Online hailing vehicle remote real-time monitoring analysis method and system

Abstract

The invention discloses a remote real-time monitoring analysis method and system for an online hailed vehicle, and belongs to the technical field of online hailed vehicle monitoring. The method comprises the steps that a vehicle condition monitoring module obtains vehicle condition information of the vehicle; the driver condition monitoring module is used for acquiring state information of a driver during driving; the vehicle driving path monitoring module is used for acquiring driving path information in the driving process of the vehicle; the analysis management center is used for processing and analyzing the acquired related information to judge whether the online hailed car is safe or not during driving, and generating an alarm instruction when judging that the safety condition of the online hailed car is abnormal; and the early warning module carries out corresponding alarm reminding according to the generated alarm instruction. According to the invention, comprehensive analysis can be carried out by combining the abnormal condition of the vehicle driving path in the driving process of the online car-hailing vehicle and the abnormal condition of the driving condition of the driver in the driving process to judge whether the fatigue driving condition exists in the online car-hailing driver, so that alarm reminding is carried out in time, and the safety of the online car-hailing vehicle is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of online car-hailing monitoring, and specifically relates to a method and system for remote real-time monitoring and analysis of online car-hailing. Background Art

[0002] Online car-hailing refers to the business activities of building a service platform based on Internet technology, integrating supply and demand information, using qualified vehicles and drivers, and providing non-cruising reservation taxi services. Users can select the model and driver through mobile phone applications, quickly call a car and enjoy travel services. Compared with traditional taxis, online car-hailing has the advantages of transparent prices, convenient calling, and controllable service quality, so it has quickly become popular around the world.

[0003] With the increasing popularity of online ride-hailing services, the driving safety of online ride-hailing services is becoming increasingly important. Existing driving safety analysis of online ride-hailing services mostly determines whether the vehicle is speeding or overloaded by obtaining the vehicle's driving speed. However, the driving safety of online ride-hailing services is affected by many factors, resulting in the existing safety detection methods being not accurate enough, and thus the safety monitoring of online ride-hailing services is not comprehensive enough. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for remote real-time monitoring and analysis of online-hailing vehicles to solve the problems faced by the above-mentioned background technology.

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A remote real-time monitoring and analysis system for online-hailing vehicles, the system comprising:

[0007] A vehicle condition monitoring module, which is used to obtain vehicle condition information after the vehicle is started and send it to an analysis and management center;

[0008] A driver status monitoring module, which is used to obtain the driver's driving status information and send it to the analysis and management center;

[0009] A vehicle driving path monitoring module, which is used to obtain the driving path information of the vehicle during driving and send it to the analysis and management center;

[0010] An analysis and management center is used to process and analyze the relevant information obtained to determine whether the online car-hailing vehicle is safe during driving, and generate an alarm instruction when it is determined that the safety status of the online car-hailing vehicle is abnormal;

[0011] An early warning module, which performs corresponding alarm reminders according to the generated alarm instructions;

[0012] An evaluation module is used to perform a quality evaluation on the driving conditions of the online car-hailing vehicle based on the data information in the analysis management center.

[0013] Furthermore, the alarm instructions include abnormal vehicle condition alarm instructions and fatigue driving alarm instructions.

[0014] Furthermore, the method for the analysis management center to perform processing and analysis is:

[0015] The detection devices installed on various parts of the automobile are used to obtain the relevant parameter values ​​of each part and compare them with the respective preset alarm thresholds. When the relevant parameter values ​​obtained exceed the respective preset alarm thresholds, an abnormal vehicle condition alarm instruction is generated;

[0016] At the same time, when no abnormal vehicle condition alarm instruction is generated, the change curve of the relevant parameter values ​​of each part within the time period is obtained at regular intervals. In the same rectangular coordinate system, the area below the alarm threshold curve set for each part and above the change curve obtained in real time is recorded as S. When the area value S is less than the preset comparison area value SV, an abnormal vehicle condition alarm instruction is generated.

[0017] Furthermore, the method for processing and analyzing by the analysis management center also includes:

[0018] Every predetermined period, the formula DMS = α1*W r +α2*W p Obtain fatigue status value DMS;

[0019] The obtained fatigue status value DMS is compared with the preset fatigue status threshold DMS st To compare:

[0020] When DMS>DMS st When the driver is in a fatigue driving state, a warning instruction is generated;

[0021] Among them, W r is the driving condition abnormal value, W r is the abnormal value of the driving path condition, α1 and α2 are proportional coefficients, and α1+α2=1.

[0022] Furthermore, the driving condition abnormal value W r The method to obtain it is:

[0023] During a predetermined period, the camera installed in the cab is used to capture the driver's abnormal driving conditions during the period, including the total number of times the driver closes his eyes N. e , duration of each eye closure Number of yawns N s 、N times of head forward tilt b ;

[0024] At the same time, the driver's physiological parameter information PHY is obtained through the monitor worn by the driver during driving j ;

[0025] By formula Obtain the driving condition abnormal value W r ;

[0026] Among them, m is the number of physiological parameter items obtained, is the standard parameter value of j physiological items during normal driving, ΔP j is the parameter control value of the jth physiological item, and i∈(1, N e ), j∈(1,m).

[0027] Furthermore, the driving path condition abnormal value W r The acquisition method is:

[0028] In a predetermined period, obtain the number of lane changes lc and the duration of each lane change The predetermined period is divided into a plurality of interval time periods with each lane change time point as an interval, and each interval time period is a non-lane change journey;

[0029] Taking the center of the road in the non-changing route as the baseline, obtain the vehicle's driving trajectory fluctuation change diagram in the non-changing route, randomly select multiple detection points in the driving trajectory fluctuation change diagram, obtain the distance between the detection point and the baseline, and thus obtain the standard deviation ε of the non-changing route f ;

[0030] By formula Obtain the abnormal value W of the driving path condition r ; where r is the total number of non-changing lanes, and f∈(1, r), lc0 is the standard number of lane changes for the vehicle, The standard duration of each lane change, v is the traffic condition influence coefficient, k∈(1, lc).

[0031] Furthermore, the method for the evaluation module to perform quality evaluation is:

[0032] Get the user evaluation score after each order is completed in one day, so as to get the average evaluation score A in one day score And the variance of the evaluation score σ score , and at the same time obtain the fatigue status value after each order is completed in a day, so as to obtain the average fatigue status value A in a day DMS and the variance of fatigue status values ​​σ DMS ;

[0033] By formula The quality score Q is obtained;

[0034] The larger the quality score Q, the better the driving quality of the online car-hailing service.

[0035] A method for remote real-time monitoring and analysis of online-hailing vehicles, wherein the analysis method is controlled and executed by the remote real-time monitoring and analysis system for online-hailing vehicles.

[0036] Beneficial effects of the present invention:

[0037] The present invention can conduct a comprehensive analysis based on the abnormal conditions of the vehicle's driving path during the driving of the online car-hailing vehicle and the abnormal driving conditions of the driver during the driving process to determine whether the driver of the online car-hailing vehicle is driving fatigued. Once fatigue driving occurs, an alarm reminder will be issued in time, thereby effectively ensuring the safety of the online car-hailing vehicle. At the same time, the driving condition of the online car-hailing vehicle is evaluated in quality through the provided evaluation module, which makes it convenient for management personnel to conduct remote management and restrict the owners of the online car-hailing vehicles, thereby ensuring safety and improving driving quality.

[0038] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0040] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] In one embodiment, a remote real-time monitoring and analysis system for online-hailing vehicles is disclosed. Figure 1 As shown, the system includes:

[0043] The vehicle condition monitoring module is used to obtain the vehicle condition information after the vehicle is started and send it to the analysis and management center;

[0044] The driver status monitoring module is used to obtain the driver's driving status information and send it to the analysis and management center;

[0045] The vehicle driving path monitoring module is used to obtain the driving path information of the vehicle during driving and send it to the analysis and management center;

[0046] The analysis and management center is used to process and analyze the relevant information obtained to determine whether the online car-hailing vehicle is safe during driving. When it is determined that the safety status of the online car-hailing vehicle is abnormal, an alarm instruction is generated, wherein the alarm instruction includes an abnormal vehicle condition alarm instruction and a fatigue driving alarm instruction;

[0047] The early warning module makes corresponding alarm reminders according to the generated alarm instructions;

[0048] The evaluation module is used to conduct a quality assessment of the driving conditions of the online car-hailing service based on the data information in the analysis management center.

[0049] Through the above technical scheme, this application first obtains the vehicle condition information of the vehicle after starting through the vehicle condition monitoring module, and sends it to the analysis and management center, and judges whether the vehicle has any abnormal condition based on the vehicle condition information, so as to ensure the safety of the online car-hailing, and then obtains the driver's status information during driving through the driver condition monitoring module, and obtains the vehicle's driving path information through the vehicle driving path monitoring module, and then conducts a comprehensive analysis through the analysis and management center to determine whether the driver is fatigued driving, and makes timely alarm reminders to ensure the safety of the online car-hailing; in addition, an evaluation module is also provided to perform quality evaluation on the driving conditions of the online car-hailing, which is convenient for management personnel to conduct remote management and restrict the owners of online car-hailing vehicles, ensuring safety while improving driving quality.

[0050] As an implementation mode of the present invention, the method for the analysis management center to perform processing and analysis is:

[0051] The detection devices installed on various parts of the automobile are used to obtain the relevant parameter values ​​of each part and compare them with the respective preset alarm thresholds. When the relevant parameter values ​​obtained exceed the respective preset alarm thresholds, an abnormal vehicle condition alarm instruction is generated;

[0052] At the same time, when no abnormal vehicle condition alarm instruction is generated, the change curve of the relevant parameter values ​​of each part within the time period is obtained at regular intervals. In the same rectangular coordinate system, the area below the alarm threshold curve set for each part and above the change curve obtained in real time is recorded as S. When the area value S is less than the preset comparison area value SV, an abnormal vehicle condition alarm instruction is generated.

[0053] Through the above technical scheme, this embodiment provides a method for the analysis management center to determine whether there is any safety abnormality in the condition of the online car-hailing vehicle. First, the relevant parameter values ​​of each part are obtained through the detection devices installed on various parts of the car, and compared with the respective set alarm thresholds. When the obtained relevant parameter values ​​exceed the respective preset alarm thresholds, an abnormal vehicle condition alarm instruction is generated. For example, the engine temperature is detected in real time. If the engine temperature is abnormally high and reaches the set alarm threshold, it means that the engine temperature is abnormal, and the corresponding abnormal vehicle condition alarm is generated. In this way, the various components of the online car-hailing vehicle can be remotely monitored in real time to see if they are normal. Once an abnormality occurs, an alarm will be issued in time to ensure the safety of the online car-hailing vehicle. In addition, since the set alarm threshold is a fixed value set according to experience, when no alarm is issued, if the obtained parameter value is always near the set alarm threshold, However, it has not exceeded the alarm threshold. Although no alarm has occurred at this time, the possibility of an abnormality is also relatively high. Therefore, when no abnormal vehicle condition alarm instruction is generated, the change curve of the relevant parameter values ​​of each part within the time period is obtained at regular intervals. In the same rectangular coordinate system, the area below the alarm threshold curve set for each part and above the change curve obtained in real time is recorded as S. When the area value S is less than the preset comparison area value SV, the preset comparison area value can be determined based on actual experience data to generate an abnormal vehicle condition alarm instruction. The smaller the enclosed area S is, the closer the obtained parameter is to the alarm threshold within the time period, which means that the risk of an abnormality is greater. Therefore, when the area value S is less than the preset comparison area value SV, it can be judged that the parameter is abnormal, and the corresponding abnormal vehicle condition alarm instruction is generated to provide timely reminders and ensure the safety of online car-hailing.

[0054] As an implementation mode of the present invention, the method for processing and analyzing by the analysis management center further includes:

[0055] Every predetermined period, the formula DMS = α1*W r +α2*W p Obtain fatigue status value DMS;

[0056] The obtained fatigue status value DMS is compared with the preset fatigue status threshold DMS st To compare:

[0057] When DMS>DMS st When the driver is in a fatigue driving state, a warning instruction is generated;

[0058] Among them, W r is the driving condition abnormal value, W r is the abnormal value of the driving path condition, α1 and α2 are proportional coefficients, and α1+α2=1;

[0059] Among them, the driving condition abnormal value W rThe acquisition method is: within a predetermined period, through the camera probe installed in the cab, capture the abnormal driving conditions of the driver during the period, including the total number of times N the driver closes his eyes e , duration of each eye closure Number of yawns N s 、N times of head forward tilt b ;

[0060] At the same time, the driver's physiological parameter information PHY is obtained through the monitor worn by the driver during driving j ;

[0061] By formula Obtain the driving condition abnormal value W r ;

[0062] Among them, m is the number of physiological parameter items obtained, is the standard parameter value of j physiological items during normal driving, ΔP j is the parameter control value of the jth physiological item, and i∈(1, N e ), j∈(1,m);

[0063] Driving path condition abnormal value W r The acquisition method is: within a predetermined period, obtain the number of lane changes lc and the duration of each lane change The predetermined period is divided into a plurality of interval time periods with each lane change time point as an interval, and each interval time period is a non-lane change journey;

[0064] Taking the center of the road in the non-changing route as the baseline, obtain the vehicle's driving trajectory fluctuation change diagram in the non-changing route, randomly select multiple detection points in the driving trajectory fluctuation change diagram, obtain the distance between the detection point and the baseline, and thus obtain the standard deviation ε of the non-changing route f ;

[0065] By formula Obtain the abnormal value W of the driving path condition r ;

[0066] Where r is the total number of non-lane change trips, and f∈(1, r), lc0 is the standard number of lane changes for the vehicle, The standard duration of each lane change, v is the traffic condition influence coefficient, k∈(1, lc).

[0067] Through the above technical solution, this embodiment provides a method for the analysis management center to analyze the safety of online car-hailing according to whether the online car-hailing owner is in a fatigue driving condition. When the online car-hailing driver is in a fatigue driving condition, its driving condition will be greatly different from the normal condition, and its driving path change will also be different from the normal condition. Therefore, the driver's fatigue condition abnormality value DMS is first obtained, and a predetermined period is specifically set manually. Within the predetermined period, the camera probe installed in the cab is used to capture the driver's abnormal driving condition during the period, including the total number of times N the driver closes his eyes. e , duration of each eye closure Number of yawns N s 、N times of head forward tilt b ; At the same time, the driver's physiological parameter information PHY is obtained through the monitor worn by the driver during driving j , and then through the formula Obtain the driving condition abnormal value W r ;formula Indicates the abnormal condition of the driver. When the number of times the driver closes his eyes is N e The more you close your eyes, the longer you close your eyes The longer, the more times you yawn s and the number of times the head is tilted forward N b The more there are, the greater the possibility that the driver is fatigued. It shows the difference between the physiological parameters of the driver during driving and the physiological parameters during normal driving. Obviously, the larger the difference, the greater the fluctuation, and the greater the possibility of driver fatigue driving. Therefore, the formula Comprehensive analysis is performed to obtain the abnormal driving condition value W r , when its value is larger, it means that the driver is more likely to be fatigued; then obtain the abnormal value W of the driving path condition r When the driver is fatigued, the route of the vehicle will be greatly different from the normal one. Therefore, the number of lane changes lc and the duration of each lane change are obtained within the predetermined period. The predetermined cycle is divided into multiple interval time periods with each lane change time point as an interval, each interval time period is a non-lane change journey, the center of the road in the non-lane change journey is taken as the baseline, and a driving trajectory fluctuation change diagram of the vehicle in the non-lane change journey is obtained. Multiple detection points are randomly selected in the driving trajectory fluctuation change diagram, and the distance between the detection point and the baseline is obtained, so as to obtain the standard deviation ε of the non-lane change journey f ; Then through the formula Obtain the abnormal value W of the driving path condition r; When the number of lane changes lc within the predetermined period is too different from the predetermined standard number of lane changes, or the duration of each lane change The larger the difference between the lane change time and the preset standard lane change time, the more abnormal the vehicle is driving. On a normal non-changing route, the vehicle travels along a fixed road. If the obtained standard deviation is larger, it means that the trajectory fluctuation is more obvious during the non-changing route, indicating that the vehicle is driving more abnormally. Therefore, when the driving path condition abnormality value W r The larger the value, the more abnormal the vehicle is in driving, which indicates that the driver is more likely to be fatigued. Finally, the abnormal driving condition value W is obtained. r And the abnormal value of driving path condition W r Comprehensive analysis is performed to obtain the fatigue status value DMS. The obtained fatigue status value DMS is compared with the preset fatigue status threshold DMS. st Compare: When DMS>DMS st When the driver is driving fatigued, it means that the driver is likely to be driving fatigued. In order to ensure the safety of online ride-hailing vehicles, a fatigue driving alarm instruction is generated to remind them. In this way, a comprehensive analysis can be conducted based on the abnormal conditions of the vehicle's driving path during driving and the abnormal driving conditions of the driver during driving to determine whether the driver of the online ride-hailing vehicle is driving fatigued. Once fatigue driving occurs, an alarm reminder will be issued in time, thereby effectively ensuring the safety of online ride-hailing vehicles.

[0068] If necessary, the proportionality coefficients α1 and α2, the preset fatigue threshold DMS st Based on empirical data, standard parameter values ​​of various physiological items during normal driving And the parameter control value ΔP of each physiological project j The standard number of lane changes lc0 and the standard duration of each lane change are determined based on the driver's historical physiological parameter data. It can be determined based on the historical habits of the drivers, and the traffic condition impact coefficient is determined based on the traffic flow conditions in the time period of the day, which will not be described in detail here.

[0069] As an embodiment of the present invention, the method for the evaluation module to perform quality evaluation is: obtaining the user evaluation score after each order is completed in one day, thereby obtaining the average evaluation score A in one day. score And the variance of the evaluation score σ score , and at the same time obtain the fatigue status value after each order is completed in a day, so as to obtain the average fatigue status value A in a day DMS and the variance of fatigue status values ​​σ DMS ;

[0070] By formula The quality score Q is obtained;

[0071] The larger the quality score Q, the better the driving quality of the online car-hailing service.

[0072] Through the above technical solution, this embodiment provides a method for evaluating driving quality by an evaluation module. First, the user evaluation score after each order is completed in a day is obtained, so as to obtain the average evaluation score A in a day. score And the variance of the evaluation score σ score , when the mean value of the evaluation score is higher, or the variance of the evaluation score is smaller, it means that the driving quality is better. Then, the fatigue status value after each order is completed in a day is obtained, so as to obtain the fatigue status mean value A in a day. DMS and the variance of fatigue status values ​​σ DMS , when the fatigue condition mean A DMS and the variance of fatigue status values ​​σ DMS The smaller it is, the better the driving quality is, so through the formula A comprehensive analysis is performed to obtain the quality score Q; from the formula, it can be seen that the larger the value of Q, the higher the surface quality score, which means the better the driving condition of the online car-hailing vehicle. In this way, it is convenient for managers to remotely manage online car-hailing vehicle drivers and restrict the driving quality of online car-hailing vehicle owners, ensuring safety while improving driving quality.

[0073] A method for remote real-time monitoring and analysis of online-hailing vehicles, wherein the analysis method is controlled and executed by the above-mentioned remote real-time monitoring and analysis system for online-hailing vehicles.

[0074] The above contents are merely examples and explanations of the concept of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they should all fall within the protection scope of the present invention.

Claims

1. A remote real-time monitoring and analysis system for online-hailing vehicles, characterized in that: The system comprises: A vehicle condition monitoring module, which is used to obtain vehicle condition information after the vehicle is started and send it to an analysis and management center; A driver status monitoring module, which is used to obtain the driver's driving status information and send it to the analysis and management center; A vehicle driving path monitoring module, which is used to obtain the driving path information of the vehicle during driving and send it to the analysis and management center; An analysis and management center is used to process and analyze the relevant information obtained to determine whether the online car-hailing vehicle is safe during driving, and generate an alarm instruction when it is determined that the safety status of the online car-hailing vehicle is abnormal; An early warning module, which performs corresponding alarm reminders according to the generated alarm instructions; An evaluation module is used to perform a quality evaluation on the driving conditions of the online car-hailing vehicle based on the data information in the analysis management center.

2. A remote real-time monitoring and analysis system for online-hailing vehicles according to claim 1, characterized in that: The alarm instructions include abnormal vehicle condition alarm instructions and fatigue driving alarm instructions.

3. A remote real-time monitoring and analysis system for online-hailing vehicles according to claim 2, characterized in that: The method for the analysis management center to perform processing and analysis is: The detection devices installed on various parts of the automobile are used to obtain the relevant parameter values ​​of each part and compare them with the respective preset alarm thresholds. When the relevant parameter values ​​obtained exceed the respective preset alarm thresholds, an abnormal vehicle condition alarm instruction is generated; At the same time, when no abnormal vehicle condition alarm instruction is generated, the change curve of the relevant parameter values ​​of each part within the time period is obtained at regular intervals. In the same rectangular coordinate system, the area below the alarm threshold curve set for each part and above the change curve obtained in real time is recorded as S. When the area value S is less than the preset comparison area value SV, an abnormal vehicle condition alarm instruction is generated.

4. The online car-hailing remote real-time monitoring and analysis system according to claim 1 is characterized in that: The method for the analysis management center to perform processing and analysis also includes: Every predetermined period, the formula DMS = α1*W r +α2*W p Obtain fatigue status value DMS; The obtained fatigue status value DMS is compared with the preset fatigue status threshold DMS st To compare: When DMS>DMS st When the driver is in a fatigue driving state, a warning instruction is generated; Among them, W r is the driving condition abnormal value, W r is the abnormal value of the driving path condition, α1 and α2 are proportional coefficients, and α1+α2=1.

5. The online car-hailing remote real-time monitoring and analysis system according to claim 4 is characterized in that: The driving condition abnormal value W r The method to obtain it is: During a predetermined period, the camera installed in the cab is used to capture the driver's abnormal driving conditions during the period, including the total number of times the driver closes his eyes N. e , duration of each eye closure Number of yawns N s 、N times of head forward tilt b ; At the same time, the driver's physiological parameter information PHY is obtained through the monitor worn by the driver during driving j ; By formula Obtain the driving condition abnormal value W r ; Among them, m is the number of physiological parameter items obtained, is the standard parameter value of j physiological items during normal driving, ΔP j is the parameter control value of the jth physiological item, and i∈(1, N e ), j∈(1,m).

6. A remote real-time monitoring and analysis system for online-hailing vehicles according to claim 4, characterized in that: The driving path condition abnormal value W r The acquisition method is: In a predetermined period, obtain the number of lane changes lc and the duration of each lane change The predetermined period is divided into a plurality of interval time periods with each lane change time point as an interval, and each interval time period is a non-lane change journey; Taking the center of the road in the non-changing route as the baseline, obtain the vehicle's driving trajectory fluctuation change diagram in the non-changing route, randomly select multiple detection points in the driving trajectory fluctuation change diagram, obtain the distance between the detection point and the baseline, and thus obtain the standard deviation ε of the non-changing route f ; By formula Obtain the abnormal value W of the driving path condition r ; where r is the total number of non-changing lanes, and f∈(1, r), lc0 is the standard number of lane changes for the vehicle, The standard duration of each lane change, v is the traffic condition influence coefficient, k∈(1, lc).

7. The online car-hailing remote real-time monitoring and analysis system according to claim 4 is characterized in that: The method for the evaluation module to perform quality evaluation is: Get the user evaluation score after each order is completed in one day, so as to get the average evaluation score A in one day score And the variance of the evaluation score σ score , and at the same time obtain the fatigue status value after each order is completed in a day, so as to obtain the average fatigue status value A in a day DMS and the variance of fatigue status values ​​σ DMS ; By formula The quality score Q is obtained; The larger the quality score Q, the better the driving quality of the online car-hailing service.

8. A method for remote real-time monitoring and analysis of online-hailing vehicles, characterized in that: The analysis method is controlled and executed by the online-hailing vehicle remote real-time monitoring and analysis system described in any one of claims 1-7.

Images