Driving behavior recognition method, behavior recognition equipment and vehicle

Abstract

The invention discloses a driving behavior recognition method, behavior recognition equipment and a vehicle, and relates to the technical field of driving behavior recognition. The behavior recognition equipment of the vehicle can obtain the driving characteristic data of the vehicle under the condition that the driving scene of the vehicle is a dangerous driving scene, and the driving characteristic data can reflect the driving behavior of a driver in the driving scene. Afterwards, the behavior recognition device can recognize the driving behavior of the driver based on the driving characteristic data to obtain a recognition result (namely dangerous driving behavior or safe driving behavior). Moreover, the driving behavior in the dangerous driving scene can more accurately reflect the driving habit of the driver, so that pricing based on the identification result of the driving behavior in the dangerous driving scene can ensure that the premium pricing of the UBI is more reasonable.

Description

Technical Field

[0001] The present application relates to the technical field of driving behavior recognition, and in particular to a driving behavior recognition method, a behavior recognition device and a vehicle. Background Art

[0002] Usage based insurance (UBI) refers to vehicle insurance that prices insurance premiums based on driving behavior and vehicle usage data (such as mileage and fuel consumption, etc.). As can be seen, UBI can price insurance premiums based on the driver's driving behavior, an important factor that affects traffic accidents, so UBI's premium pricing is more reasonable.

[0003] However, before pricing insurance premiums based on the driver's driving behavior, it is necessary to identify the driver's driving behavior to provide a basis for pricing insurance premiums. Summary of the invention

[0004] The present application provides a driving behavior recognition method, a behavior recognition device and a vehicle, which can effectively recognize the driving behavior of the driver of the vehicle.

[0005] In a first aspect, the present application provides a method for identifying driving behavior, the method comprising:

[0006] During the driving process of the vehicle, if it is determined that the driving scene of the vehicle is a dangerous driving scene, obtaining driving characteristic data of the vehicle, wherein the driving characteristic data is used to reflect the driving behavior of the driver in the driving scene;

[0007] Based on the driving characteristic data, it is identified whether the driving behavior in the driving scenario is a dangerous driving behavior.

[0008] The vehicle behavior recognition device provided in the present application can obtain the driving characteristic data of the vehicle when the driving scenario of the vehicle is a dangerous driving scenario, and the driving characteristic data can reflect the driving behavior of the driver in the driving scenario. Afterwards, the behavior recognition device can identify the driving behavior of the driver based on the driving characteristic data to obtain an identification result (i.e., dangerous driving behavior or safe driving behavior). Moreover, since the driving behavior in a dangerous driving scenario can more accurately reflect the driver's driving habits, pricing based on the identification result of the driving behavior in a dangerous driving scenario can ensure that the UBI premium pricing is more reasonable.

[0009] Optionally, the acquiring the driving characteristic data of the vehicle includes:

[0010] According to the correspondence between the scene and the characteristic parameters, obtaining the target characteristic parameters corresponding to the driving scene;

[0011] The parameter value of the target characteristic parameter is used as the driving characteristic data of the vehicle.

[0012] In this way, the efficiency of the behavior recognition device in determining the recognition result can be improved while ensuring that the behavior recognition device obtains the recognition result of the driving behavior.

[0013] Optionally, the method further includes:

[0014] If the driving behavior in the driving scenario is identified as a dangerous driving behavior, increasing the count value corresponding to the driving scenario;

[0015] The count value is positively correlated with the number of times dangerous driving behavior occurs in the driving scenario.

[0016] Optionally, there are multiple dangerous driving scenarios; the method further includes:

[0017] The dangerousness level of the driver's comprehensive driving behavior is determined according to the count values ​​corresponding to the multiple dangerous driving scenarios.

[0018] Since the behavior recognition device can comprehensively consider the count values ​​corresponding to various dangerous driving scenarios when determining the dangerousness level of the driver's comprehensive driving behavior, it can ensure that the determined dangerousness level can more accurately reflect the overall driving quality of the driver.

[0019] Optionally, the danger level is represented by a numerical value; and determining the danger level of the driver's comprehensive driving behavior according to the count values ​​corresponding to the multiple dangerous driving scenarios includes:

[0020] The count values ​​corresponding to the multiple dangerous driving scenarios are weighted and summed to obtain the value. Since the driving behaviors in different dangerous driving scenarios reflect the driver's driving habits to different degrees, the weighted sum of the count values ​​corresponding to the multiple dangerous driving scenarios can further ensure that the determined degree of danger can more accurately reflect the overall driving quality of the driver.

[0021] Optionally, the method further includes:

[0022] If it is identified that the driving behavior in the driving scenario is a safe driving behavior, the count value corresponding to the driving scenario is reduced.

[0023] Optionally, the method further includes:

[0024] The degree of danger is displayed on a display screen, so that the driver can be effectively reminded, so that the driver can improve his driving habits on his own and optimize his driving behavior.

[0025] In a second aspect, a vehicle is provided, the vehicle comprising: a behavior recognition device; the behavior recognition device is used to:

[0026] During the driving process of the vehicle, if it is determined that the driving scene of the vehicle is a dangerous driving scene, obtaining driving characteristic data of the vehicle, wherein the driving characteristic data is used to reflect the driving behavior of the driver in the driving scene;

[0027] Based on the driving characteristic data, it is identified whether the driving behavior in the driving scenario is a dangerous driving behavior.

[0028] The vehicle behavior recognition device provided in the present application can obtain the driving characteristic data of the vehicle when the driving scenario of the vehicle is a dangerous driving scenario, and the driving characteristic data can reflect the driving behavior of the driver in the driving scenario. Afterwards, the behavior recognition device can identify the driving behavior of the driver based on the driving characteristic data to obtain an identification result (i.e., dangerous driving behavior or safe driving behavior). Moreover, since the driving behavior in a dangerous driving scenario can more accurately reflect the driver's driving habits, pricing based on the identification result of the driving behavior in a dangerous driving scenario can ensure that the UBI premium pricing is more reasonable.

[0029] In a third aspect, a behavior recognition device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the driving behavior recognition method described in the above aspect is implemented.

[0030] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for identifying driving behavior described in the above aspects is implemented.

[0031] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present application. Moreover, the same reference numerals are used throughout the drawings to represent the same components. In the drawings:

[0033] Figure 1 is a structural schematic diagram of a vehicle provided in an embodiment of the present application;

[0034] Figure 2 is a flow chart of a driving behavior recognition method provided in an embodiment of the present application;

[0035] Figure 3 is a flow chart of another driving behavior identification method provided in an embodiment of the present application;

[0036] Figure 4 is a schematic diagram of a lane change scenario provided in an embodiment of the present application;

[0037] Figure 5 It is a schematic diagram of the structure of a T-Box provided in an embodiment of the present application. DETAILED DESCRIPTION

[0038] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0040] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0041] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0042] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0043] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0044] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0045] Traditional car insurance pricing models only consider vehicle usage data when pricing, such as vehicle usage, vehicle age, vehicle purchase price, number of seats, vehicle purpose, and vehicle mileage. However, a large number of traffic accidents are caused by the driver's driving behavior. Traditional car insurance pricing models do not consider the driver's driving behavior when pricing, resulting in unreasonable and unfair premium pricing that cannot meet the current market needs.

[0046] With the development of Internet of Vehicles technology, UBI has emerged. UBI is a vehicle insurance that prices insurance premiums based on driving behavior and vehicle usage data. Since UBI can price insurance premiums based on the driver's driving behavior and vehicle usage data, the premium pricing of UBI is more reasonable. Accurately identifying the driver's driving behavior is an important basis for accurate pricing of UBI.

[0047] The embodiment of the present application provides a method for identifying driving behavior. The vehicle's behavior recognition device can obtain the vehicle's driving characteristic data when the vehicle's driving scenario is a dangerous driving scenario. The driving characteristic data can reflect the driver's driving behavior in the driving scenario. Afterwards, the behavior recognition device can identify the driver's driving behavior based on the driving characteristic data to obtain an identification result (i.e., dangerous driving behavior or safe driving behavior). In addition, since the driving behavior in a dangerous driving scenario can more accurately reflect the driver's driving habits, pricing based on the identification result of the driving behavior in the dangerous driving scenario can ensure that the UBI premium pricing is more reasonable.

[0048] Figure 1 is a schematic diagram of the structure of a vehicle provided in an embodiment of the present application. Figure 1 The vehicle includes: a behavior recognition device 01, a forward camera 02, a radar 03 and an inertial measurement unit (IMU) 04.

[0049] Among them, the forward camera 02, the radar 03 and the IMU 04 are all connected to the behavior recognition device 01. The behavior recognition device 01 includes one or more processors and a memory that can store one or more programs, and the behavior recognition device 01 can be used to obtain basic data of the vehicle during driving (such as the cabin temperature and the remaining fuel and power, etc.).

[0050] The forward camera 02 and the radar 03 can both be used to collect information about the surrounding environment of the vehicle while it is traveling. The IMU 04 is a sensor mainly used to measure acceleration and rotational motion, that is, the IMU 04 can be used to collect the acceleration of the vehicle while it is traveling.

[0051] It is understandable that the number of radars 03 can be multiple, for example three. The three radars 03 are respectively located in front, on the left and on the right of the vehicle body. Optionally, the radar 03 can be an ultrasonic radar, a laser radar or a millimeter wave radar (radio detection and ranging, RADAR).

[0052] Optionally, the behavior recognition device 01 may be a telematics box (T-Box), which may also be referred to as a vehicle networking communication terminal and a remote vehicle terminal. The T-Box may be a post-installed T-Box for a vehicle. At this point, the T-Box may be connected to the vehicle's on-board diagnostic (OBD) interface to install a T-Box for a vehicle that does not have a pre-installed T-Box. Pre-installed without a T-Box means that the vehicle is not installed with a T-Box before leaving the factory.

[0053] At least one of the forward camera 02, the radar 03 and the IMU 04 may be installed before the vehicle leaves the factory. Alternatively, the forward camera 02 may be a rear-mounted camera, the radar 03 may be a rear-mounted radar, and the IMU 04 may be a rear-mounted IMU.

[0054] It can be understood that, when the T-Box, the forward camera 02, the radar 03 and the IMU 04 are all installed later, the forward camera 02 can be connected to the T-Box via an Ethernet or FlexRay communication interface, and the radar 03 and the IMU 04 can be connected to the T-Box via a controller area network (CAN) communication interface.

[0055] If the T-Box is a post-installed T-Box and the IMU 04 is installed before the vehicle leaves the factory, the T-Box can obtain the data collected by the IMU 04 through the OBD interface.

[0056] The present application provides a method for identifying driving behavior, which is applied to a vehicle behavior identification device. The following uses the behavior identification device as a vehicle T-Box to illustrate the identification method. Figure 2 , the method comprising:

[0057] Step 101: During the driving process of the vehicle, if it is determined that the driving scene of the vehicle is a dangerous driving scene, the driving characteristic data of the vehicle is obtained.

[0058] The driving characteristic data is used to reflect the driver's driving behavior in a driving scenario.

[0059] In an embodiment of the present application, when it is determined that the driving scenario of the vehicle is a dangerous driving scenario, the T-Box of the vehicle can use all the status data of the vehicle at this time (such as speed, acceleration, and distance to other vehicles, etc.) as driving characteristic data.

[0060] Alternatively, the T-Box may determine the target characteristic parameter corresponding to the dangerous driving scenario based on the pre-stored correspondence between the scenario and the characteristic parameter, and use the parameter value of the target characteristic parameter as the driving characteristic data.

[0061] Step 102: Based on the driving characteristic data, identify whether the driving behavior in the driving scenario is a dangerous driving behavior.

[0062] For example, a behavior recognition model may be pre-installed in the T-Box. The T-Box may input driving feature data into the behavior recognition model to obtain a recognition result of the driving behavior output by the behavior recognition model. The recognition result may be a dangerous driving behavior or a safe driving behavior.

[0063] It is understandable that before inputting the driving feature data into the behavior recognition model, the T-Box may also obtain multiple training data and perform model training on the multiple training data to obtain a behavior recognition model. Each training data includes: sample feature data for reflecting the driver's sample driving behavior in a dangerous driving scenario, and a sample recognition result of the sample driving behavior.

[0064] In summary, the embodiment of the present application provides a method for identifying driving behavior, and the vehicle's behavior recognition device can obtain the vehicle's driving characteristic data when the vehicle's driving scenario is a dangerous driving scenario, and the driving characteristic data can reflect the driver's driving behavior in the driving scenario. Afterwards, the behavior recognition device can identify the driver's driving behavior based on the driving characteristic data to obtain an identification result (i.e., dangerous driving behavior or safe driving behavior). Moreover, since the driving behavior in a dangerous driving scenario can more accurately reflect the driver's driving habits, pricing based on the identification result of the driving behavior in a dangerous driving scenario can ensure that the UBI premium pricing is more reasonable.

[0065] Figure 3 is a flowchart of another driving behavior recognition method provided in an embodiment of the present application, which can be applied to a vehicle behavior recognition device. Continuing to take the behavior recognition device as a T-Box as an example, the driving behavior recognition method provided in an embodiment of the present application is exemplarily described. Figure 3 , the method may include:

[0066] Step 201: During the driving process of the vehicle, if it is determined that the driving scene of the vehicle is a dangerous driving scene, the driving characteristic data of the vehicle is obtained.

[0067] The driving characteristic data is used to reflect the driving behavior of the driver in the driving scenario. There may be multiple dangerous driving scenarios. The multiple dangerous driving scenarios may include: at least two of the following: passing a traffic light, passing a zebra crossing, changing lanes, driving on a curve, passing a blind spot, driving with a small distance between vehicles, and overtaking.

[0068] The multiple dangerous driving scenarios may be pre-stored in the vehicle. For example, the vehicle developer may determine driving scenarios that are prone to accidents based on road traffic safety statistics as dangerous driving scenarios and pre-set them in the vehicle before the vehicle leaves the factory.

[0069] In the embodiment of the present application, the driving characteristic data may include: parameter values ​​of characteristic parameters. And for different dangerous driving scenarios, the characteristic parameters that the vehicle needs to obtain are different. Based on this, the process of the vehicle's T-Box obtaining driving characteristic data in the driving scenario may include:

[0070] T-Box first obtains the target feature parameter corresponding to the driving scene based on the correspondence between the scene and the feature parameter. Then, T-Box obtains the parameter value of the target feature parameter and uses the parameter value of the target feature parameter as the driving feature data under the driving scene. The correspondence between the scene and the feature parameter can be pre-stored by the vehicle. And the feature parameter corresponding to each scene recorded in the correspondence is the parameter that has a greater impact on the recognition result of the driving behavior under the scene.

[0071] In this way, the efficiency of T-Box in determining the recognition result can be improved while ensuring that T-Box obtains the recognition result of the driving behavior.

[0072] For example, if the dangerous driving scene is a scene of passing a traffic light, the corresponding characteristic parameters may include: the color of the traffic light and the acceleration of the vehicle. If the dangerous driving scene is a scene of passing a zebra crossing, the corresponding characteristic parameters may include: the acceleration of the vehicle. If the dangerous driving scene is a scene of passing a blind spot, the corresponding characteristic parameters may include: the speed of the vehicle and the acceleration of the vehicle.

[0073] If the dangerous driving scene is a scene of driving with a small distance between vehicles, the corresponding characteristic parameters may include: the speed of the vehicle and the distance between the vehicle and the vehicle in front. If the dangerous driving scene is a scene of driving on a curve, the corresponding characteristic parameters may include the speed of the vehicle.

[0074] If the driving scenario is a lane change scenario, refer to Figure 4 , the corresponding characteristic parameters include: a first distance D1 between vehicle H0 and the first vehicle H1 on the target lane, a second distance D2 between vehicle H0 and the second vehicle H2 on the target lane, and the speed of vehicle H0. The target lane is the destination lane to which vehicle H0 is to switch. The first vehicle H1 is the vehicle in front of vehicle H0 on the target lane and closest to vehicle H0. The second vehicle H2 is the vehicle behind vehicle H0 on the target lane and closest to vehicle H0.

[0075] In an embodiment of the present application, when the T-Box determines that the driving scene is a dangerous driving scene, it can obtain the driving characteristic data of the vehicle in the dangerous driving scene through at least one of the environmental perception sensors, vehicle speed sensors, and IMU installed in the vehicle.

[0076] Among them, the environmental perception sensor may include at least one of the forward-facing camera and radar mentioned above.

[0077] In an embodiment of the present application, during the driving of the vehicle, the T-Box can collect the surrounding environment information of the vehicle through the environmental perception sensor, and identify whether the driving scene of the vehicle is a dangerous driving scene based on the surrounding environment information.

[0078] For example, T-Box can determine whether the vehicle's driving scene is a dangerous driving scene by identifying targets in the surrounding environment information collected by radar (such as millimeter wave radar) and forward-facing cameras. The targets may include: behavior, vehicles, lane lines, and traffic lights.

[0079] Furthermore, the vehicle's T-Box can also communicate with neighboring vehicles. During the vehicle's driving process, the T-Box can also obtain data collected by sensors (such as positioning sensors) in neighboring vehicles, and combine the data collected by the sensors to determine whether the vehicle's driving scene is a dangerous behavior scene. In this way, the recognition accuracy of the vehicle's driving scene can be ensured to be high.

[0080] It is understandable that for lane change scenarios, the T-Box can also combine the working status of the vehicle's turn signal and the steering wheel angle to determine whether the vehicle's driving scenario is a lane change scenario.

[0081] Step 202: Based on the driving characteristic data, identify whether the driving behavior in the driving scenario is a dangerous driving behavior.

[0082] In an embodiment of the present application, a behavior recognition model may be pre-installed in the T-Box. The T-Box may input driving feature data into the behavior recognition model to obtain a recognition result of the driving behavior output by the behavior recognition model. The recognition result is a dangerous driving behavior or a safe driving behavior.

[0083] Alternatively, for a dangerous driving scenario such as passing a traffic light, if the T-Box determines that the green light is flashing based on the color of the traffic light and the vehicle's acceleration increases, it can be determined that the driver's driving behavior is rushing to catch the green light, and then it can be determined that the driving behavior is a dangerous driving behavior.

[0084] For the dangerous driving scenario of crossing a zebra crossing, if the T-Box determines that the acceleration of the vehicle has increased, it can be determined that the driver's driving behavior is to cross the zebra crossing before pedestrians, and then it can be determined that the driving behavior is a dangerous driving behavior.

[0085] For dangerous driving scenarios such as passing through a blind spot, if the T-Box determines that the vehicle's speed is greater than a first speed threshold and the acceleration increases, it can be determined that the driver's safety awareness is insufficient during the process of passing through the blind spot, and then the driver's driving behavior can be determined to be dangerous driving behavior. The first speed threshold can be pre-stored by the T-Box.

[0086] For dangerous driving scenarios where the vehicle is traveling at a small distance from other vehicles, if the T-Box determines that the vehicle's speed is greater than the second speed threshold and the distance between the vehicle and the vehicle in front is less than the safe distance, it can be determined that the vehicle did not maintain a safe distance from the vehicle in front during high-speed driving, and then the driver's driving behavior can be determined to be dangerous driving behavior. The second speed threshold can be greater than or equal to 60 kilometers per hour (km / h) and less than or equal to 120km / h.

[0087] For a dangerous driving scenario, if the T-Box determines that the speed of the vehicle is greater than the third speed threshold, it can be determined that the vehicle is driving too fast on the curve, and then it can be determined that the driver's driving behavior is dangerous driving behavior. The third speed threshold can be pre-stored by the T-Box.

[0088] For the dangerous driving scenario, which is a lane change scenario, if the T-Box determines that the first distance D1 between the vehicle and the vehicle in front is less than the first distance threshold, the second distance D2 between the vehicle and the vehicle behind is also less than the distance threshold, and the speed of the vehicle is greater than the fourth speed threshold, then it can be determined that the vehicle still performs a lane change operation when the lane change gap is insufficient, and then the driver's driving behavior can be determined to be a dangerous driving behavior.

[0089] If the T-Box determines that the first distance D1 between the vehicle and the vehicle in front is greater than or equal to the first distance threshold, the second distance D2 between the vehicle and the vehicle behind is less than the distance threshold, and the acceleration of the vehicle decreases, it can be determined that the vehicle performs a deceleration waiting operation when the gap with the vehicle behind is small, and then the driver's driving behavior can be determined to be a safe driving behavior.

[0090] If the T-Box determines that the first distance D1 between the vehicle and the vehicle in front is less than the first distance threshold, the second distance D2 between the vehicle and the vehicle behind is greater than or equal to the distance threshold, and the speed of the vehicle is 0, that is, it remains stationary, then it can be determined that the vehicle performs a lane keeping operation when the gap with the vehicle in front is small, and then the driver's driving behavior can be determined to be a safe driving behavior.

[0091] Step 203: If the driving behavior in the driving scenario is identified as a dangerous driving behavior, the count value corresponding to the driving scenario is increased.

[0092] Among them, the count value is positively correlated with the number of occurrences of dangerous driving behavior in the driving scene. It can be seen that the count value can represent the probability of occurrence of dangerous driving behavior in the driving scene, and the larger the count value, the higher the probability of occurrence. The smaller the count value, the lower the probability of occurrence.

[0093] For example, the count value may be the number of occurrences of the dangerous driving behavior in the driving scenario. Alternatively, the count value may be determined based on the number of occurrences, and the count value is positively correlated with the number of occurrences.

[0094] In an embodiment of the present application, if the count value is the number of occurrences of dangerous driving behavior in the driving scenario, the T-Box of the vehicle may increase the count value by 1. If the count value is determined based on the number of occurrences, the T-Box may increase the count value by a first value. That is, in a dangerous driving scenario, if the T-Box determines that the dangerous driving behavior occurs once, the first value may be increased by the count value. The first value may be an integer greater than 1 pre-stored by the vehicle. For example, the first value may be 3.

[0095] It is understandable that a counter corresponding to a dangerous driving scenario is pre-set in the T-Box, and the count value of the counter is the count value corresponding to the dangerous driving scenario. After the T-Box determines that the driving behavior in the dangerous driving scenario is a dangerous driving behavior, it can control the counter to increase its count value.

[0096] Step 204: If it is identified that the driving behavior in the driving scenario is a safe driving behavior, then the count value corresponding to the driving scenario is reduced.

[0097] Among them, the count value is also negatively correlated with the number of times safe driving behavior occurs in the driving scenario.

[0098] In an embodiment of the present application, if the count value is the number of times the dangerous driving behavior occurs in the driving scenario, the T-Box of the vehicle may subtract 1 from the count value. If the count value is determined based on the number of occurrences, the T-Box may subtract a second value from the count value. That is, if the T-Box determines that the safe driving behavior occurs once in the driving scenario, the second value may be subtracted from the count value. The second value may be pre-stored by the vehicle.

[0099] Optionally, the second value may be less than or equal to the first value, such as the second value may be less than the first value. For example, the second value may be 1. It can be seen that the T-Box can add a larger value to the count value when determining that the driving behavior is a dangerous driving behavior, and subtract a smaller value from the count value when the driving behavior is a safe driving behavior, that is, the T-Box introduces a penalty mechanism in the process of updating the count value based on the recognition result of the driving behavior. In this way, it can better encourage drivers with bad driving behavior to improve their driving habits to optimize their own driving behavior.

[0100] It is understandable that after the vehicle determines that the driving behavior in a dangerous driving scenario is a safe driving behavior, the vehicle can control the corresponding counter to reduce its count value to reduce the count value corresponding to the dangerous driving scenario.

[0101] Step 205: Determine the degree of danger of the driver's comprehensive driving behavior according to the count values ​​corresponding to the multiple dangerous driving scenarios.

[0102] In the embodiment of the present application, there are multiple dangerous driving scenarios for the vehicle. After obtaining the recognition result of the driver's driving behavior in any dangerous driving scenario, the vehicle's T-Box can determine the degree of danger of the driver's comprehensive driving behavior based on the count values ​​corresponding to the multiple dangerous driving scenarios.

[0103] Since the T-Box can comprehensively consider the count values ​​corresponding to a variety of dangerous driving scenarios when determining the degree of danger, it can ensure that the determined degree of danger can more accurately reflect the overall driving pros and cons of the driver.

[0104] The degree of danger is positively correlated with the count value corresponding to each dangerous driving scenario. Optionally, the degree of danger can be represented by a danger level, or the degree of danger can be represented by a numerical value.

[0105] The embodiment of the present application takes the use of numerical representation of the degree of danger as an example to exemplify the process of determining the degree of danger of the driver's comprehensive driving behavior by the vehicle:

[0106] In an optional implementation, the vehicle may directly determine the average value of the sum of the count values ​​corresponding to a plurality of dangerous driving scenarios as a numerical value representing the degree of danger of the driver's comprehensive driving behavior.

[0107] In another optional implementation, the vehicle may perform a weighted summation on the count values ​​corresponding to the multiple dangerous driving scenarios to obtain a numerical value that can characterize the degree of danger of the driver's comprehensive driving behavior.

[0108] The weighting coefficients corresponding to the multiple count values ​​may be pre-stored in the vehicle, and the sum of the multiple weighting coefficients may be 1.

[0109] Since the driving behaviors in different dangerous driving scenarios reflect the driver's driving habits to different degrees, weighted summation of the count values ​​corresponding to multiple dangerous driving scenarios can further ensure that the determined degree of danger can more accurately reflect the driver's overall driving pros and cons.

[0110] In the embodiment of the present application, the vehicle further includes a display screen (such as a central control display screen). After determining the degree of danger of the driver's comprehensive driving behavior, the vehicle's T-box can display the degree of danger on the display screen. In this way, the driver can be effectively reminded, so that the driver can autonomously improve his driving habits to optimize his driving behavior.

[0111] It is understandable that, taking the danger level as an example, if the T-box determines that the value is greater than a numerical threshold, the value may be displayed on the display screen, wherein the numerical threshold may be pre-stored by the T-box.

[0112] It is understandable that the order of the steps of the driving behavior identification method provided in the embodiment of the present application can be appropriately adjusted, and the steps can also be increased or decreased accordingly according to the situation. For example, steps 203 to 205 can be deleted according to the situation. Any technician familiar with the technical field can easily think of a method of change within the technical scope disclosed in this application, which should be included in the protection scope of this application, so it will not be repeated.

[0113] In summary, the embodiment of the present application provides a method for identifying driving behavior, and the vehicle's behavior recognition device can obtain the vehicle's driving characteristic data when the vehicle's driving scenario is a dangerous driving scenario, and the driving characteristic data can reflect the driver's driving behavior in the driving scenario. Afterwards, the behavior recognition device can identify the driver's driving behavior based on the driving characteristic data to obtain an identification result (i.e., dangerous driving behavior or safe driving behavior). Moreover, since the driving behavior in a dangerous driving scenario can more accurately reflect the driver's driving habits, pricing based on the identification result of the driving behavior in a dangerous driving scenario can ensure that the UBI premium pricing is more reasonable.

[0114] The present application embodiment provides a vehicle, see Figure 1 The vehicle includes a behavior recognition device 01. The behavior recognition device 01 can be used to execute the driving behavior recognition method provided by the above method embodiment. The behavior recognition device 01 is used to:

[0115] During the driving process of the vehicle, if it is determined that the driving scene of the vehicle is a dangerous driving scene, the driving characteristic data of the vehicle is obtained, wherein the driving characteristic data is used to reflect the driving behavior of the driver in the driving scene;

[0116] Based on driving characteristic data, identify whether the driving behavior in the driving scenario is dangerous driving behavior.

[0117] Optionally, the behavior recognition device 01 can be used for:

[0118] According to the correspondence between the scene and the characteristic parameters, the target characteristic parameters corresponding to the driving scene are obtained;

[0119] The parameter value of the target characteristic parameter is used as the driving characteristic data of the vehicle.

[0120] Optionally, the behavior recognition device 01 may also be used for:

[0121] If the driving behavior in the driving scene is identified as a dangerous driving behavior, the count value corresponding to the driving scene is increased;

[0122] Among them, the count value is positively correlated with the number of times dangerous driving behaviors occur in the driving scenario.

[0123] Optionally, there are multiple dangerous driving scenarios; the behavior recognition device 01 can also be used for:

[0124] The dangerousness level of the driver's comprehensive driving behavior is determined based on the count values ​​corresponding to the various dangerous driving scenarios.

[0125] Optionally, the degree of danger is represented by a numerical value; the behavior recognition device 01 can be used for:

[0126] The count values ​​corresponding to various dangerous driving scenarios are weightedly summed to obtain a numerical value.

[0127] Optionally, the behavior recognition device 01 may also be used for:

[0128] If the driving behavior in the driving scenario is identified as a safe driving behavior, the count value corresponding to the driving scenario is reduced.

[0129] Optionally, the behavior recognition device 01 may also be used for:

[0130] The degree of danger is shown in the display.

[0131] In summary, the embodiment of the present application provides a vehicle, and the vehicle's behavior recognition device can obtain the vehicle's driving characteristic data when the vehicle's driving scenario is a dangerous driving scenario, and the driving characteristic data can reflect the driver's driving behavior in the driving scenario. Afterwards, the behavior recognition device can identify the driver's driving behavior based on the driving characteristic data to obtain an identification result (i.e., dangerous driving behavior or safe driving behavior). In addition, since the driving behavior in a dangerous driving scenario can more accurately reflect the driver's driving habits, pricing based on the identification result of the driving behavior in a dangerous driving scenario can ensure that the UBI premium pricing is more reasonable.

[0132] The present application embodiment provides a vehicle behavior recognition device, see Figure 5The behavior recognition device 01 includes: a processor 110 and a memory 120. The processor 110 and the memory 120 are connected, such as through a bus 130.

[0133] The processor 110 may be a CPU (central processing unit), a general-purpose processor, a DSP (digital signal processor), an ASIC (application specific integrated circuit), an FPGA (field programmable gate array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It may implement or execute various exemplary logic blocks, modules and circuits described in conjunction with the disclosure of this application. The processor 110 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0134] The bus 130 may include a path to transmit information between the above components. The bus 130 may be a PCI (peripheral component interconnect) bus or an EISA (extended industry standard architecture) bus. The bus 130 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0135] The memory 120 is used to store a computer program corresponding to the driving behavior recognition method of the above embodiment of the present application, and the computer program is controlled and executed by the processor 110. The processor 110 is used to execute the computer program stored in the memory 120 to implement the content shown in the above method embodiment.

[0136] The present application embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the driving behavior recognition method provided by the above method embodiment is implemented. For example, Figure 2 or Figure 3 The method shown.

[0137] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0138] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0139] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for identifying driving behavior, characterized in that: The method comprises: During the driving process of the vehicle, if it is determined that the driving scene of the vehicle is a dangerous driving scene, obtaining driving characteristic data of the vehicle, wherein the driving characteristic data is used to reflect the driving behavior of the driver in the driving scene; Based on the driving characteristic data, it is identified whether the driving behavior in the driving scenario is a dangerous driving behavior.

2. The method according to claim 1, characterized in that The obtaining of the driving characteristic data of the vehicle includes: According to the correspondence between the scene and the characteristic parameters, obtaining the target characteristic parameters corresponding to the driving scene; The parameter value of the target characteristic parameter is used as the driving characteristic data of the vehicle.

3. The method according to claim 1 or 2, characterized in that: The method further comprises: If the driving behavior in the driving scenario is identified as a dangerous driving behavior, increasing the count value corresponding to the driving scenario; The count value is positively correlated with the number of times dangerous driving behavior occurs in the driving scenario.

4. The method according to claim 3, characterized in that There are multiple dangerous driving scenarios; the method also includes: The dangerousness level of the driver's comprehensive driving behavior is determined according to the count values ​​corresponding to the multiple dangerous driving scenarios.

5. The method according to claim 4, characterized in that The degree of danger is represented by a numerical value; the degree of danger of the driver's comprehensive driving behavior is determined according to the count values ​​corresponding to the multiple dangerous driving scenarios, including: The count values ​​corresponding to the multiple dangerous driving scenarios are weightedly summed to obtain the numerical value.

6. The method according to any one of claims 3 to 5, characterized in that: The method further comprises: If it is identified that the driving behavior in the driving scenario is a safe driving behavior, the count value corresponding to the driving scenario is reduced.

7. The method according to claim 4, characterized in that: The method further comprises: The degree of danger is shown in the display.

8. A vehicle, characterized in that: The vehicle comprises: a behavior recognition device; the behavior recognition device is used to: During the driving process of the vehicle, if it is determined that the driving scene of the vehicle is a dangerous driving scene, obtaining driving characteristic data of the vehicle, wherein the driving characteristic data is used to reflect the driving behavior of the driver in the driving scene; Based on the driving characteristic data, it is identified whether the driving behavior in the driving scenario is a dangerous driving behavior.

9. The vehicle according to claim 8, characterized in that The behavior recognition device is used for: According to the correspondence between the scene and the characteristic parameters, obtaining the target characteristic parameters corresponding to the driving scene; The parameter value of the target characteristic parameter is used as the driving characteristic data of the vehicle.

10. A behavior recognition device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images