Method and System for Evaluating Vehicle Driving Behavior Based on ETC Data of Internet of Things

Abstract

The present invention discloses a method and system for evaluating vehicle driving behavior based on ETC data of the Internet of Things, which relates to the technical field of electrical digital data processing. The method for evaluating vehicle driving behavior based on ETC data of the Internet of Things includes the following steps: real-time driving evaluation, emergency lane evaluation, fatigue driving judgment, and full-course driving evaluation. The present invention determines whether to give a driving warning based on the obtained real-time driving behavior evaluation index, then obtains road data and combines it with real-time driving data to obtain an evaluation index for occupying the emergency lane and determines whether to conduct an inspection for occupying the emergency lane. Then, it determines whether there is fatigue driving based on the passing data. Finally, it obtains the full-course driving behavior index based on the real-time driving behavior evaluation index and the passing data and gives driving feedback, achieving the effect of more accurately evaluating vehicle driving behavior and solving the problem of inaccurate data in the prior art when evaluating the driving behavior of high-speed vehicles based on ETC data.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and particularly to a method and system for evaluating vehicle driving behavior based on Internet of Things (IoT)-enabled ETC data. Background Art

[0002] With the rapid development of Internet of Things (IoT) technology, intelligent management in the transportation field has become an important means to improve road safety and efficiency. The Electronic Toll Collection (ETC) system is a typical application of IoT in the transportation field. It enables rapid data collection of vehicles passing through toll stations via wireless communication, significantly enhancing vehicle passing efficiency and driving experience. IoT-enabled ETC data can not only be used for toll management but also, in combination with information such as vehicle driving routes, speeds, and times, be used to evaluate and analyze driving behavior. By integrating with in-vehicle sensors and external information, this data can be used in multiple scenarios such as identifying driving habits, evaluating safety, optimizing traffic management, and vehicle insurance pricing, thereby contributing to the further improvement of intelligent transportation systems.

[0003] In the prior art, methods for evaluating vehicle driving behavior based on IoT-enabled ETC data have been applied and verified in multiple fields such as traffic management, insurance pricing, and fleet management. These methods mainly rely on data such as timestamps, locations, and driving speeds of vehicles passing through toll stations collected by the ETC system. By integrating with sensor data installed in the vehicle (such as acceleration and direction changes) and external traffic information (such as real-time road conditions and weather data), a driving behavior evaluation model is constructed. Using machine learning and big data analysis techniques, existing systems can identify unsafe driving behaviors such as speeding, hard braking, and rapid acceleration, and can even generate personalized driving habit evaluation reports based on historical driving behavior data. The application of these technologies can not only help improve road safety but also enable new insurance models such as "pricing based on driving behavior", which helps encourage safe driving.

[0004] For example, a method and system for portrait modeling of new energy vehicle owners' driving behavior habits based on Internet of Vehicles big data disclosed in a patent application with publication number CN114756761A includes: obtaining vehicle information, where the vehicle information includes the vehicle identification number; the enterprise cloud server logs in to the national new energy vehicle data server and searches for the vehicle driving data document corresponding to the vehicle according to the vehicle identification number; and multi-dimensional data of the owner's driving behavior habits is obtained by analyzing the original data obtained from the national new energy vehicle data server, completing the portrait of the driving behavior habits.

[0005] For example, a computer data remote management system and method based on the Internet of Things announced in the invention patent announcement with the announcement number of CN116305735B includes: a data acquisition module, an intelligent monitoring module, a model construction and analysis module, a probability calculation module, and an intelligent management module; the output end of the data acquisition module is connected to the input end of the model construction and analysis module; the output end of the intelligent monitoring module is connected to the input end of the model construction and analysis module; the output end of the model construction and analysis module is connected to the input end of the probability calculation module; the output end of the probability calculation module is connected to the input end of the intelligent management module.

[0006] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, it is found that the above technology has at least the following technical problems:

[0007] In the prior art, ETC data is less integrated with other Internet of Things data, and only relying on ETC data for driving behavior recognition leads to insufficient data dimensions, resulting in inaccurate data when evaluating the driving behavior of high-speed vehicles based on ETC data. Summary of the Invention

[0008] The embodiments of the present application provide a method and system for evaluating vehicle driving behavior based on ETC data of the Internet of Things, which solves the problem of inaccurate data when evaluating the driving behavior of high-speed vehicles based on ETC data in the prior art, and realizes more accurate evaluation of vehicle driving behavior.

[0009] The embodiments of the present application provide a method for evaluating vehicle driving behavior based on ETC data of the Internet of Things, including the following steps: obtaining real-time driving data of the vehicle passing through each ETC gantry after entering the highway, obtaining real-time driving behavior evaluation indicators according to the real-time driving data and judging whether to give a driving warning, where the real-time driving behavior evaluation indicators are used to quantify the degree of compliance of the vehicle's real driving behavior on the highway with the standard driving behavior; obtaining road data and combining the real-time driving data to obtain an evaluation indicator for occupying the emergency lane, and judging whether to conduct a verification of occupying the emergency lane according to the evaluation indicator for occupying the emergency lane, where the evaluation indicator for occupying the emergency lane is used to quantify the degree of compliance of the vehicle occupying the emergency lane; obtaining the passing data of the vehicle driving at high speed based on ETC, and judging whether there is fatigue driving according to the passing data; obtaining the whole-course driving behavior index according to the real-time driving behavior evaluation indicators and the passing data and giving driving feedback, where the whole-course driving behavior index is used to comprehensively quantify the degree of compliance of the driving behavior of the driver.

[0010] Further, the real-time driving data includes the vehicle detected speed, the number of longitudinal acceleration changes, the number of lateral acceleration changes, the number of abnormal brakes, and the number of abnormal throttles; the road data includes the number of lane changes, the number of road lanes, the number of turn signal uses, the deviation from lane warning frequency, and the average road congestion index; the average road congestion index represents the average value of the road congestion indices of the sections between two adjacent ETC gantries; the passing data includes the passing duration, the passing kilometers, and the number of service area stops.

[0011] Further, the specific obtaining process of the real-time driving behavior evaluation index is as follows: Number the ETC gantries, and obtain the reference driving data from a preset database, where the reference driving data includes the maximum speed limit and the minimum speed limit; Process the vehicle detected speed and the reference driving data to obtain the vehicle detected speed evaluation index, which is used to quantify the standard degree of the vehicle detected speed; Perform a mean operation on the result of processing the sum of the number of longitudinal acceleration changes, the number of lateral acceleration changes, the number of abnormal brakes, and the number of abnormal throttles and the vehicle detected speed evaluation index to obtain the real-time driving behavior evaluation index.

[0012] Further, the specific obtaining process of the occupying emergency lane evaluation index is as follows: Obtain the emergency lane evaluation weights from a preset database, where the emergency lane evaluation weights include the congestion weight and the lane change weight; Number the driving lanes, and obtain the lane change index based on the number of road lanes and the number of lane changes, which is used to quantify the probability of the vehicle changing lanes to the emergency lane; Based on the obtained number of turn signal uses, the deviation from lane warning frequency, the average road congestion index, the emergency lane evaluation weights, and the lane change index, obtain the occupying emergency lane evaluation index.

[0013] Further, the specific limiting expression of the whole-course driving behavior index is as follows:

[0014] ;

[0015] In the formula, represents the number of the ETC gantry, , represents the total number of ETC gantries, represents the passing kilometers, represents arriving at the th ETC gantry, the real-time driving behavior evaluation index of the vehicle, represents the whole-course driving behavior index, and e represents the natural constant.

[0016] The embodiment of the present application provides a vehicle driving behavior evaluation system based on ETC data of the Internet of Things, including: a real-time driving evaluation module, an emergency lane evaluation module, a fatigue driving judgment module, and a full-course driving evaluation module; wherein, the real-time driving evaluation module is used to obtain real-time driving data of the vehicle passing through each ETC gantry after entering the highway, obtain real-time driving behavior evaluation indicators according to the real-time driving data, and judge whether to give a driving warning. The real-time driving behavior evaluation indicators are used to quantify the degree of compliance between the real-time driving behavior of the vehicle on the highway and the standard driving behavior; the emergency lane evaluation module is used to obtain occupancy emergency lane evaluation indicators by obtaining road data and combining real-time driving data, and judge whether to conduct occupancy emergency lane verification according to the occupancy emergency lane evaluation indicators. The occupancy emergency lane evaluation indicators are used to quantify the degree of compliance of the vehicle occupying the emergency lane; the fatigue driving judgment module is used to judge whether there is fatigue driving according to the passing data obtained by the vehicle traveling at high speed based on ETC; the full-course driving evaluation module is used to obtain a full-course driving behavior index according to the real-time driving behavior evaluation indicators and the passing data and give driving feedback. The full-course driving behavior index is used to comprehensively quantify the degree of compliance of the driving behavior of the driver.

[0017] One or more technical solutions provided in the embodiment of the present application have at least the following technical effects or advantages:

[0018] 1. By obtaining real-time driving behavior evaluation indicators from the obtained real-time driving data and judging whether to give a driving warning, then obtaining occupancy emergency lane evaluation indicators by obtaining road data and combining real-time driving data and judging whether to conduct occupancy emergency lane verification, then judging whether there is fatigue driving based on the obtained passing data, and finally obtaining a full-course driving behavior index according to the real-time driving behavior evaluation indicators and the passing data and giving driving feedback, the driving behavior of the vehicle is evaluated more accurately. Furthermore, the driving behavior of the vehicle is evaluated more accurately, effectively solving the problem of inaccurate data in the prior art when evaluating the driving behavior of high-speed vehicles based on ETC data.

[0019] 2. By numbering the ETC gantries and obtaining reference driving data from a preset database, then processing the detected vehicle speed and the reference driving data to obtain a vehicle detection speed evaluation indicator, and then performing a mean operation on the result of processing the sum of the number of longitudinal acceleration changes, the number of lateral acceleration changes, the number of abnormal brakes, and the number of abnormal throttle operations and the vehicle detection speed evaluation indicator to obtain real-time driving behavior evaluation indicators, the driving behavior of the vehicle is evaluated more timely. Furthermore, the driving behavior of the vehicle is evaluated more accurately.

[0020] 3. By obtaining the emergency lane evaluation weight from a preset database, numbering the driving lanes, obtaining the lane-changing index based on the number of road lanes and the number of lane changes, and then obtaining the emergency lane occupancy evaluation index based on the obtained number of turn signal uses, deviation lane alarm frequency, average road congestion index, emergency lane evaluation weight, and lane-changing index, it is possible to more timely determine whether a vehicle occupies the emergency lane, and thus realize more standardized guidance of vehicle driving behavior. Brief Description of the Drawings

[0021] Figure 1 It is a flowchart of a vehicle driving behavior evaluation method based on ETC data of the Internet of Things provided by an embodiment of the present application;

[0022] Figure 2 is a schematic diagram of the change of real-time driving behavior evaluation indicators provided by an embodiment of the present application. Among them, (a) is a schematic diagram of the change of real-time driving behavior evaluation indicators with the vehicle detection speed, (b) is a schematic diagram of the change of real-time driving behavior evaluation indicators with the number of longitudinal acceleration changes, (c) is a schematic diagram of the change of real-time driving behavior evaluation indicators with the number of lateral acceleration changes, (d) is a schematic diagram of the change of real-time driving behavior evaluation indicators with the number of abnormal braking times, and (e) is a schematic diagram of the change of real-time driving behavior evaluation indicators with the number of abnormal throttle times. Detailed Embodiment

[0023] In an embodiment of the present application, by providing a vehicle driving behavior evaluation method and system based on ETC data of the Internet of Things, the problem of inaccurate data in the prior art when evaluating the driving behavior of high-speed vehicles based on ETC data is solved. By numbering the ETC gantries and obtaining reference driving data from a preset database, then processing the vehicle detection speed and the reference driving data to obtain a vehicle detection speed evaluation index, and then performing a mean operation on the result of processing the sum of the number of longitudinal acceleration changes, the number of lateral acceleration changes, the number of abnormal braking times, and the number of abnormal throttle times and the vehicle detection speed evaluation index to obtain a real-time driving behavior evaluation index, and judging whether to give a driving warning accordingly. Then, by obtaining the emergency lane evaluation weight from a preset database, numbering the driving lanes at the same time, obtaining the lane-changing index based on the number of road lanes and the number of lane changes, and then obtaining the emergency lane occupancy evaluation index based on the obtained number of turn signal uses, deviation lane alarm frequency, average road congestion index, emergency lane evaluation weight, and lane-changing index, and judging whether to verify the occupancy of the emergency lane accordingly. Then, based on the obtained passing data, it is judged whether there is fatigue driving. Finally, the whole journey driving behavior index is obtained according to the real-time driving behavior evaluation index and the passing data, and driving feedback is performed, realizing more accurate evaluation of vehicle driving behavior.

[0024] The technical solution in the embodiment of the present application is to solve the problem of inaccurate data when evaluating the driving behavior of high-speed vehicles based on ETC data. The general idea is as follows:

[0025] Based on the obtained real-time driving data, real-time driving behavior evaluation indicators are obtained and it is judged whether to give a driving warning. Then, road data is obtained and combined with the real-time driving data to obtain an evaluation indicator for occupying the emergency lane and it is judged whether to conduct an inspection for occupying the emergency lane. Then, based on the obtained passing data, it is judged whether there is fatigue driving. Finally, based on the real-time driving behavior evaluation indicators and the passing data, an overall driving behavior index is obtained and driving feedback is given, achieving the effect of more accurately evaluating the vehicle driving behavior.

[0026] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific embodiments.

[0027] As Figure 1 shown, it is a flowchart of a vehicle driving behavior evaluation method based on ETC data of the Internet of Things provided by an embodiment of the present application. The method includes the following steps: obtaining real-time driving data of a vehicle passing through each ETC gantry after entering the highway, obtaining real-time driving behavior evaluation indicators according to the real-time driving data and judging whether to give a driving warning. The real-time driving behavior evaluation indicators are used to quantify the degree of compliance of the vehicle's real-time driving behavior on the highway with the standard driving behavior, and the driving warning is used to alert the driver to pay attention to restricting the driving behavior; obtaining road data and combining it with the real-time driving data to obtain an evaluation indicator for occupying the emergency lane, and judging whether to conduct an inspection for occupying the emergency lane according to the evaluation indicator for occupying the emergency lane. The evaluation indicator for occupying the emergency lane is used to quantify the degree of compliance of the vehicle occupying the emergency lane, and the inspection for occupying the emergency lane is used to detect the actual situation of the vehicle to check whether it occupies the emergency lane; based on the ETC, obtaining the passing data of the vehicle driving at high speed, and judging whether there is fatigue driving according to the passing data; obtaining an overall driving behavior index according to the real-time driving behavior evaluation indicators and the passing data and giving driving feedback. The overall driving behavior index is used to comprehensively quantify the degree of compliance of the driver's driving behavior, and the driving feedback includes score visualization and giving driving suggestions.

[0028] In this embodiment, by real-time monitoring and evaluating the driving behavior and giving a driving warning in a timely manner, it is beneficial to prevent dangerous driving behaviors and reduce the risk of traffic accidents; and accurately verifying the behavior of occupying the emergency lane to ensure the smoothness of the emergency passage and provide strong guarantee for emergency rescue; through continuous monitoring and feedback of the driving behavior, cultivating the driver's safe driving habits, improving the driving skills and safety awareness, promoting the popularization and compliance of driving behavior norms, and at the same time more accurately evaluating the vehicle driving behavior.

[0029] It should be added that the real-time driving data includes the vehicle detected speed, the number of longitudinal acceleration changes, the number of lateral acceleration changes, the number of abnormal brakes, and the number of abnormal throttle operations; the road data includes the number of lane changes, the number of road lanes, the number of turn signal uses, the lane departure warning frequency, and the average road congestion index; the average road congestion index represents the average value of the road congestion index of the section between two adjacent ETC gantries; the passing data includes the passing duration, the passing kilometers, and the number of service area stops.

[0030] It should be understood that the method for obtaining the real-time driving data is as follows: The ETC gantry usually obtains the vehicle detected speed by combining the communication between the on-board unit (OBU) and the roadside unit (RSU) with the geomagnetic sensor. The OBU device records the current speed of the vehicle, and the ETC system can collect this information periodically; The longitudinal and lateral acceleration changes of the vehicle are detected by the inertial sensors (such as accelerometers and gyroscopes) installed on the vehicle and counted by counters to obtain the number of longitudinal acceleration changes and the number of lateral acceleration changes respectively; The OBU device can obtain engine data, throttle, and brake data. If the vehicle brakes suddenly or accelerates rapidly within a short period of time, the OBU will record it as an abnormal operation and count to obtain the number of abnormal brakes and the number of abnormal throttle operations respectively. The method for judging that the vehicle brakes suddenly or accelerates rapidly within a short period of time is the time window method. For example, within 2 seconds, if the vehicle speed drops by more than 20 km / h, it is recorded as a sudden brake; if within 2 seconds, the vehicle speed rises by more than 20 km / h, it is recorded as a rapid acceleration.

[0031] The method for obtaining the road data is as follows: The lane change situation is monitored by the lane keeping system installed in the vehicle and counted to obtain the number of lane changes. When the vehicle changes lanes to the right, the number of lane changes increases, and vice versa; The number of road lanes can be obtained through road sensors, and the ETC system will automatically match the relevant road attributes according to the vehicle's position data; The Internet of Things collects the turn signal signal data in the vehicle and records the number of times the turn signal is turned on and off to obtain the number of turn signal uses; The lane departure warning system uses the in-vehicle camera to identify the lane markings to judge whether the vehicle deviates from the lane, and the OBU collects the alarm frequency of this system to obtain the lane departure warning frequency; The corresponding average road congestion index is obtained through the traffic management system in the Internet of Things.

[0032] The method for obtaining passing data is as follows: The ETC system records the passing time of the vehicle through the starting ETC gantry and the ending ETC gantry to obtain the passing duration; The ETC system calculates the driving kilometers through the distance between the ETC gantries passed by the vehicle; The ETC system records the entry and exit times and the number of times at the service area entrance and exit to obtain the number of server stops; Through the above data obtained, it can be used for driving behavior analysis, road congestion management, driving safety warning, etc., which is beneficial for traffic management departments and vehicle owners to have a clearer understanding and management of aspects such as driving safety and passing efficiency.

[0033] Furthermore, the specific process for obtaining real-time driving behavior evaluation indicators is as follows: Number the ETC gantries, and obtain reference driving data from a preset database. The reference driving data includes the maximum speed limit and the minimum speed limit; Process the vehicle detection speed and the reference driving data to obtain a vehicle detection speed evaluation indicator, which is used to quantify the standard degree of the vehicle detection speed; Perform a mean operation on the result of processing the sum of the number of longitudinal acceleration changes, the number of lateral acceleration changes, the number of abnormal brakes, and the number of abnormal throttle operations and the vehicle detection speed evaluation indicator to obtain a real-time driving behavior evaluation indicator;

[0034] The specific limit expression of the real-time driving behavior evaluation indicator is as follows:

[0035] ;

[0036] In the formula, n represents the number of the ETC gantry, , represents the total number of ETC gantries, represents the vehicle detection speed of the vehicle passing through the nth ETC gantry, represents the cumulative number of longitudinal acceleration changes of the vehicle reaching the nth ETC gantry, represents the cumulative number of lateral acceleration changes of the vehicle reaching the nth ETC gantry, represents the cumulative number of abnormal brakes of the vehicle reaching the nth ETC gantry, represents the cumulative number of abnormal throttle operations of the vehicle reaching the nth ETC gantry, represents the maximum speed limit, represents the minimum speed limit, represents the real-time driving behavior evaluation indicator of the vehicle reaching the nth ETC gantry.

[0037] In this embodiment, the algorithm comprehensively analyzes the longitudinal acceleration change times, lateral acceleration change times, abnormal braking times, abnormal throttle times, and vehicle detection speed evaluation index to obtain a real-time driving behavior evaluation index. In the formula, when the vehicle detection speed is much greater than the maximum speed limit or much less than the minimum speed limit, the vehicle detection speed evaluation index is small, indicating that the vehicle detection speed of the real-time driving behavior is less compliant with the standard driving behavior; when the longitudinal acceleration change times, lateral acceleration change times, abnormal braking times, and abnormal throttle times are larger, the value of the real-time driving behavior evaluation index is smaller, indicating that the vehicle driving behavior is less compliant with the standard driving behavior.

[0038] As shown in Figure 2, it is a schematic diagram of the change of the real-time driving behavior evaluation index provided by the embodiment of the present application. Among them, (a) is a schematic diagram of the change of the real-time driving behavior evaluation index with the vehicle detection speed, where it is assumed that the longitudinal acceleration change times, lateral acceleration change times, abnormal braking times, and abnormal throttle times are all 10; (b) is a schematic diagram of the change of the real-time driving behavior evaluation index with the longitudinal acceleration change times, where it is assumed that the vehicle detection speed is 90 km / h, and the lateral acceleration change times, abnormal braking times, and abnormal throttle times are all 10; (c) is a schematic diagram of the change of the real-time driving behavior evaluation index with the lateral acceleration change times, where it is assumed that the vehicle detection speed is 90 km / h, and the longitudinal acceleration change times, abnormal braking times, and abnormal throttle times are all 10; (d) is a schematic diagram of the change of the real-time driving behavior evaluation index with the abnormal braking times, where it is assumed that the vehicle detection speed is 90 km / h, and the longitudinal acceleration change times, lateral acceleration change times, and abnormal throttle times are all 10; (e) is a schematic diagram of the change of the real-time driving behavior evaluation index with the abnormal throttle times, where it is assumed that the vehicle detection speed is 90 km / h, and the longitudinal acceleration change times, lateral acceleration change times, and abnormal braking times are all 10, and it is assumed that the maximum speed limit is 120 km / h and the minimum speed limit is 60 km / h.

[0039] As can be seen from Figure (a), when the vehicle detection speed is between the minimum speed limit and the maximum speed limit, the vehicle detection speed evaluation index reaches the maximum, indicating that the vehicle detection speed meets the specifications. In Figures (b), (c), (d), and (e), as the number of longitudinal acceleration changes, the number of lateral acceleration changes, the number of abnormal brakes, and the number of abnormal throttle operations increase, the value of the real-time driving behavior evaluation index decreases accordingly, indicating that during driving, the vehicle driving behavior deviates from the standard driving behavior more frequently; moreover, the higher the number of longitudinal acceleration changes, the number of lateral acceleration changes, the number of abnormal brakes, and the number of abnormal throttle operations, the more it indicates that the driver is used to aggressive driving and frequently performs rapid acceleration, hard braking, and lane-changing operations, and the higher the risk brought by the driving behavior. Among them, the change in longitudinal acceleration mainly comes from acceleration and deceleration operations. Especially hard braking will cause a drastic change in longitudinal acceleration. Therefore, the more the number of abnormal brakes, the more likely the number of longitudinal acceleration changes will be. A high number of lateral acceleration changes may indicate frequent lane-changing or sharp turns, while a high number of abnormal throttle operations indicates that the driver tends to frequently accelerate during driving. This combination often appears in aggressive driving behaviors, such as frequently cutting in and out or chasing in traffic. Therefore, when the number of lateral acceleration changes increases, the number of abnormal throttle operations may also increase; by evaluating the driving behavior of the driver in real time, it not only helps to detect potential safety hazards but also helps to guide the driver to drive in a standardized manner and strictly abide by traffic rules.

[0040] Specifically, the reference driving data is limited by traffic rules and has nothing to do with the ETC gantry, and both the maximum speed limit and the minimum speed limit are obtained from a preset database. In a specific embodiment, both the minimum speed limit and the maximum speed limit are obtained by querying traffic rules. For example, by consulting traffic rules, it can be known that the minimum speed limit is 60 km / h and the maximum speed limit is 120 km / h.

[0041] Furthermore, the specific process for determining whether to issue a driving warning is as follows: Obtain the real-time driving evaluation threshold from the preset database. The real-time driving evaluation threshold is used to determine the degree of compliance of the vehicle's real-time driving behavior with the standard driving behavior on the highway; compare the real-time driving behavior evaluation index with the real-time driving evaluation threshold: If the real-time driving behavior evaluation index is not less than the real-time driving evaluation threshold, no driving warning is issued; if the real-time driving behavior evaluation index is less than the real-time driving evaluation threshold, a driving warning is issued. The driving warning includes a voice warning and a central control warning; the voice warning means warning the driver through voice broadcast to pay attention to driving habits and informing the potential hazards of the current driving behavior; the central control warning means visualizing the real-time driving behavior evaluation index through the vehicle's central control display screen and informing the driver.

[0042] In this embodiment, the driving warning process evaluates and judges real-time driving behaviors through a preset driving evaluation threshold. When the driving behavior deviates more from the standard driving behavior (i.e., the real-time driving behavior evaluation index is less than the real-time driving evaluation threshold), feedback is immediately given through voice warnings and central control warnings, effectively preventing potential safety hazards and enhancing the safety and interactivity during driving. At the same time, this process also promotes the popularization and compliance of driving behavior norms, contributing to the construction of a safer and more orderly traffic environment.

[0043] Specifically, the real-time driving evaluation threshold is obtained from a preset database. In a specific embodiment, the real-time driving data corresponding to the situation of violating traffic rules is substituted into the specific limit expression of the real-time driving behavior evaluation index, and the corresponding data set is obtained. Denote the result of performing a mean operation on the data set as the real-time driving evaluation threshold.

[0044] Furthermore, the specific obtaining process of the emergency lane occupancy evaluation index is as follows: Obtain the emergency lane evaluation weights from a preset database. The emergency lane evaluation weights include a congestion weight and a lane change weight. The congestion weight is used to represent the probability of the emergency lane being occupied due to road congestion, and the lane change weight represents the probability of a vehicle changing lanes and occupying the emergency lane; Number the driving lanes, and obtain a lane change index based on the number of road channels and the number of lane changes. The number of road channels represents the sum of the total number of driving lanes and the number of emergency lanes. The lane change index is used to quantify the probability of a vehicle changing lanes to the emergency lane; Based on the obtained number of turn signal uses, deviation from lane alarm frequency, average road congestion index, emergency lane evaluation weights, and lane change index, obtain the emergency lane occupancy evaluation index;

[0045] The specific limit expression of the emergency lane occupancy evaluation index is as follows:

[0046] ;

[0047] ;

[0048] In the formula, n represents the number of the ETC gantry, , represents the total number of ETC gantries, m represents the number of the driving lane, , represents the total number of driving lanes, represents the number of road channels corresponding to the nth ETC gantry, represents the driving lane where the vehicle is located when it reaches the nth ETC gantry, represents the cumulative number of lane changes of the vehicle when it reaches the nth ETC gantry, represents the lane change index of the vehicle when it reaches the nth ETC gantry, represents the cumulative number of turn signal uses of the vehicle when it reaches the nth ETC gantry, represents the cumulative deviation lane alarm frequency when the vehicle reaches the nth ETC gantry, represents the average road congestion index of the nth ETC gantry, represents the congestion weight, represents the lane change weight, represents the evaluation index of the vehicle occupying the emergency lane when reaching the nth ETC gantry.

[0049] In this embodiment, the algorithm comprehensively analyzes the evaluation index of occupying the emergency lane by combining the number of times the turn signal is used, the deviation lane alarm frequency, the average road congestion index, the emergency lane evaluation weight, and the lane change index. In the formula, based on the average road congestion index, when the lane change index is 1, it indicates that the emergency lane is not occupied, and then the impact on the evaluation index of occupying the emergency lane reaches the minimum. Otherwise, when the lane change index is 0, the impact on the evaluation index of occupying the emergency lane reaches the maximum; among them, the value range of the average road congestion index is from 0 to 1, and the range of the congestion weight is also between 0 and 1. Therefore, the product of the average road congestion index and the congestion weight (i.e., ) is also between 0 and 1, and the number m of the driving lane represents the specific lane where the vehicle is driving. Combining the number of lane changes helps to more accurately analyze whether the vehicle changes lanes onto the emergency lane; in addition, the relationship between the number of times the turn signal is used and the evaluation index of occupying the emergency lane is negatively correlated. Without considering the situation of not using the turn signal for the time being, as the number of times the turn signal is used increases, it means that the probability of the vehicle being in the driving lane is greater, and the possibility of driving on the emergency lane is smaller (when the vehicle is driving on the emergency lane, usually the emergency road is unobstructed and the number of times the turn signal is used decreases), and the evaluation index of occupying the emergency lane is smaller. While the higher the deviation lane alarm frequency, the more positively correlated it is with the evaluation of occupying the emergency lane. As the deviation lane alarm frequency increases, the evaluation index of occupying the emergency lane also increases, indicating that the more times the turn signal is used, the smaller the probability of the vehicle driving on the emergency lane, and vice versa. When the deviation lane alarm frequency is greater, it indicates that the vehicle deviates from the lane more frequently, and then the probability of the vehicle deviating to the emergency lane is higher; generally speaking, the number of lane changes is directly related to the number of road channels. On multi-lane roads (such as highways or urban expressways), the driver has more opportunities to change lanes. Therefore, the number of lane changes is often higher, and the turn signal should be used when changing lanes. Therefore, theoretically, the number of lane changes and the number of times the turn signal is used should be close; through the analysis of the evaluation index of occupying the emergency lane, it helps to detect in time whether the vehicle occupies the emergency lane, so as to guide the driver to correct in time to form good driving habits, and at the same time urge the driver to strictly abide by traffic regulations.

[0050] Specifically, the congestion weight is a value determined based on the average road congestion index in a preset database, which reflects the importance of the average road congestion level for evaluating the indicator of occupying the emergency lane. In practical applications, the weight value matching the current average road congestion index can be directly retrieved from the preset database. This matching is based on a predefined mapping relationship, that is, a mapping set is established between the average road congestion index and the weights corresponding to the evaluation indicators of occupying the emergency lane. By inputting the real-time obtained average road congestion index into this mapping set, the corresponding weight value can be found. In this example, the mapping relationship is a strict one-to-one relationship, and the value range of the weight is limited to 0 to 1.

[0051] Specifically, in this example, the sum of the congestion weight and the lane-changing weight is 1.

[0052] Furthermore, the specific process of verifying the occupation of the emergency lane is as follows: Obtain the emergency lane occupation threshold from the preset database, and the emergency lane occupation threshold is used to judge the compliance of the vehicle occupying the emergency lane; Compare the evaluation indicator of occupying the emergency lane with the emergency lane occupation threshold: If the evaluation indicator of occupying the emergency lane is less than the emergency lane occupation threshold, no verification of occupying the emergency lane is performed; If the evaluation indicator of occupying the emergency lane is not less than the emergency lane occupation threshold, the vehicle vision system is enabled to verify whether the vehicle is located in the emergency lane. If the vehicle is located in the emergency lane, the driver is immediately reminded to drive out of the emergency lane, otherwise, the verification of occupying the emergency lane is exited.

[0053] In this embodiment, the process of verifying the occupation of the emergency lane obtains the emergency lane occupation threshold through the preset database and uses the vehicle vision system for intelligent verification, realizing the automatic identification and processing of the behavior of illegally occupying the emergency lane; This process not only improves the standardization of the use of the emergency lane, enhances road safety, and improves the efficiency and accuracy of verification; At the same time, the entire verification process is automated, reducing the links of manual judgment and intervention, reducing misjudgment and missed judgment caused by human factors, and improving the fairness and objectivity of verification.

[0054] Specifically, the emergency lane occupation threshold is obtained from the preset database. In a specific embodiment, the road data corresponding to the situation of occupying the emergency lane in the historical data is substituted into the specific limit expression of the evaluation indicator of occupying the emergency lane, and the corresponding data set is obtained. Denote the result of performing the mean operation on the data set as the emergency lane occupation threshold.

[0055] Furthermore, the specific limit expression of the whole driving behavior index is as follows:

[0056] ;

[0057] In the formula, n represents the number of the ETC gantry, , represents the total number of ETC gantries, represents the number of kilometers traveled, represents the real-time driving behavior evaluation index of the vehicle arriving at the nth ETC gantry, represents the full-course driving behavior index, and e represents the natural constant.

[0058] In this embodiment, the algorithm comprehensively analyzes the full-course driving behavior index by combining the number of kilometers traveled and the real-time driving behavior evaluation index. In the formula, the number of kilometers traveled is processed as the base. When the number of kilometers traveled is larger, the base is larger and the base is greater than 1. In addition, when the real-time driving behavior evaluation indexes of each ETC gantry are larger, the result of the average operation on the real-time driving behavior evaluation indexes of all ETC gantries is larger. Then the full-course driving behavior index is larger, indicating that the vehicle driving behavior is more standardized. By evaluating the driving behavior of the driver based on the number of kilometers traveled, the vehicle driving behavior evaluation method is made more reasonable. And by analyzing the real-time driving behavior evaluation indexes of each ETC gantry, the driving behavior of the vehicle is analyzed more comprehensively and comprehensively, so as to give the driver more accurate driving feedback.

[0059] Specifically, denote , as the real-time driving average value, and combine the number of kilometers traveled to obtain the data change table of the full-course driving behavior index, as shown in Table 1 specifically:

[0060] Table 1 Data change table of full-course driving behavior index

[0061]

[0062] It can be seen from Table 1 that as the number of kilometers traveled and the real-time driving average value increase, the full-course driving behavior index also increases. For example, when the number of kilometers traveled increases from 60 in the first row to 300 in the fifth row, and the real-time driving average value increases from 0.5 in the first row to 0.9 in the fifth row, the full-course driving behavior index also increases from 1.475 in the first row to 2.013 in the fifth row, indicating that both the number of kilometers traveled and the real-time driving average value are positively correlated with the full-course driving behavior index; through the analysis of the full-course driving behavior index, it is beneficial to evaluate the vehicle driving behavior more comprehensively and accurately and standardize the driving habits of the driver.

[0063] Further, the specific steps for determining whether there is fatigue driving are as follows: Step 1, obtain the driving duration and the number of stops at service areas from the passing data. If the number of stops at service areas is 0, then execute Step 3; otherwise, execute Step 2. Step 2, record the operation result of the ratio of the driving duration to the number of stops at service areas as the driving duration and execute Step 3. Step 3, compare the driving duration with the preset safe driving duration. If the driving duration is not less than the preset safe driving duration, it is determined that the driver is fatigued; otherwise, there is no fatigue driving. The preset safe driving duration is generally set to 4 hours.

[0064] In this embodiment, the preset safe driving duration is set according to the provisions of traffic rules. And the specific steps for determining whether there is fatigue driving, by comprehensively considering the driving duration and the number of stops at service areas and using a scientific determination method, can accurately and timely identify the fatigue driving situation of the driver. When it is determined that there is fatigue driving, a warning can be issued in a timely manner to remind the driver to pay attention to rest and ensure driving safety. This method is simple to operate and easy to promote, helps prevent traffic accidents caused by fatigue driving, and improves the level of road traffic safety.

[0065] Further, the specific content of the driving feedback is as follows: Obtain the full - course evaluation interval from the preset database. The full - course evaluation interval includes the first evaluation interval and the second evaluation interval. Compare the full - course driving behavior index with the full - course evaluation interval: If the full - course driving behavior index is within the first evaluation interval, record the evaluation level of the driver's driving behavior as qualified and visualize the score on the vehicle central control display screen. If the full - course driving behavior index is within the second evaluation interval, record the evaluation level of the driver's driving behavior as unqualified and give driving feedback on the vehicle central control display screen. The driving feedback includes score visualization and relevant driving suggestions for the driver.

[0066] In this embodiment, the first evaluation interval represents the range where the full - course driving behavior index is qualified, and the second evaluation interval represents the range where the full - course driving behavior index is unqualified. By setting the full - course evaluation interval and evaluating the full - course driving behavior index, it can prompt the driver to pay more attention to the normativity of driving behavior during driving, thereby reducing the risk of traffic accidents. At the same time, the score visualization and driving suggestions in the driving feedback can intuitively display the driver's driving behavior performance and remind the driver to pay attention to improvement, thereby enhancing the driver's driving safety awareness. This method not only improves the normativity of driving behavior, enhances the driving safety awareness, but also realizes personalized driving guidance and improves the driving experience.

[0067] Specifically, the full evaluation interval is obtained from a preset database. In a specific embodiment, all real-time driving behavior evaluation indicators and the corresponding driving kilometers are substituted into the specific limit expression of the full driving behavior index to obtain a corresponding data set, and the minimum value, maximum value, and median value of the data set are obtained. Then, the value range from the minimum value to the median value is recorded as the second evaluation interval, and the value range from the median value to the maximum value is recorded as the first evaluation interval.

[0068] The vehicle driving behavior evaluation system based on IoT ETC data provided by the embodiments of the present application includes: a real-time driving evaluation module, an emergency lane evaluation module, a fatigue driving judgment module, and a full driving evaluation module. Among them, the real-time driving evaluation module is used to obtain real-time driving data of the vehicle passing through each ETC gantry after entering the highway, obtain real-time driving behavior evaluation indicators based on the real-time driving data, and judge whether to issue a driving warning. The real-time driving behavior evaluation indicators are used to quantify the compliance degree of the vehicle's real-time driving behavior on the highway with the standard driving behavior, and the driving warning is used to alert the driver to pay attention to restricting the driving behavior. The emergency lane evaluation module is used to obtain the occupancy emergency lane evaluation indicators by obtaining road data and combining real-time driving data, and judge whether to conduct an occupancy emergency lane verification based on the occupancy emergency lane evaluation indicators. The occupancy emergency lane evaluation indicators are used to quantify the compliance degree of the vehicle occupying the emergency lane, and the occupancy emergency lane verification is used to detect the actual situation of the vehicle to check whether it occupies the emergency lane. The fatigue driving judgment module is used to judge whether there is fatigue driving based on the passing data obtained by the ETC for the vehicle's high-speed driving. The full driving evaluation module is used to obtain the full driving behavior index based on the real-time driving behavior evaluation indicators and the passing data and give driving feedback. The full driving behavior index is used to comprehensively quantify the driving behavior standard degree of the driver, and the driving feedback includes score visualization and giving driving suggestions.

[0069] In this embodiment, the system uses IoT technology and ETC data to realize real-time monitoring, evaluation, and feedback of driving behavior, improves the efficiency and intelligent level of traffic management, and also provides data support for traffic management departments, which helps to formulate more scientific and reasonable traffic management measures.

[0070] In summary, the embodiments of the present application obtain real-time driving behavior evaluation indicators from the obtained real-time driving data and determine whether to issue a driving warning. Then, road data is obtained and combined with the real-time driving data to obtain an evaluation indicator for occupying the emergency lane and determine whether to conduct an inspection for occupying the emergency lane. Then, based on the obtained traffic data, it is determined whether there is fatigue driving. Finally, the overall driving behavior index is obtained based on the real-time driving behavior evaluation indicators and the traffic data and driving feedback is provided, thereby more accurately evaluating the driving behavior of the vehicle, and further achieving a more accurate evaluation of the vehicle driving behavior, effectively solving the problem of inaccurate data in the prior art when evaluating the driving behavior of high-speed vehicles based on ETC data.

[0071] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, system, or computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0072] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices produce a machine for realizing the functions specified in Figure 1 one or more of the processes Figure 1 or a plurality of processes and / or blocks

[0073] a device for the functions specified in one or more of the blocks or a plurality of blocks. Figure 1 one or more of the processes Figure 1 or a plurality of processes and / or blocks

[0074] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction device that realizes the functions specified in Figure 1Steps of the functions specified in one or more processes and / or boxes Figure 1 Steps of the functions specified in one or more boxes

[0075] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0076] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A method for evaluating vehicle driving behavior based on ETC data of the Internet of Things, characterized in that Including the following steps: Obtain the real-time driving data of the vehicle passing through each ETC gantry after entering the highway, obtain the real-time driving behavior evaluation index based on the real-time driving data and determine whether to give a driving warning. The real-time driving behavior evaluation index is used to quantify the degree of compliance between the real-time driving behavior of the vehicle on the highway and the standard driving behavior; Obtain the road data and combine it with the real-time driving data to obtain the evaluation index for occupying the emergency lane, and determine whether to conduct an inspection for occupying the emergency lane based on the evaluation index for occupying the emergency lane. The evaluation index for occupying the emergency lane is used to quantify the degree of compliance of the vehicle occupying the emergency lane; Based on the ETC, obtain the passing data of the vehicle driving at high speed, and determine whether there is fatigue driving according to the passing data; Obtain the whole-course driving behavior index based on the real-time driving behavior evaluation index and the passing data and give driving feedback. The whole-course driving behavior index is used to comprehensively quantify the degree of compliance of the driving behavior of the driver; The specific process for obtaining the real-time driving behavior evaluation index is as follows: Number the ETC gantries, and obtain the reference driving data from the preset database. The reference driving data includes the maximum speed limit and the minimum speed limit; Process the vehicle detection speed and the reference driving data to obtain the vehicle detection speed evaluation index. The vehicle detection speed evaluation index is used to quantify the degree of compliance of the vehicle detection speed; Perform a mean operation on the result of processing the sum of the number of longitudinal acceleration changes, the number of lateral acceleration changes, the number of abnormal brakes, and the number of abnormal throttle operations and the vehicle detection speed evaluation index to obtain the real-time driving behavior evaluation index; The specific process for obtaining the evaluation index for occupying the emergency lane is as follows: Obtain the emergency lane evaluation weights from the preset database. The emergency lane evaluation weights include the congestion weight and the lane change weight; Number the driving lanes, and obtain the lane change index based on the number of road lanes and the number of lane changes. The lane change index is used to quantify the probability of the vehicle changing lanes to the emergency lane; Based on the obtained number of turn signal uses, the deviation from lane warning frequency, the average road congestion index, the emergency lane evaluation weights, and the lane change index, obtain the evaluation index for occupying the emergency lane.

2. The vehicle driving behavior evaluation method for ETC data based on the Internet of Things according to claim 1, wherein: The real-time driving data includes the vehicle detection speed, the number of longitudinal acceleration changes, the number of lateral acceleration changes, the number of abnormal brakes, and the number of abnormal throttle operations; The road data includes the number of lane changes, the number of road lanes, the number of turn signal uses, the deviation from lane warning frequency, and the average road congestion index; The average road congestion index represents the mean value of the road congestion indices of the sections between two adjacent ETC gantries; The passing data includes the passing duration, the passing kilometers, and the number of stops at service areas.

3. The vehicle driving behavior evaluation method for ETC data based on the Internet of Things according to claim 1, characterized in that: The specific process for determining whether to give a driving warning is as follows: Obtain the real-time driving evaluation threshold from the preset database. The real-time driving evaluation threshold is used to judge the degree of compliance between the real-time driving behavior of the vehicle on the highway and the standard driving behavior; Compare the real-time driving behavior evaluation index with the real-time driving evaluation threshold: If the real-time driving behavior evaluation index is not less than the real-time driving evaluation threshold, no driving warning is given; If the real-time driving behavior evaluation index is less than the real-time driving evaluation threshold, a driving warning is issued, and the driving warning includes a voice warning and a central control warning; The voice warning indicates that the driver is warned of their driving habits through voice broadcast and informed of the potential hazards of the current driving behavior; The central control warning indicates that the real-time driving behavior evaluation index is visually informed to the driver through the vehicle's central control display screen.

4. The vehicle driving behavior evaluation method based on ETC data of the Internet of Things according to claim 1, wherein: The specific process of verifying the occupation of the emergency lane is as follows: Obtain the emergency lane occupation threshold from the preset database, and the emergency lane occupation threshold is used to judge the compliance degree of the vehicle occupying the emergency lane; Compare the emergency lane occupation evaluation index with the emergency lane occupation threshold: If the emergency lane occupation evaluation index is less than the emergency lane occupation threshold, the verification of the occupation of the emergency lane is not carried out; If the emergency lane occupation evaluation index is not less than the emergency lane occupation threshold, enable the vehicle vision system to verify whether the vehicle is located in the emergency lane. If the vehicle is located in the emergency lane, immediately remind the driver to drive out of the emergency lane, otherwise exit the verification of the occupation of the emergency lane.

5. The vehicle driving behavior evaluation method based on ETC data of the Internet of Things according to claim 1, wherein: The specific limit expression of the whole journey driving behavior index is as follows: ； Wherein, n represents the number of the ETC gantry, , represents the total number of ETC gantries, represents the number of kilometers traveled, represents the real-time driving behavior evaluation index of the vehicle arriving at the nth ETC gantry, represents the whole journey driving behavior index, and e represents the natural constant.

6. The vehicle driving behavior evaluation method based on ETC data of the Internet of Things according to claim 1, characterized in that: The specific steps to judge whether there is fatigue driving are as follows: Step 1, obtain the driving duration and the number of stops at service areas from the traffic data. If the number of stops at service areas is 0, execute Step 3, otherwise execute Step 2; Step 2, record the operation result of the ratio of the driving duration to the number of stops at service areas as the driving duration and execute Step 3; Step 3, compare the driving duration with the preset safe driving duration. If the driving duration is not less than the preset safe driving duration, it is determined that the driver has fatigue driving, otherwise there is no fatigue driving.

7. The vehicle driving behavior evaluation method based on ETC data of the Internet of Things according to claim 1, characterized in that: The specific content of the driving feedback is as follows: Obtain the whole journey evaluation interval from the preset database, and the whole journey evaluation interval includes the first evaluation interval and the second evaluation interval; Compare the whole journey driving behavior index with the whole journey evaluation interval: If the whole journey driving behavior index is within the first evaluation interval, record the evaluation level of the driver's driving behavior as qualified and visualize the score on the vehicle's central control display screen; If the whole journey driving behavior index is within the second evaluation interval, record the evaluation level of the driver's driving behavior as unqualified and give driving feedback on the vehicle's central control display screen. The driving feedback includes score visualization.

8. An in-vehicle driving behavior evaluation system based on Internet of Things ETC data, the in-vehicle driving behavior evaluation system being used to execute the in-vehicle driving behavior evaluation method according to any one of claims 1-7, the evaluation system comprising: Real-time driving evaluation module, emergency lane evaluation module, fatigue driving judgment module and whole journey driving evaluation module; Among them, the real-time driving evaluation module is used to obtain the real-time driving data of the vehicle passing through each ETC gantry after entering the highway, obtain the real-time driving behavior evaluation index according to the real-time driving data and judge whether to issue a driving warning. The real-time driving behavior evaluation index is used to quantify the compliance degree of the vehicle's real-time driving behavior on the highway with the standard driving behavior; The emergency lane evaluation module is used to obtain road data and combine it with the real-time driving data to obtain the emergency lane occupation evaluation index, and judge whether to verify the occupation of the emergency lane according to the emergency lane occupation evaluation index. The emergency lane occupation evaluation index is used to quantify the compliance degree of the vehicle occupying the emergency lane; The fatigue driving judgment module is used to obtain the passing data of the vehicle driving at high speed based on ETC, and judge whether there is fatigue driving according to the passing data; The whole journey driving evaluation module is used to obtain the whole journey driving behavior index according to the real-time driving behavior evaluation index and the passing data and give driving feedback, and the whole journey driving behavior index is used to comprehensively quantify the driving behavior standard degree of the driver.

Images