicators of compliance with traffic rules can be the number of red light violations, the number of line violations, the number of lane changes without turning on the turn signal, and the number of times of not giving way to pedestrians before zebra crossings. The specific data indicators of command execution can be the number of times of deviating from the preset route, the response time of overspeed alarm (such as not improving after receiving a fatigue driving reminder). The specific data indicators of cooperative driving behavior can be the qualified rate of distance to the front vehicle, the number of times of yielding, and the use time of high beam during night-time overtaking. The specific data indicators of cargo safety management can be the number of times of cargo displacement caused by sudden braking, and the number of times of cargo center of gravity deviation warning during turning (cargo monitoring sensors need to be installed).

[0099] It should be noted that the mental state is the psychological and physiological state of the driver during driving, and the risk factors of the mental state include facial / eye features, head posture, and operation abnormalities. Specifically, the specific data indicators of facial / eye features can be blink frequency, eye closure duration, gaze deviation duration (such as looking down at the mobile phone), and facial expression change frequency. The specific data indicators of head posture can be head tilt angle, nodding / shaking frequency, and head deviation direction from lane line duration. The specific data indicators of operation abnormalities can be reaction delay time (such as brake lag when encountering an emergency), and misoperation times (such as wrong gear selection and accidental button pressing).

[0100] It should be noted that the driving smoothness is the smoothness of the driver operating the vehicle, and the risk factors of the driving smoothness include acceleration / deceleration behavior, steering operation, braking behavior, speed control, and energy management. Specifically, the specific data indicators of acceleration / deceleration behavior can be rapid acceleration frequency, rapid deceleration frequency, average acceleration / deceleration, and acceleration / deceleration fluctuation rate. The specific data indicators of steering operation can be sharp turn frequency, steering angle fluctuation rate, lane deviation times, and lane change frequency. The specific data indicators of braking behavior can be emergency braking frequency, braking distance, and acceleration peak value during braking. The specific data indicators of speed control can be speed fluctuation rate, speed duration ratio, and speed deviation value on speed limit section. The specific data indicators of energy management can be motor power output fluctuation rate, kinetic energy recovery usage frequency, and battery charge / discharge current stability.

[0101] It should be noted that the work intensity is the workload of the driver within a preset period, and the risk factors of the work intensity include continuous driving duration, work and rest schedule, operation frequency, and task pressure. Among them, the specific data indicators of continuous driving duration can be single driving longest time, daily cumulative driving duration, and fatigue driving duration in violation of regulations. The specific data indicators of work and rest schedule can be daily average rest duration, night driving duration ratio, and high-risk period (2-5 am) driving duration. The specific data indicators of operation frequency can be steering / braking / acceleration operation times per unit time, and gear shifting frequency (for manual transmission vehicles). The specific data indicators of task pressure can be daily average transportation mileage, and load change rate (such as load fluctuation caused by frequent loading and unloading).

[0102] It should be noted that the violation record is the traffic violation record of the driver within a preset period. The risk factors of the violation record include historical violation record, risk road section warning, industry comparison analysis and abnormal behavior clustering. Among them, the specific data indicators of the historical violation record can be the number of violations (such as speeding, illegal parking, driving in the wrong lane) in the past 12 months, and the type distribution of the violation. The specific data indicators of the risk road section warning can be the driving time on the accident-prone road section and the number of repeated passes through the high-risk intersection. The specific data indicators of the industry comparison analysis can be the percentage of high-frequency sudden acceleration and the percentage of fatigue driving time higher than the average of the same type of driver. The specific data indicators of abnormal behavior clustering can be the number of abnormal route driving in a specific period (such as late at night) and the frequency of vehicle start during non-working hours (which may involve private use).

[0103] It should be noted that the risk driving evaluation is a process of comprehensive analysis and risk assessment of the driving behavior of the driver based on the driving coordination degree, mental state, driving stability, work intensity and violation record of the driver, aiming to identify potential dangerous driving behavior and provide basis for subsequent intervention measures.

[0104] It can be understood that by integrating multi-source data, the driving state of the driver can be comprehensively evaluated from multiple dimensions such as driving coordination degree, mental state, driving stability, work intensity and violation record, so as to more accurately reflect the actual driving ability and risk level of the driver.

[0105] It can be understood that by generating a detailed driving analysis report, a scientific basis is provided for the training and management of the driver, so that the management personnel can train and guide the driver according to the scores and improvement suggestions in the report, and improve the efficiency and effect of driving safety management.

[0106] In specific implementation, the periodic driving behavior state of the driver can be evaluated by relying on the driving behavior scoring algorithm. Specifically, the driving scoring algorithm identifies the driver's driving stability, mental state, driving coordination degree, work intensity, and big data violation in five dimensions. Specifically, the five-dimensional data and initial weights are collected, the factor data is trained by a machine learning algorithm (LSTM), a driver risk scoring model is established, and periodic grade warning (such as green-normal, yellow-attention, and red-high risk) is realized. The driving score is output after the vehicle runs for one week / month. According to the driving score, the driver's driving behavior is comprehensively evaluated, and the driver can obtain corresponding points incentive. The driver can exchange positive incentive rewards through points, and through the difference dimension of the score, such as the driver getting 70 points, the driver is trained according to the lost points project, and the driver's driving behavior is improved.

[0107] It should be noted that the initial weight of each dimension can be dynamically adjusted according to actual conditions.

[0108] Further, step S3 further includes:

[0109] Based on the recorded multi-source data of the vehicle's environment data, the driver's violation and management compliance analysis is performed to determine the driving cooperation degree of the driver in the preset period;

[0110] Based on the recorded multi-source data of the vehicle's operating state data, the smoothness analysis of the driver's operation is performed to determine the driving stability of the driver in the preset period, and the operating state data includes acceleration and deceleration behavior data, steering operation data, braking behavior data, speed control data and energy management data;

[0111] Based on the recorded multi-source data of the vehicle's log information, the work load and fatigue accumulation degree analysis of the driver is performed to determine the work intensity of the driver in the preset period.

[0112] It should be noted that the violation and management compliance analysis is a process of analyzing the driver's behavior in a specific environment to determine whether he / she complies with traffic rules and enterprise management regulations. Operating state data is data related to vehicle operation, including acceleration and deceleration behavior data, steering operation data, braking behavior data, speed control data and energy management data, etc. Smoothness analysis is a process of analyzing the smoothness of the driver's acceleration, deceleration, steering, braking and other behaviors when operating the vehicle. Smoothness analysis is used to evaluate whether the driver's operation is smooth and whether there are dangerous behaviors such as sudden acceleration and sudden braking. Log information is information recorded during vehicle operation, including driving time, mileage, operation frequency, etc. Work load and fatigue accumulation degree analysis is a process of analyzing vehicle log information to evaluate the work intensity and fatigue accumulation degree of the driver in the preset period.

[0113] It can be understood that by quantifying the driving cooperation degree, driving stability and work intensity of the driver, a scientific basis is provided for driving safety management. Management personnel can provide targeted training and guidance to drivers based on these data to improve the efficiency and effectiveness of driving safety management.

[0114] Further, the step S3 specifically includes:

[0115] From the recorded multi-source data of the vehicle's environment data, the driver's compliance with traffic rules record, instruction execution, cooperative driving behavior and cargo safety management are obtained;

[0116] determine a driving coordination degree of the driver in the preset period based on the traffic rule compliance record, the instruction execution, the cooperative driving behavior, and the cargo safety management.

[0117] It can be understood that by evaluating the traffic rule compliance and instruction execution of the driver, driving behaviors that may cause accidents due to illegal driving or non-compliance with instructions can be effectively identified; by evaluating the cooperative driving behavior, the ability of the driver to effectively cooperate with other vehicles and infrastructure in complex scenarios such as team driving and intersection passing can be evaluated; since commercial vehicles are mainly used for transporting goods and need to ensure the safety of the goods, when evaluating the driving coordination degree of the commercial vehicle, the number of times of cargo displacement caused by sudden braking during loading, fixing, and transportation of the goods, and the number of times of warning of cargo center of gravity deviation during turning are evaluated, so that the driving coordination degree of the driver is evaluated from multiple aspects to make the driving coordination degree more in line with the driving risk evaluation of the commercial vehicle.

[0118] Further, after step S3, the risk intervention method of the commercial vehicle further comprises:

[0119] Based on the driving analysis report, obtain training measures required for improving the driving behavior of the driver.

[0120] It should be noted that the driving analysis report is a comprehensive evaluation report generated based on the multi-source data of the driver in the preset period, including driving coordination degree, mental state, driving stability, work intensity, and violation record. The report records in detail the driving behavior performance, risk level, potential problems, and improvement suggestions of the driver. The training measures are a series of specific training programs and methods designed to improve driving behavior. These measures can include theoretical training, simulation driving training, actual operation guidance, safety education, etc., aiming to help the driver improve driving skills and safety awareness.

[0121] It can be understood that since the driving analysis report is based on the comprehensive analysis of multi-source data, it can accurately identify the bad driving habits and potential risk points of the driver, and develop personalized training programs based on the driving analysis report of the driver to effectively solve the actual problems of the driver and enhance the training effect.

[0122] It can be understood that the personalized training program can allocate training resources according to the actual needs of the driver, avoiding unnecessary training investment, thereby improving management efficiency and reducing training cost.

[0123] The application also provides a risk intervention device for a commercial vehicle, please refer to Figure 5 The risk intervention device for the commercial vehicle comprises:

[0124] An acquisition module 10 is configured to acquire multi-dimensional risk factors of a commercial vehicle, wherein the risk factors are derived from multi-source data, and the multi-source data comprises vehicle data, external environment data and state data of a driver of the commercial vehicle;

[0125] A risk prediction module 20 is configured to predict a risk type and a risk level of the commercial vehicle based on the multi-dimensional risk factors.

[0126] An execution module 30 is configured to execute a corresponding intervention strategy based on the risk type and the risk level.

[0127] Optionally, the risk intervention device of the commercial vehicle further comprises:

[0128] A receiving module 40 is configured to receive a preliminary prediction result of the commercial vehicle sent by the edge computing unit based on the multi-dimensional risk factors, and acquire a risk type of the vehicle from the preliminary prediction result if the preliminary prediction result indicates that there is a driving risk.

[0129] Optionally, the risk prediction module 20 is configured to determine whether there is distracted driving or fatigue driving of the driver in the risk type, determine a risk number associated with the distracted driving or the fatigue driving from the risk type if there is, acquire a driving speed of the vehicle from the multi-dimensional risk factors if the risk number does not exceed a preset number, and determine a risk level of the vehicle based on an interval to which the driving speed belongs.

[0130] Optionally, the risk intervention device of the commercial vehicle further comprises:

[0131] A driving behavior scoring module 50 is configured to acquire multi-source data recorded in a preset period when it is necessary to score a driving state of the driver, determine driving coordination, mental state, driving stability and working intensity of the driver in the preset period based on the multi-source data in the preset period, acquire a violation record of the driver, and perform risk driving evaluation on the driver based on the driving coordination, the mental state, the driving stability, the working intensity and the violation data to obtain a driving analysis report of the driver.

[0132] Optionally, the driving behavior scoring module 50 is further configured to perform a violation and management compliance analysis on the driver based on the recorded environmental data of the vehicle in the multi-source data, to determine a driving coordination degree of the driver in the preset period; perform a smoothness analysis on the driver's operation based on the recorded operating state data of the vehicle in the multi-source data, to determine a driving stability of the driver in the preset period, the operating state data including acceleration and deceleration behavior data, steering operation data, braking behavior data, speed control data, and energy management data; and perform a workload and fatigue accumulation degree analysis on the driver based on the recorded log information of the vehicle in the multi-source data, to determine a work intensity of the driver in the preset period.

[0133] Optionally, the driving behavior scoring module 50 is further configured to obtain a traffic rule compliance record, an instruction execution situation, a cooperative driving behavior, and a cargo safety management situation of the driver from the recorded environmental data of the vehicle in the multi-source data; and determine a driving coordination degree of the driver in the preset period based on the traffic rule compliance record, the instruction execution situation, the cooperative driving behavior, and the cargo safety management situation.

[0134] Optionally, the driving behavior scoring module 50 is further configured to obtain a training measure required for improving the driving behavior of the driver based on the driving analysis report.

[0135] The risk intervention device for a commercial vehicle provided in the present application adopts the risk intervention method for a commercial vehicle in the above embodiments, and can solve the technical problem that a relatively single intervention measure or risk identification basis cannot effectively intervene in the driving risk of the commercial vehicle, thereby reducing the driving safety of the commercial vehicle. Compared with the prior art, the risk intervention device for a commercial vehicle provided in the present application has the same beneficial effects as the risk intervention method for a commercial vehicle provided in the above embodiments, and other technical features in the risk intervention device for a commercial vehicle are the same as the features disclosed in the above embodiments, which will not be repeated here.

[0136] The present application provides a risk intervention device for a commercial vehicle, which comprises at least one processor and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the risk intervention method for a commercial vehicle in the above embodiment one.

[0137] The following will be described with reference to the drawings Figure 6The diagram illustrates a structural schematic of a risk intervention device suitable for implementing embodiments of this application in commercial vehicles. The risk intervention device for commercial vehicles in these embodiments may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The risk intervention device for commercial vehicles shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0138] like Figure 6 As shown, the risk intervention device for a commercial vehicle may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the risk intervention device for the commercial vehicle. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the risk intervention equipment of a commercial vehicle to communicate wirelessly or wiredly with other devices to exchange data. While the figures show risk intervention equipment for a commercial vehicle with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0139] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer readable medium, the computer program containing program code for executing the method shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network through a communication device, or installed from the storage device 1003, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiments disclosed in the present application are executed.

[0140] The risk intervention device for a commercial vehicle provided by the present application adopts the risk intervention method for a commercial vehicle in the above-mentioned embodiments, and can solve the technical problem that the driving risk of a commercial vehicle cannot be effectively intervened in a targeted manner according to a relatively single intervention measure or risk identification basis, thereby leading to a decline in the driving safety of the commercial vehicle. Compared with the prior art, the risk intervention device for a commercial vehicle provided by the present application has the same beneficial effects as the risk intervention method for a commercial vehicle provided by the above-mentioned embodiments, and other technical features in the risk intervention device for a commercial vehicle are the same as the features disclosed in the above-mentioned embodiment method, which will not be described here.

[0141] It should be understood that various parts of the present application can be realized by hardware, software, firmware or a combination thereof. In the description of the above-mentioned embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0142] The above is merely specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0143] The present application provides a computer readable storage medium having stored thereon computer readable program instructions (i.e. computer program) for executing the risk intervention method for a commercial vehicle in the above-mentioned embodiments.

[0144] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0145] The aforementioned computer-readable storage medium may be included in the risk intervention device of the commercial vehicle; or it may exist independently and not be installed in the risk intervention device of the commercial vehicle.

[0146] The aforementioned computer-readable storage medium carries one or more programs. When the aforementioned one or more programs are executed by the risk intervention device of the commercial vehicle, the risk intervention device of the commercial vehicle causes the following to occur: acquire multi-dimensional risk factors of the commercial vehicle, the risk factors being derived from multi-source data, the multi-source data including vehicle data, external environment data, and driver status data of the commercial vehicle; predict the type and level of risk present in the commercial vehicle based on the multi-dimensional risk factors; and execute corresponding intervention strategies based on the risk type and the risk level.

[0147] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0148] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0149] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0150] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned risk intervention method for commercial vehicles. This addresses the technical problem that relying on relatively simple intervention measures or risk identification criteria cannot effectively and specifically intervene in the driving risks of commercial vehicles, thus leading to a decline in driving safety. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the risk intervention method for commercial vehicles provided in the above embodiments, and will not be elaborated upon here.

[0151] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the risk intervention method for commercial vehicles as described above.

[0152] The computer program product provided in this application can solve the technical problem that relying on relatively simple intervention measures or risk identification criteria cannot effectively and specifically intervene in the driving risks of commercial vehicles, thus leading to a decline in the driving safety of commercial vehicles. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the risk intervention method for commercial vehicles provided in the above embodiments, and will not be repeated here.

[0153] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A risk intervention method for commercial vehicles, characterized in that, When applied in the cloud, the method includes: The risk factors of commercial vehicles are obtained from multiple sources of data, including vehicle data, external environment data, and driver status data. Based on the aforementioned multi-dimensional risk factors, the types and levels of risks present in the commercial vehicle are predicted. Based on the risk type and risk level, implement the corresponding intervention strategy.

2. The method as described in claim 1, characterized in that, The prediction of the types of risks present in the commercial vehicle also includes: Receive the preliminary prediction results of commercial vehicles based on the multi-dimensional risk factors sent by the edge computing unit; If the preliminary prediction indicates a driving risk, then the risk type of the vehicle is obtained from the preliminary prediction.

3. The method as described in claim 1, characterized in that, The step of predicting the risk level of the commercial vehicle based on the multi-dimensional risk factors includes: Determine whether the risk type includes distracted driving or fatigued driving by the driver; If present, determine the number of risks associated with the distracted driving or the fatigued driving from the risk types; If the number of risks does not exceed the preset number, the vehicle's speed is obtained from the multi-dimensional risk factors. The risk level of the vehicle is determined based on the range to which the driving speed belongs.

4. The method as described in claim 1, characterized in that, Following the step of obtaining multi-dimensional risk factors for commercial vehicles, the method further includes: When it is necessary to score the driver's driving status, multi-source data recorded within a preset period is acquired; Based on multi-source data within the preset period, determine the driver's driving cooperation, mental state, driving stability, and workload within the preset period, and obtain the driver's traffic violation records. Based on the driving coordination, mental state, driving smoothness, workload, and traffic violation data, a risk driving evaluation is conducted on the driver to obtain a driving analysis report.

5. The method as described in claim 4, characterized in that, The step of determining the driver's driving cooperation, driving stability, and workload within the preset period based on multi-source data within the preset period includes: Based on the vehicle's environmental data from the recorded multi-source data, the driver's violation and management compliance degree is analyzed to determine the driver's driving cooperation degree within the preset period. Based on the vehicle's operating status data from the recorded multi-source data, the smoothness of the driver's operation is analyzed to determine the driver's driving stability within the preset period. The operating status data includes acceleration and deceleration behavior data, steering operation data, braking behavior data, speed control data, and energy management data. Based on the vehicle's log information from the multi-source data, the driver's workload and fatigue accumulation are analyzed to determine the driver's work intensity within a preset period.

6. The method as described in claim 4, characterized in that, The step of analyzing the driver's violation and management compliance degree based on the vehicle's environmental data from the recorded multi-source data, and determining the driver's driving cooperation degree within the preset period, includes: From the vehicle's environmental data recorded from multiple sources, the driver's traffic rule compliance records, instruction execution status, cooperative driving behavior, and cargo safety management status are obtained. Based on the traffic rule compliance records, instruction execution status, cooperative driving behavior, and cargo safety management status, the driver's driving cooperation level within the preset period is determined.

7. The method as described in claim 4, characterized in that, After the step of evaluating the driver's risk driving based on the driving coordination, mental state, driving stability, workload, and traffic violation data to obtain the driver's driving analysis report, the method further includes: Based on the driving analysis report, training measures needed to improve the driver's driving behavior are obtained.

8. A risk intervention device for commercial vehicles, characterized in that, The device includes: The acquisition module is used to acquire multi-dimensional risk factors of commercial vehicles. The risk factors are derived from multi-source data, which includes vehicle data, external environment data, and driver status data of the commercial vehicles. The risk prediction module is used to predict the type and level of risk of the commercial vehicle based on the multi-dimensional risk factors. The execution module is used to execute the corresponding intervention strategy based on the risk type and the risk level.

9. A risk intervention device for commercial vehicles, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the risk intervention method for a commercial vehicle as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the risk intervention method for commercial vehicles as described in any one of claims 1 to 7.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the risk intervention method for new energy commercial vehicles as described in any one of claims 1 to 7.

Images