A driving behavior prediction method and device, electronic equipment and storage medium

Abstract

The application provides a driving behavior prediction method and device, electronic equipment and a storage medium, relates to the technical field of intelligent driving, and obtains driving state information of other vehicles around a target vehicle and a speed limit value of a current road section; the driving state information comprises speed information of the other vehicles and relative distances between the other vehicles and the target vehicle; a driving category of the other vehicles is determined according to the speed information of the other vehicles and the speed limit value; a current driving speed of the target vehicle, the relative distances between the other vehicles and the target vehicle and the driving category of the other vehicles are input into a driving behavior prediction database for matching, and a prediction result of a predicted driving behavior of the target vehicle and a corresponding safety risk level is obtained. Thus, the driving behavior is comprehensively judged through the current driving speed of the target vehicle, the relative distances between the other vehicles and the target vehicle and the driving category of the other vehicles, and more accurate driving assistance is provided for the driver.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent driving, in particular to a driving behavior prediction method and device, an electronic device and a storage medium. BACKGROUND

[0002] In the field of transportation engineering, vehicle engineering and artificial intelligence, intelligent driving of vehicles has become a hot research and development topic. With the progress of science and technology, cars not only need to have basic driving functions, but also need to have intelligent driving assistance functions to improve driving safety and comfort.

[0003] The existing driving assistance technology collects information such as the position of the vehicle in the lane and the distance between the front and rear vehicles during driving and performs warning work, but lacks the collection and early warning of the driving trajectories of other vehicles. And when giving driving safety warnings, it lacks research on the choices and safety risks of similar scenarios in the driver's historical driving behavior. This leads to inaccurate driving behavior prediction and affects driving safety. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a driving behavior prediction method, device, electronic device and storage medium, which can provide more accurate driving assistance for drivers.

[0005] In a first aspect, the embodiments of the present application provide a driving behavior prediction method, which comprises the following steps:

[0006] Obtain the driving state information of other vehicles around the target vehicle and the speed limit value of the current section; wherein the driving state information includes the speed information of other vehicles and the relative distance between other vehicles and the target vehicle;

[0007] Determine the driving category of other vehicles according to the speed information of other vehicles and the speed limit value; the driving category includes at least one of the following: speeding vehicle, turtle speed vehicle, and aggressive driving vehicle;

[0008] Input the current driving speed of the target vehicle, the relative distance between other vehicles and the target vehicle, and the driving category of other vehicles into a driving behavior prediction database for matching to obtain a prediction result of the predicted driving behavior of the target vehicle and the corresponding safety risk level of the predicted driving behavior; the predicted driving behavior includes at least one of the following: acceleration, deceleration, lane change, and maintaining vehicle distance.

[0009] In some embodiments, the method further comprises the following steps:

[0010] According to the obtained safety risk level, a safety risk prompt is given.

[0011] In some embodiments, the method further comprises the following steps:

[0012] acquiring an actual driving behavior of the target vehicle taken according to the safety risk prompt;

[0013] updating the driving behavior prediction database based on the actual driving behavior.

[0014] In some embodiments, the speed information of the other vehicle includes speed, acceleration and steering angle, and the determination of the driving category of the other vehicle according to the speed information of the other vehicle and the speed limit value comprises the following steps:

[0015] if the speed of the other vehicle is detected to be greater than the speed limit value, the other vehicle is determined to be a speeding vehicle;

[0016] if the ratio of the speed of the other vehicle to the speed limit value is detected to be less than a first threshold value, the other vehicle is determined to be a turtle vehicle;

[0017] if the acceleration of the other vehicle is detected to be greater than a second threshold value or the steering angle of the other vehicle is detected to be greater than a third threshold value, the other vehicle is determined to be an aggressive driving vehicle.

[0018] In some embodiments, the inputting of the current driving speed of the target vehicle, the relative distance between the other vehicle and the target vehicle and the driving category of the other vehicle into the driving behavior prediction database for matching to obtain the prediction result of the predicted driving behavior of the target vehicle and the corresponding safety risk level of the predicted driving behavior comprises the following steps:

[0019] constructing a first two-dimensional array with the current driving speed of the target vehicle, the relative distance between the other vehicle and the target vehicle and the driving category of the other vehicle;

[0020] inputting the first two-dimensional array into the driving behavior prediction database and matching it with a second two-dimensional array stored in the driving behavior prediction database, and when the first row elements of the first two-dimensional array and the second two-dimensional array stored in the driving behavior prediction database are successfully matched, outputting the second row elements of the corresponding second two-dimensional array; the second two-dimensional array comprises first row elements and second row elements, the first row elements are composed of the speed of the target vehicle, the relative distance between the other vehicle and the target vehicle and the category of the other vehicle collected historically, and the second row elements are composed of the predicted driving behavior and the safety risk level corresponding to the first row elements.

[0021] In some embodiments, the inputting of the first two-dimensional array into the driving behavior prediction database and the matching with the second two-dimensional array stored in the driving behavior prediction database comprises the following steps:

[0022] comparing each row element in the first two-dimensional array with a first row element of a second two-dimensional array stored in the driving behavior prediction database, and determining that the row element is matched successfully if the speed of the target vehicle, the relative distance between the other vehicle and the target vehicle, and the category of the other vehicle are all consistent or within a set error range;

[0023] outputting a second row element of the second two-dimensional array if each row element in the first two-dimensional array is matched successfully.

[0024] In some embodiments, the safety risk prompt includes voice and text.

[0025] In a second aspect, the embodiments of the present application provide a driving behavior prediction device, and the device comprises:

[0026] an acquisition module configured to acquire driving state information of other vehicles around a target vehicle and a speed limit value of a current road section, wherein the driving state information comprises speed information of the other vehicles and relative distances between the other vehicles and the target vehicle;

[0027] a classification module configured to determine a driving category of the other vehicles according to the speed information of the other vehicles and the speed limit value, wherein the driving category comprises at least one of a speeding vehicle, a turtle vehicle, and an aggressive driving vehicle;

[0028] a prediction module configured to input a current driving speed of the target vehicle, the relative distances between the other vehicles and the target vehicle, and the driving category of the other vehicles into a driving behavior prediction database for matching to obtain a prediction result of a predicted driving behavior of the target vehicle and a safety risk level corresponding to the predicted driving behavior, wherein the predicted driving behavior comprises at least one of acceleration, deceleration, lane changing, and maintaining a distance.

[0029] In a third aspect, the embodiments of the present application provide an electronic device, which comprises a processor, a memory, and a bus, wherein the memory stores machine readable instructions executable by the processor, the processor and the memory communicate through the bus when the electronic device is running, and the machine readable instructions are executed by the processor to perform the steps of the driving behavior prediction method according to any one of the first aspect.

[0030] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to perform the steps of the driving behavior prediction method according to any one of the first aspect.

[0031] The driving behavior prediction method, device, electronic equipment and storage medium provided in the application obtain driving state information of other vehicles around a target vehicle and a speed limit value in driving of the target vehicle, wherein the driving state information comprises speed information of the other vehicles and relative distances between the other vehicles and the target vehicle; a driving category of the other vehicles is determined according to the speed information of the other vehicles and the speed limit value; the current driving speed of the target vehicle, the relative distances between the other vehicles and the target vehicle and the driving category of the other vehicles are input into a driving behavior prediction database for matching to obtain a prediction result of a predicted driving behavior of the target vehicle and a safety risk level corresponding to the predicted driving behavior. Thus, the driving behavior is comprehensively judged through the current driving speed of the target vehicle, the relative distances between the other vehicles and the target vehicle and the driving category of the other vehicles, and more accurate driving assistance is provided for the driver. BRIEF DESCRIPTION OF DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be considered as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0033] Figure 1 A flowchart of the driving behavior prediction method according to the embodiments of the application is shown;

[0034] Figure 2 A flowchart of inputting the current vehicle speed, the relative positions of the other vehicles and the other vehicles into the driving behavior prediction database for matching and outputting the corresponding predicted driving behavior and safety risk level according to the matching result is shown;

[0035] Figure 3 A structural schematic diagram of the driving behavior prediction device according to the embodiments of the application is shown;

[0036] Figure 4 A structural block diagram of the electronic equipment according to the embodiments of the application is shown. DETAILED DESCRIPTION

[0037] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of description and illustration, and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn according to the actual proportions. The flowcharts used in the present application show the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts can not be implemented in sequence, and the steps without logical context relationship can be reversed in sequence or implemented simultaneously. In addition, one or more other operations can be added to the flowcharts or one or more operations can be removed from the flowcharts under the guidance of the content of the present application.

[0038] In addition, the described embodiments are only some of the embodiments of the present application, not all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0039] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the presence of the features declared thereafter, but does not exclude the addition of other features.

[0040] In view of the technical problems proposed in the background art, the present application provides a driving behavior prediction method and device, electronic equipment and storage medium, which not only considers the current vehicle speed, the relative position of other vehicles and the category of other vehicles, but also combines the historical driving behavior choices of the vehicle owner to improve the accuracy of driving safety judgment.

[0041] Referring to the drawings accompanying the Figure 1 The driving behavior prediction method provided in the embodiments of the present application comprises the following steps:

[0042] S1, obtaining the driving state information of other vehicles around a target vehicle and the speed limit value of a current road section; wherein the driving state information comprises speed information of other vehicles and relative distance between other vehicles and the target vehicle;

[0043] S2, determining the driving category of other vehicles according to the speed information of other vehicles and the speed limit value; the driving category comprises at least one of a speeding vehicle, a turtle vehicle and an aggressive driving vehicle;

[0044] S3, inputting the current driving speed of the target vehicle, the relative distance between the other vehicles and the target vehicle and the driving category of the other vehicles into a driving behavior prediction database to obtain a prediction result of the predicted driving behavior of the target vehicle and the safety risk level corresponding to the predicted driving behavior; the driving behavior includes at least one of acceleration, deceleration, lane changing and maintaining a distance.

[0045] Specifically, in step S1, the driving state information of the surrounding other vehicles and the speed limit value of the current road section are obtained in real time based on the sensors configured on the target vehicle, including recognizing the digital information on the speed limit sign on the road during driving of the target vehicle based on the camera using image recognition technology to obtain the speed limit value, and measuring the speed information of the other vehicles and the relative distance between the other vehicles and the target vehicle based on the radar using Doppler effect, where the speed information includes speed, acceleration and steering angle. The selection of the camera and the radar has flexibility and can be adjusted according to actual needs to ensure that the obtained vehicle state information is accurate and reliable.

[0046] In the present application, the other vehicles around the target vehicle refer to the vehicle closest to the target vehicle at the front, rear and left and right positions of the target vehicle. In an embodiment, the target vehicle is equipped with multiple types of cameras (A, B, C, D) and radars (E, F, G, H), which are carefully distributed in front of, behind and on the left and right of the target vehicle to ensure that there is no dead angle to cover the surrounding environment. Camera A can be a high-definition wide-angle camera installed above the front grille of the target vehicle, which is used to capture image information of a wide area in front of the target vehicle and can clearly identify the outline of a distant vehicle, lane lines and traffic signs, etc. Cameras B and C are respectively located below the left and right rearview mirrors of the target vehicle, which have a certain oblique viewing angle and are mainly responsible for monitoring the dynamic of vehicles and pedestrians on both sides of the target vehicle and providing key side information when changing lanes or turning. Camera D is installed above the rear bumper of the target vehicle and can clearly capture the overall appearance of the rear vehicle and the road conditions behind. Radars E and F are located inside the front bumper of the target vehicle, which use millimeter wave radar technology and can quickly and accurately calculate the distance, speed and relative motion direction of the front vehicle through Doppler effect. Radars G and H are symmetrically distributed on both sides of the rear bumper of the target vehicle and are used to monitor the approaching speed and distance of the rear vehicle. In addition, the camera processes the collected images through image recognition technology and uses advanced deep learning algorithms to accurately identify the digital information on the speed limit sign and convert it into speed limit data for use by the system.

[0047] In step S2, the application formulates a set of clear and reasonable classification rules according to the driving behavior characteristics of other vehicles, and divides other vehicles into different types such as speeding vehicles, turtle speed vehicles, aggressive driving vehicles, etc. Among them, the judgment basis of speeding vehicles is very clear, that is, the vehicle speed is greater than the speed limit value of the current road section. This rule directly refers to the speed limit of the vehicle driving speed in the traffic regulations, and can quickly and accurately identify the vehicle that violates the speed limit by comparing with the speed limit information of the current road section.

[0048] The judgment of turtle speed vehicle considers the proportional relationship between vehicle speed and current road speed limit value. In an embodiment, when the vehicle speed is less than 0.6*current road speed limit value, it is judged as a turtle speed vehicle. This determination method not only pays attention to whether the vehicle is below the speed limit, but also considers the influence degree of its too low speed on the smoothness of traffic flow. For example, on the highway, if a vehicle is driving at a speed significantly lower than the normal driving speed, it may cause the rear vehicles to frequently change lanes to overtake, increasing the risk of traffic congestion and accidents.

[0049] The judgment of aggressive driving vehicle is relatively complex, which comprehensively considers the acceleration and steering angle. When the vehicle acceleration is greater than or equal to (current road speed limit value-current vehicle speed value)*1000 / 3600 / t (t is consistent with the calculation time of vehicle acceleration) m / s 2 or the vehicle steering angle is greater than or equal to 12° (which can be adjusted according to actual needs), it can be judged as an aggressive driving vehicle. The calculation of acceleration can reflect the acceleration or deceleration of the vehicle, and rapid acceleration or deceleration may indicate that the driver's driving behavior is more aggressive. The monitoring of the steering angle can capture the behavior of sudden steering or large steering of the vehicle, which may indicate potential dangerous driving behavior such as forced lane change or sharp turn in some cases.

[0050] In the driving process of the target vehicle, the speed, acceleration and steering angle of the surrounding other vehicles are obtained in real time, and each other vehicle is classified and judged according to the above classification rules. Once the vehicle meets a certain classification condition, it will be immediately labeled with the corresponding type label. For example, when a vehicle in front is detected to exceed the speed limit of the current highway section of 120 kilometers per hour, it will be quickly labeled as a "speeding vehicle" and displayed on the target vehicle display interface with a specific icon or color, so that the driver can intuitively identify the type of other vehicles; for turtle speed vehicles and aggressive driving vehicles, real-time labeling is also performed, so that the driver can timely understand the driving state of other vehicles and make preparations in advance. At the same time, these classification data are also recorded for subsequent driving behavior analysis and prediction, providing more data support for the system to continuously optimize the classification algorithm and improve the accuracy of judgment.

[0051] Referring to the drawingsFigure 2 In step S3, the current driving speed of the target vehicle, the relative distance between the other vehicle and the target vehicle, and the driving category of the other vehicle are input into the driving behavior prediction database for matching, to obtain the prediction result of the predicted driving behavior of the target vehicle and the corresponding safety risk level, including the following steps:

[0052] S301, the current driving speed of the target vehicle, the relative distance between the other vehicle and the target vehicle, and the driving category of the other vehicle are input into the driving behavior prediction database for matching, to obtain the prediction result of the predicted driving behavior of the target vehicle and the corresponding safety risk level, including the following steps:

[0053] S302, the first two-dimensional array is input into the driving behavior prediction database and matched with the second two-dimensional array stored in the driving behavior prediction database, and when the first row elements of the first two-dimensional array and the second two-dimensional array stored in the driving behavior prediction database are successfully matched, the second row elements of the corresponding second two-dimensional array are output; the second two-dimensional array includes first row elements and second row elements, the first row elements are composed of the speed of the target vehicle, the relative distance between the other vehicle and the target vehicle, and the category of the other vehicle, and the second row elements are composed of the predicted driving behavior and the safety risk level corresponding to the first row elements.

[0054] Specifically, in step S301, after obtaining the current driving speed of the target vehicle, the relative position of the other vehicle, and the driving category of the other vehicle, they are arranged into a two-dimensional array form ({ {current vehicle speed, front vehicle relative position, front vehicle type}, {current vehicle speed, rear vehicle relative position, rear vehicle type}, {current vehicle speed, left vehicle relative position, left vehicle type}, {current vehicle speed, right vehicle relative position, right vehicle type}}), which is called the first two-dimensional array.

[0055] For example, assuming that the current vehicle speed is 80 km / h, the front vehicle relative position is 15 meters (distance from the front of the vehicle), and the front vehicle type is "turtle speed vehicle"; the rear vehicle relative position is 30 meters (distance from the rear of the vehicle), and the rear vehicle type is "speeding vehicle"; the left vehicle relative position is 2 meters (lateral distance from the left side of the vehicle), and the left vehicle type is "aggressive driving vehicle"; the right vehicle relative position is 5 meters (lateral distance from the right side of the vehicle), and the right vehicle type is "speeding vehicle". The input first two-dimensional array is {{80, 15, turtle speed vehicle}, {80, 30, speeding vehicle}, {80, 2, aggressive driving vehicle}, {80, 5, speeding vehicle}}.

[0056] In step S302, it should be noted that the driving behavior prediction database is built through a large amount of actual driving data collection, arrangement and analysis. It stores a large amount of driving behavior data in different scenarios, including various speed combinations, vehicle relative position relationship and vehicle type matching corresponding driver behavior and safety risk level (low, medium and high). In order to ensure the effectiveness and real-time performance of the driving behavior prediction database, the data will be updated regularly, and new driving data will be continuously incorporated into the driving behavior prediction database, while obsolete or inaccurate data will be cleaned up or corrected.

[0057] Among them, the format of the predicted driving behavior data stored in the driving behavior prediction database is {{current vehicle speed, front / rear / left / right vehicle relative position, front / rear / left / right vehicle type}, {driver behavior, risk level}}, which is called the second two-dimensional array here. Among them, the speed, the relative position of other vehicles and the type of other vehicles constitute the first element of the driving behavior data, and the predicted driving behavior and safety risk level corresponding to the first element constitute the second element of the driving behavior data. Then, the first two-dimensional array obtained in step S301 is compared with the first element of the driving behavior data stored in the driving behavior prediction database. Specifically, each row element in the first two-dimensional array is compared with the first row element of the second two-dimensional array stored in the driving behavior prediction database. If the speed of the target vehicle, the relative distance between the other vehicles and the target vehicle and the type of the other vehicles are consistent or within a certain error range, it is determined that the row element is matched successfully. If each row element in the first two-dimensional array is matched successfully, the second row element of the corresponding second two-dimensional array is output.

[0058] It should be noted that in the comparison process, for the judgment of the current vehicle speed and the relative position of the vehicle, an adjustable deviation range (≤±2) is set. As long as it is within this deviation range, it is considered consistent. For example, the current vehicle speed is 60 kilometers per hour, and the speed data stored in the driving behavior prediction database is 59 kilometers per hour, which is within the deviation range, so the two speeds are considered consistent. Similarly, for the relative position of the vehicle, such as the relative position of the front vehicle being 10 meters, the data in the driving behavior prediction database being 9 meters, which is also within the deviation range, is considered consistent. This flexible deviation setting can adapt to the changes of different sensor accuracy and actual driving conditions, and improve the accuracy and reliability of the matching. Once the data comparison and matching are completed, the corresponding predicted driving behavior and safety risk level information will be obtained from the driving behavior prediction database according to the matching result. For example, the distance between the current vehicle and the front vehicle is less than 20 meters, and the speed of the current vehicle is 120 kilometers per hour. According to the driving behavior prediction database, the prediction result that the current driver will overtake and the safety risk level is high is obtained.

[0059] The safety risk level is mainly obtained by comprehensively analyzing the predicted driving behavior in combination with the current driving speed of the target vehicle, the relative position of other vehicles, and the driving category of other vehicles. For example, when the target vehicle is driving at a high speed, the consequences after a collision are usually more serious, and the overtaking risk level is correspondingly higher; when the distance between the target vehicle and other vehicles is too close, whether in front or behind or in left and right directions, the possibility of a collision is increased, and the overtaking risk level is correspondingly higher; when there are aggressive driving vehicles around the target vehicle, there is a potential risk of causing an accident, and the overtaking risk level is correspondingly higher.

[0060] Further, according to the obtained safety risk level prediction result, the target vehicle is prompted in multiple ways to ensure that the driver can timely and accurately receive key information. Among them, voice prompt is one of the most direct and effective ways, and corresponding voice alarm is issued according to different risk levels. For example, when the risk level is “high”, the voice prompt may be “overtaking danger”, and the voice tone is urgent and the volume is large to attract the attention of the driver. The text prompt will be displayed on the instrument panel display screen or central control display screen of the vehicle, with simple and clear text describing the risk situation, such as “high risk of lane change”. At the same time, the display screen may also emphasize the risk with flashing icons or eye-catching color marks, such as a red flashing triangular icon representing a high risk situation.

[0061] In other embodiments, when the risk level is high, the seat or steering wheel will remind the driver with a specific vibration mode. This tactile prompt can play a supplementary reminder role when the driver's visual attention is distracted.

[0062] In addition, after the driver receives the prompt, his actual driving behavior will be collected and recorded in detail. These behavior data include whether the driver has taken corresponding operations such as speed reduction, acceleration, lane change according to the prompt, as well as details such as the time, amplitude and method of operation. In order to fully understand the driver's driving behavior in a specific scenario and its impact on the surrounding traffic environment. These rich data will provide comprehensive materials for subsequent learning and analysis, and will be updated to the driving behavior prediction database to provide more accurate predictions in similar future scenarios.

[0063] The driving behavior prediction method provided by the present application comprehensively considers multi-dimensional information to achieve more accurate vehicle classification. Unlike the prior art which only focuses on the position of the vehicle in the lane and the distance between the front and rear vehicles, the present application not only comprehensively considers real-time information such as the current vehicle speed, relative position and driving trend, but also introduces the choices of the driver's historical driving behavior in similar scenarios. Through these factors, more targeted and accurate safety warnings can be provided to the driver, helping the driver to prepare in advance, and significantly improving driving safety.

[0064] Based on the same inventive concept, the embodiment of the present application also provides a driving behavior prediction device. Since the principle of the device in the embodiment of the present application solves problems is similar to the above-mentioned driving behavior prediction method, device, electronic equipment and storage medium, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described here.

[0065] As shown in the description accompanying drawings Figure 3 The present application also provides a driving behavior prediction device, which comprises:

[0066] The acquisition module 301 is configured to acquire driving state information of other vehicles around a target vehicle and a speed limit value of a current road section; wherein the driving state information comprises speed information of the other vehicles and relative distances between the other vehicles and the target vehicle;

[0067] The classification module 302 is configured to determine driving categories of the other vehicles according to the speed information of the other vehicles and the speed limit value; the driving categories comprise at least one of speeding vehicles, turtle vehicles and aggressive driving vehicles;

[0068] The prediction module 303 is configured to input a current driving speed of the target vehicle, the relative distances between the other vehicles and the target vehicle and the driving categories of the other vehicles into a driving behavior prediction database for matching, to obtain a prediction result of a predicted driving behavior of the target vehicle and a safety risk level corresponding to the predicted driving behavior; the predicted driving behavior comprises at least one of acceleration, deceleration, lane changing and maintaining a vehicle distance.

[0069] In some embodiments, the device further comprises:

[0070] The prompting module is configured to perform a safety risk prompt according to the obtained safety risk level.

[0071] In some embodiments, the device further comprises:

[0072] The updating module is configured to acquire an actual driving behavior of the target vehicle taken according to the safety risk prompt; and update the driving behavior prediction database based on the actual driving behavior.

[0073] In some embodiments, the acquisition module 301 acquires the driving state information of the other vehicles and the speed limit information in the driving of the target vehicle in real time based on sensors configured by the target vehicle.

[0074] In some embodiments, the speed information of the other vehicle includes speed, acceleration and steering angle, and the classification module 302 determines the driving category of the other vehicle according to the speed information of the other vehicle and the speed limit value, including: if the speed of the other vehicle is detected to be greater than the speed limit value, the other vehicle is determined to be a speeding vehicle; if the ratio of the speed of the other vehicle to the speed limit value is detected to be less than a first threshold value, the other vehicle is determined to be a turtle vehicle; and if the acceleration of the other vehicle is detected to be greater than a second threshold value or the steering angle of the other vehicle is detected to be greater than a third threshold value, the other vehicle is determined to be an aggressive driving vehicle.

[0075] In some embodiments, the prediction module 303 inputs the current driving speed of the target vehicle, the relative distance between the other vehicle and the target vehicle, and the driving category of the other vehicle into a driving behavior prediction database for matching to obtain a prediction result of the driving behavior of the target vehicle and the corresponding safety risk level, including: forming a first two-dimensional array with the current driving speed of the target vehicle, the relative distance between the other vehicle and the target vehicle, and the driving category of the other vehicle; inputting the first two-dimensional array into the driving behavior prediction database and matching it with a second two-dimensional array stored in the driving behavior prediction database, and when the first row elements of the first two-dimensional array and the second two-dimensional array stored in the driving behavior prediction database match successfully, outputting the second row elements of the corresponding second two-dimensional array; the second two-dimensional array includes first row elements and second row elements, the first row elements are composed of the speed of the target vehicle, the relative distance between the other vehicle and the target vehicle, and the category of the other vehicle collected historically, and the second row elements are composed of the predicted driving behavior and the safety risk level corresponding to the first elements.

[0076] In some embodiments, the prediction module 303 inputs the first two-dimensional array into the driving behavior prediction database and matches it with the second two-dimensional array stored in the driving behavior prediction database, including: comparing each row element in the first two-dimensional array with the first row elements of the second two-dimensional array stored in the driving behavior prediction database respectively, if the speed of the target vehicle, the relative distance between the other vehicle and the target vehicle, and the category of the other vehicle are all consistent or within a set error range, it is determined that the row element matches successfully; and if each row element in the first two-dimensional array matches successfully, the second row elements of the corresponding second two-dimensional array are outputted.

[0077] The application provides a driving behavior prediction device, which obtains the driving state information of other vehicles around a target vehicle and a speed limit value in the driving of the target vehicle through an acquisition module; wherein the driving state information comprises speed information of the other vehicles and relative distances between the other vehicles and the target vehicle; the driving categories of the other vehicles are determined according to the speed information of the other vehicles and the speed limit value through a classification module; the current driving speed of the target vehicle, the relative distances between the other vehicles and the target vehicle and the driving categories of the other vehicles are input into a driving behavior prediction database for matching through a prediction module, so as to obtain a prediction result of a predicted driving behavior of the target vehicle and a safety risk level corresponding to the predicted driving behavior. Thus, the current driving speed of the target vehicle, the relative distances between the other vehicles and the target vehicle and the driving categories of the other vehicles are used to comprehensively judge the driving behavior, so as to provide the driver with higher-accuracy driving assistance.

[0078] Based on the same concept of the application, the specification attached Figure 4 As shown in the accompanying drawings, the electronic device 400 provided by the embodiments of the application comprises at least one processor 401, at least one network interface 404 or other user interface 403, a memory 405 and at least one communication bus 402. The communication bus 402 is used to realize the connection and communication between the components. The electronic device 400 can optionally comprise a user interface 403, including a display (for example, a touch screen, an LCD, a CRT, holographic imaging (Holographic) or a projector (Projector) and the like), a keyboard or a clicking device (for example, a mouse, a trackball, a touchpad or a touch screen and the like).

[0079] The memory 405 can comprise a read-only memory and a random access memory, and provide instructions and data for the processor 401. A part of the memory 405 can also comprise a non-volatile random access memory (NVRAM).

[0080] In some embodiments, the memory 405 stores the following elements, protected modules or data structures, or a subset of them, or an extended set of them:

[0081] An operating system 4051 comprises various system programs, used to realize various basic services and process hardware-based tasks;

[0082] An application program module 4052 comprises various application programs, for example, a desktop (launcher), a media player (MediaPlayer), a browser (Browser) and the like, used to realize various application services.

[0083] In the embodiments of the present application, the processor 401 is configured to execute the steps in the driving behavior prediction method, device, electronic device and storage medium by calling the program or instruction stored in the memory 405, so as to provide the driver with more accurate driving assistance.

[0084] The present application also provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by the processor to perform the steps in the driving behavior prediction method.

[0085] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc., and the computer program stored in the storage medium can be executed to perform the driving behavior prediction method.

[0086] In the embodiments provided in the present application, it should be understood that the disclosed device and method can be implemented in other manners. The described device embodiments are only schematic, and the division of units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0087] The units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purposes of the embodiments of the present application.

[0088] In addition, each functional unit in the embodiments of the present application can be integrated in one processing unit, or each unit can be a physical unit, or two or more units can be integrated in one unit.

[0089] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts of the prior art that make contributions or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0090] Finally, it should be noted that: the above embodiments are only specific embodiments of the present application, which are used to illustrate the technical solutions of the present application, but not to limit them. The protection scope of the present application is not limited thereto. Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily think of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed by the present application, or replace some technical features with equivalent ones. The modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A driving behavior prediction method characterized by, The method comprises the following steps: Obtaining the driving state information of other vehicles around the target vehicle and the speed limit value of the current section; wherein the driving state information comprises the speed information of other vehicles, the relative distance between other vehicles and the target vehicle; According to the speed information of other vehicles and the speed limit value, determine the driving category of other vehicles; the driving category comprises at least one of the following: speeding vehicle, turtle speed vehicle, aggressive driving vehicle; Input the current driving speed of the target vehicle, the relative distance between other vehicles and the target vehicle, and the driving category of other vehicles into the driving behavior prediction database for matching to obtain the prediction result of the predicted driving behavior of the target vehicle and the safety risk level corresponding to the predicted driving behavior; the predicted driving behavior comprises at least one of the following: acceleration, deceleration, lane change, and maintaining distance; Wherein, inputting the current driving speed of the target vehicle, the relative distance between other vehicles and the target vehicle, and the driving category of other vehicles into the driving behavior prediction database for matching to obtain the prediction result of the predicted driving behavior of the target vehicle and the safety risk level corresponding to the predicted driving behavior comprises the following steps: constructing a first two-dimensional array with the current driving speed of the target vehicle, the relative distance between other vehicles and the target vehicle, and the driving category of other vehicles; input the first two-dimensional array into the driving behavior prediction database and match it with the second two-dimensional array stored in the driving behavior prediction database, and when the first row elements of the first two-dimensional array and the second two-dimensional array stored in the driving behavior prediction database are matched successfully, output the second row elements corresponding to the second two-dimensional array; the second two-dimensional array comprises first row elements and second row elements, the first row elements are composed of the speed of the target vehicle, the relative distance between other vehicles and the target vehicle, and the category of other vehicles collected historically, and the second row elements are composed of the predicted driving behavior and safety risk level corresponding to the first row elements; Wherein, inputting the first two-dimensional array into the driving behavior prediction database and matching it with the second two-dimensional array stored in the driving behavior prediction database comprises the following steps: comparing each row element in the first two-dimensional array with the first row element of the second two-dimensional array stored in the driving behavior prediction database respectively, if the speed of the target vehicle, the relative distance between other vehicles and the target vehicle, and the category of other vehicles are consistent or within a certain error range, it is determined that the row element is matched successfully; if each row element in the first two-dimensional array is matched successfully, output the second row elements corresponding to the second two-dimensional array.

2. The driving behavior prediction method according to claim 1, characterized in that, The method further comprises the following steps: According to the obtained safety risk level, a safety risk prompt is given.

3. The driving behavior prediction method according to claim 2, characterized in that, The method further comprises: Obtaining the actual driving behavior of the target vehicle according to the safety risk prompt; Updating the driving behavior prediction database based on the actual driving behavior.

4. The driving behavior prediction method according to claim 3, characterized in that, The speed information of other vehicles comprises speed, acceleration and steering angle, and the determination of the driving category of other vehicles according to the speed information of other vehicles and the speed limit value comprises the following steps: If the speed of the other vehicle is detected to be greater than the speed limit value, the other vehicle is determined to be a speeding vehicle; If the ratio of the speed of the other vehicle to the speed limit value is detected to be less than a first threshold value, the other vehicle is determined to be a turtle vehicle; If the acceleration of the other vehicle is detected to be greater than a second threshold value or the steering angle of the other vehicle is detected to be greater than a third threshold value, the other vehicle is determined to be an aggressive driving vehicle.

5. The driving behavior prediction method according to claim 4, characterized in that, In the formula, The safety risk prompt includes voice and text.

6. A driving behavior prediction device characterized by comprising: The device comprises: An acquisition module configured to acquire driving state information of other vehicles around a target vehicle and a speed limit value of a current road section; wherein the driving state information includes speed information of the other vehicles and relative distances between the other vehicles and the target vehicle; A classification module configured to determine a driving category of the other vehicles according to the speed information of the other vehicles and the speed limit value; the driving category includes at least one of a speeding vehicle, a turtle vehicle and an aggressive driving vehicle; A prediction module configured to input a current driving speed of the target vehicle, the relative distances between the other vehicles and the target vehicle and the driving category of the other vehicles into a driving behavior prediction database for matching to obtain a prediction result of a predicted driving behavior of the target vehicle and a safety risk level corresponding to the predicted driving behavior; the predicted driving behavior includes at least one of acceleration, deceleration, lane changing and maintaining a distance; wherein the inputting of the current driving speed of the target vehicle, the relative distances between the other vehicles and the target vehicle and the driving category of the other vehicles into the driving behavior prediction database for matching to obtain the prediction result of the predicted driving behavior of the target vehicle and the safety risk level corresponding to the predicted driving behavior includes: forming a first two-dimensional array with the current driving speed of the target vehicle, the relative distances between the other vehicles and the target vehicle and the driving category of the other vehicles; inputting the first two-dimensional array into the driving behavior prediction database and matching the first two-dimensional array with a second two-dimensional array stored in the driving behavior prediction database, and outputting a second row element of the corresponding second two-dimensional array when a first row element of the second two-dimensional array is matched successfully; the second two-dimensional array includes the first row element and the second row element, the first row element is composed of a speed of a target vehicle, relative distances between other vehicles and the target vehicle and a category of the other vehicles collected historically, and the second row element is composed of a predicted driving behavior and a safety risk level corresponding to the first row element; wherein the inputting of the first two-dimensional array into the driving behavior prediction database and the matching of the first two-dimensional array with the second two-dimensional array stored in the driving behavior prediction database include: comparing each row element in the first two-dimensional array with the first row element of the second two-dimensional array stored in the driving behavior prediction database respectively, and determining that the row element is matched successfully if the speed of the target vehicle, the relative distances between the other vehicles and the target vehicle and the category of the other vehicles are all consistent or within a set error range; and outputting the second row element of the corresponding second two-dimensional array if each row element in the first two-dimensional array is matched successfully.

7. An electronic device, comprising: The method comprises: A processor, a memory, and a bus, the memory storing machine readable instructions executable by the processor, the processor in communication with the memory via the bus when the electronic device is running, the machine readable instructions, when executed by the processor, performing the steps of the driving behavior prediction method of any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, A computer readable storage medium storing a computer program, the computer program, when executed by a processor, performing the steps of the driving behavior prediction method of any one of claims 1 to 5.

Images