Driving risk warning method, device, computing equipment and storage medium

Abstract

The embodiments of the present application provide a driving risk warning method, apparatus, computing device and storage medium, the method comprising: obtaining first dangerous driving behavior data of a driver in a current time period, and obtaining a correspondence between the number of occurrences of the dangerous driving behavior and the actual number of occurrences of dangerous scenarios, accurately predicting the number of times each dangerous scenario will occur to the driver in the current time period based on the correspondence and the number of occurrences of each dangerous driving behavior in the first dangerous driving behavior data, and providing a risk warning based on the accurately predicted possible number of occurrences of each dangerous scenario, thereby improving the accuracy of the driving risk warning, and providing a warning for a variety of dangerous scenarios that may be caused by the driver's dangerous driving behavior at the current moment.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of intelligent driving technology, and in particular, to a driving risk warning method, device, computing device and storage medium. Background Art

[0002] How to achieve safe driving is the most important issue for every driver during the driving process. With the development of computer vision technology, computer vision technology has been widely used in the field of safe driving. For example, a camera is installed on the vehicle to collect the driver's driving behavior in real time and issue a driving risk warning based on the driver's driving behavior.

[0003] The current driving risk warning method predicts the possibility of a driver encountering a dangerous scenario based on the driver's historical driving behavior. Its warning accuracy is low and it is unable to warn of multiple dangerous scenarios that may be caused by the driver's current dangerous driving behavior. Summary of the invention

[0004] The embodiments of the present application provide a driving risk warning method, device, computing device and storage medium to improve the accuracy of vehicle driving risk warning and to provide accurate warning of various dangerous scenarios that may be caused by the driver's current dangerous driving behavior.

[0005] In a first aspect, an embodiment of the present application provides a driving risk warning method, comprising:

[0006] Acquire the first dangerous driving behavior data of the driver in the current time period, and acquire the corresponding relationship between the number of occurrences of the dangerous driving behavior and the actual number of occurrences of the dangerous scene;

[0007] According to the number of occurrences of each dangerous driving behavior in the first dangerous driving behavior data and the corresponding relationship, predict the number of times the driver will encounter each dangerous scenario in the current time period;

[0008] According to the predicted number of times each dangerous scenario will occur to the driver in the current time period, a warning message is generated.

[0009] In a second aspect, an embodiment of the present application provides a driving risk warning device, including:

[0010] An acquisition unit, used to acquire the first dangerous driving behavior data of the driver in the current time period, and to acquire the corresponding relationship between the number of occurrences of the dangerous driving behavior and the actual number of occurrences of the dangerous scene;

[0011] a prediction unit, configured to predict the number of times the driver will encounter each dangerous scenario in a current time period according to the number of times each dangerous driving behavior occurs in the first dangerous driving behavior data and the corresponding relationship;

[0012] The determination unit is used to generate warning information according to the predicted number of times each dangerous scenario occurs to the driver in the current time period.

[0013] In a possible implementation of the second aspect, the above-mentioned acquisition unit is specifically used to obtain the driver's historical dangerous driving behavior data and historical dangerous scene data within a preset historical time period; and based on the driver's historical dangerous driving data, obtain the number of times the driver has each dangerous driving behavior within the historical time period; and based on the driver's historical dangerous scene data, obtain the number of times the driver has each dangerous scene within the historical time period; finally, based on the number of times the driver has each dangerous driving behavior within the historical time period and the number of times the driver has each dangerous scene within the historical time period, obtain the correspondence between the number of occurrences of dangerous driving behaviors and the actual number of occurrences of dangerous scenes.

[0014] Optionally, the warning information includes the predicted number of times the driver will encounter each dangerous scenario within the current time period.

[0015] In a possible implementation of the second aspect, the above-mentioned determination unit is specifically used to determine the probability of being warned for each dangerous scenario based on the predicted number of times the driver will encounter each dangerous scenario within the current time period; based on the probability of being warned for each dangerous scenario, determine at least one dangerous scenario to be warned, and the warning information includes at least one dangerous scenario to be warned.

[0016] In a possible implementation manner of the second aspect, the above-mentioned determination unit is specifically used to generate a random number; and determine at least one dangerous scene to be warned according to the warning probability of each dangerous scene and the random number.

[0017] In a possible implementation of the second aspect, the above-mentioned determination unit is specifically used to determine the k+1th dangerous scenario as the dangerous scenario to be warned when the random number is greater than the sum of the warning probabilities of the first k dangerous scenarios and less than or equal to the sum of the warning probabilities of the first k+1 dangerous scenarios; and to determine the kth dangerous scenario as the dangerous scenario to be warned when the random number is greater than a first numerical value and less than or equal to the sum of the warning probabilities of the first k dangerous scenarios; wherein, when the k is greater than 1, the first numerical value is the sum of the warning probabilities of the first k-1 dangerous scenarios, and when the k is equal to 1, the first numerical value is 0.

[0018] In a possible implementation of the second aspect, the above-mentioned acquisition unit is specifically used to obtain the driver image captured by the first camera within the current time period; identify each dangerous driving behavior of the driver in the driver image according to the type of preset dangerous driving behavior; and obtain first dangerous driving behavior data based on the identified dangerous driving behaviors of the driver.

[0019] In a possible implementation of the second aspect, the above-mentioned acquisition unit is specifically used to obtain the first dangerous driving behavior data of the driver in the current time period from the second vehicle-mounted camera, and the second vehicle-mounted camera is used to capture the driver's image, and perform dangerous driving behavior identification on the captured driver image according to a preset type of dangerous driving behavior to generate the first dangerous driving behavior data.

[0020] Optionally, the duration of the current time period is the duration for the first vehicle-mounted camera to capture the driver's image.

[0021] In a third aspect, an embodiment of the present application provides a computing device, including a processor and a memory;

[0022] The memory is used to store computer programs;

[0023] The processor is used to execute the computer program to implement the driving risk warning method described in the first aspect above.

[0024] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the storage medium includes computer instructions. When the instructions are executed by a computer, the computer implements the driving risk warning method as described in the first aspect.

[0025] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a computer program, and the computer program is stored in a readable storage medium. At least one processor of a computer can read the computer program from the readable storage medium, and the at least one processor executes the computer program so that the computer implements the driving risk warning method described in the first aspect.

[0026] The driving risk warning method, device, computing device and storage medium provided in the embodiment of the present application can truly reflect the correlation between the number of occurrences of dangerous driving behaviors and the number of occurrences of dangerous scenes by obtaining the first dangerous driving behavior data of the driver in the current time period, and obtaining the corresponding relationship between the number of occurrences of dangerous driving behaviors and the actual number of occurrences of dangerous scenes. In this way, the number of occurrences of each dangerous scene of the driver in the current time period can be accurately predicted based on the corresponding relationship and the number of occurrences of each dangerous driving behavior in the first dangerous driving behavior data, and risk warning can be performed based on the accurately predicted number of possible occurrences of each dangerous scene, thereby improving the accuracy of driving risk warning, and can achieve warning of multiple dangerous scenes that may be caused by the driver's dangerous driving behavior at the current moment. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0028] Figure 1 A schematic diagram of an application scenario provided for an embodiment of the present application;

[0029] Figure 2 This is a system architecture diagram involved in the embodiments of the present application;

[0030] Figure 3 A schematic diagram of a process flow of a driving risk warning method provided in an embodiment of the present application;

[0031] Figure 4 A schematic diagram of image processing involved in an embodiment of the present application;

[0032] Figure 5 A schematic diagram of the early warning information involved in the embodiment of the present application;

[0033] Figure 6 Another schematic diagram of the warning information involved in the embodiment of the present application;

[0034] Figure 7 Another schematic diagram of a process flow of a driving risk warning method provided in an embodiment of the present application;

[0035] Figure 8 A schematic diagram of another process flow of the driving risk warning method provided in an embodiment of the present application;

[0036] Fig. 9 A schematic diagram of a flow chart of a method for predicting dangerous driving behavior provided in an embodiment of the present application;

[0037] Fig.10A schematic diagram of the structure of a driving risk warning device provided in an embodiment of the present application;

[0038] Fig.11 A schematic diagram of a structure of a device for predicting dangerous driving behavior provided in an embodiment of the present application;

[0039] Fig.12 A block diagram of a computing device involved in an embodiment of the present application. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.

[0041] In order to facilitate understanding of the embodiments of the present application, the relevant concepts involved in the embodiments of the present application are briefly introduced as follows:

[0042] Vehicle to everything (V2X) provides vehicle information through sensors and on-board terminals installed in the vehicle, and uses various communication technologies to achieve communication between vehicles (Vehicle to Vehicle, V2V), between vehicles and roads (Vehicle to Infrastructure, V2I), between vehicles and people (Vehicle to Pedestrian, V2P), and between vehicles and networks (Vehicle to Network, V2N).

[0043] Artificial Intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is a comprehensive technology in computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a similar way to human intelligence. Artificial intelligence is to study the design principles and implementation methods of various intelligent machines so that machines have the functions of perception, reasoning and decision-making.

[0044] Artificial intelligence technology is a comprehensive discipline that covers a wide range of fields, including both hardware-level and software-level technologies. The basic technologies of artificial intelligence generally include sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics and other technologies. Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0045] Computer Vision (CV) is a science that studies how to make machines "see". To put it more specifically, it refers to the use of cameras and computers to replace human eyes to identify, track and measure targets, and further perform graphics processing so that the computer processes the images into images that are more suitable for human observation or transmission to instruments for detection. As a scientific discipline, computer vision studies related theories and technologies, and attempts to establish an artificial intelligence system that can obtain information from images or multi-dimensional data. Computer vision technology usually includes image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content / behavior recognition, three-dimensional object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous positioning and mapping, and other technologies, as well as common biometric recognition technologies such as face recognition and fingerprint recognition.

[0046] Intelligent driving technology includes high-precision maps, environmental perception, behavioral decision-making, path planning, motion control and other technologies, and intelligent driving technology has broad application prospects. The embodiment of the present application is applied to the field of intelligent driving technology to warn the driver of driving risks and assist the driver in driving safely.

[0047] It should be understood that in the embodiment of the present invention, "B corresponding to A" means that B is associated with A. In one implementation, B can be determined based on A. However, it should also be understood that determining B based on A does not mean determining B based only on A, and B can also be determined based on A and / or other information.

[0048] In the description of the present application, unless otherwise specified, “plurality” means two or more than two.

[0049] In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference.

[0050] Figure 1 A schematic diagram of an application scenario provided in an embodiment of the present application, such as Figure 1 As shown, vehicle A, vehicle B and vehicle C are all moving vehicles, and at least one of the vehicles can execute the driving risk warning method provided in the embodiment of the present application during driving.

[0051] Figure 2 This is a system architecture diagram involved in the embodiment of the present application, such as Figure 2 As shown, the system architecture includes: a driver, a computing device, an on-board camera and a warning system.

[0052] The vehicle-mounted camera is installed on the vehicle to collect images of the driver. Optionally, the vehicle-mounted camera can be an AI camera, which can use computer vision technology to obtain data on the driver's dangerous driving behavior.

[0053] The computing device is respectively connected to the vehicle-mounted camera and the early warning system in communication, and can obtain data from the vehicle-mounted camera and the early warning system, and can also send data to the vehicle-mounted camera and the early warning system. For example, the computing device can obtain the driver's driving behavior data from the vehicle-mounted camera, and can obtain the dangerous scene data of the vehicle from the early warning system. The above computing device can be used to execute the technical solution of the embodiment of the present application, for example, it can be used to obtain the first dangerous driving behavior data of the driver in the current time period, and obtain the corresponding relationship between the number of occurrences of the dangerous driving behavior and the actual number of occurrences of the dangerous scene; and according to the number of occurrences of each dangerous driving behavior in the first dangerous driving behavior data, and the corresponding relationship, predict the number of times the driver will have each dangerous scene in the current time period, and finally generate early warning information according to the predicted number of times the driver will have each dangerous scene in the current time period.

[0054] In some embodiments, if the computing device does not have a display function, the computing device may send the generated warning information to the warning system, and the warning system displays the warning information.

[0055] In some embodiments, when the computing device has a display function, such as a display screen, the computing device can directly display the warning information.

[0056] The early warning system is installed on the vehicle to warn of dangerous scenarios and save data on dangerous scenarios that have actually occurred in the vehicle.

[0057] In some embodiments, if the computing device is a vehicle-mounted device, the above-mentioned early warning system can be installed on the computing device.

[0058] The current driving risk warning method predicts the possibility of a driver encountering a dangerous scenario based on the driver's historical driving behavior. Its warning accuracy is low and it is unable to warn of various dangerous scenarios that may be caused by the driver's current dangerous driving behavior.

[0059] In order to solve the above technical problems, the embodiment of the present application provides a driving risk prediction method and device, which obtains the first dangerous driving behavior data of the driver in the current time period, and obtains the corresponding relationship between the number of occurrences of dangerous driving behaviors and the actual number of occurrences of dangerous scenes. The corresponding relationship can truly reflect the correlation between the number of occurrences of dangerous driving behaviors and the number of occurrences of dangerous scenes. In this way, based on the corresponding relationship and the number of occurrences of each dangerous driving behavior in the first dangerous driving behavior data, the number of times the driver will encounter each dangerous scene in the current time period can be accurately predicted, and risk warnings can be issued based on the accurately predicted number of possible occurrences of each dangerous scene, thereby improving the accuracy of driving risk warnings, and warnings can be issued for various dangerous scenes that may be caused by the driver's dangerous driving behavior at the current moment.

[0060] The technical solutions of the embodiments of the present application are described in detail below through some embodiments. The following embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0061] Figure 3 A flowchart of a driving risk warning method provided in an embodiment of the present application. Figure 3 As shown, the method of the embodiment of the present application includes:

[0062] S301, obtaining first dangerous driving behavior data of a driver in a current time period, and obtaining a corresponding relationship between the number of occurrences of the dangerous driving behavior and the actual number of occurrences of dangerous scenarios.

[0063] The execution subject of the embodiment of the present application is a device with a warning function for the driving risk of the vehicle, such as a warning device for driving risk, hereinafter referred to as the warning device. In some embodiments, the warning device is Figure 2 In some embodiments, the early warning device is a unit in the computing device with data processing function, such as a processor in the computing device. The embodiment of the present application is described by taking the execution subject as a computing device as an example.

[0064] The dangerous driving behaviors involved in the embodiments of the present application include preset M different types of dangerous driving behaviors, as shown in Table 1, including fatigue driving, distracted driving, drunk driving, not wearing a seat belt, etc., where M is an integer greater than or equal to 1. The type of dangerous driving behavior can be set according to actual needs, and the embodiments of the present application do not limit this.

[0065] Table 1

[0066]

[0067] In some embodiments, the types of dangerous driving behaviors can be stored in advance. Figure 2 In the vehicle-mounted camera shown, in actual use, the computing device can obtain the type of dangerous driving behavior from the vehicle-mounted camera.

[0068] In some embodiments, the types of dangerous driving behaviors may be stored in advance in the computing device.

[0069] The dangerous scenarios involved in the embodiments of the present application include preset N different types of dangerous scenarios, as shown in Table 2, including lane deviation, pedestrian collision, front collision, safe vehicle distance, etc., where N is an integer greater than or equal to 1. The type of dangerous scenario can be set according to actual needs, and the embodiments of the present application do not limit this.

[0070] Table 2

[0071]

[0072] It should be noted that if the dangerous driving behavior includes speeding, the computing device can obtain the vehicle's driving speed from the vehicle's driving system to determine whether the vehicle is speeding.

[0073] In some embodiments, the type of dangerous scene can be saved in advance. Figure 2 In the early warning system shown, in actual use, the computing device can obtain the type of dangerous scene from the early warning system.

[0074] In some embodiments, the type of dangerous scenario may be stored in advance in the computing device.

[0075] In the embodiment of the present application, the method of obtaining the first dangerous driving behavior data of the driver in the current time period in the above S301 includes at least the following two methods: Figure 2 When the vehicle-mounted camera shown is a first vehicle-mounted camera without an image recognition function, the computing device may adopt method 1 to obtain the first dangerous driving data of the driver. Figure 2 When the vehicle-mounted camera shown is a second vehicle-mounted camera with an image recognition function, the computing device may obtain the first dangerous driving behavior data of the driver in a second manner, specifically:

[0076] Method 1: The computing device generates first dangerous driving behavior data based on the driver image collected by the first vehicle-mounted camera. The specific process includes the following steps C1 to C3:

[0077] Step C1, obtaining the driver image captured by the first vehicle-mounted camera in the current time period.

[0078] The first vehicle-mounted camera is installed on the vehicle at a position facing the driver, and is used to collect the driver's image in real time. At the same time, the first vehicle-mounted camera is connected to the computing device for communication, and can send the driver's image collected in the current time period to the computing device.

[0079] Step C2, identifying each dangerous driving behavior of the driver in the driver image according to the preset types of dangerous driving behaviors.

[0080] Specifically, the computing device obtains the driver image captured by the first vehicle-mounted camera in the current time period from the first vehicle-mounted camera. Then, according to the preset types of M dangerous driving behaviors, based on the existing technology, the facial features and behavioral features of the driver in the driver image are identified, and it is determined which of the M dangerous driving behaviors the driver has exhibited in the current time period. For example, the computing device includes a pre-trained image recognition model, and the image recognition model can identify the facial features and behavioral features of the driver. The computing device inputs the driver image into the image recognition model, and the image recognition model identifies the facial features and behavioral features of the driver, wherein the facial features include eye states (e.g., whether the eyes are open or squinting), mouth states (e.g., whether the mouth is open or closed, and the size of the opening), head position, etc., and the behavioral features include hand movements and upper body movements, etc. The computing device compares the facial features and behavioral features of the driver identified by the image recognition model with the facial features and behavioral features corresponding to each of the M dangerous driving behaviors to determine the dangerous driving behavior corresponding to the identified facial features and behavioral features. For example, if the driver's eyes are identified as squinting and his mouth is open, it can be determined that the driver is driving fatigued; if the seat belt is not identified in the driver's image, it can be determined that the driver is not wearing the seat belt; if the driver's hand is raised and holding a phone, it can be determined that the driver is distracted, etc. Among them, the facial features and behavioral features of the driver corresponding to different dangerous driving behaviors can be set according to actual conditions.

[0081] Step C3, obtaining first dangerous driving behavior data according to the identified dangerous driving behaviors of the driver.

[0082] If multiple driver images are collected in the current time period, the above recognition method is used for each driver image to identify the dangerous driving behavior of the driver in each driver image. According to the dangerous driving behavior of the driver in each driver image, the number of times each dangerous driving behavior occurs in multiple driver images is counted. For example, if fatigue driving is identified in 10 of the 1000 driver images, it can be determined that the driver has 10 fatigue drivings in the current time period. Each identified dangerous driving behavior and the number of occurrences of each dangerous driving behavior are used as the first dangerous driving behavior data, that is, the first dangerous driving behavior data includes each dangerous driving behavior of the driver identified in the current time period and the number of occurrences of each dangerous driving behavior. It should be noted that for the dangerous driving behavior of not wearing a seat belt, if the seat belt is not identified in the multiple consecutive driver images collected, the number of times the driver is not wearing a seat belt is determined to be 1 time, not multiple times.

[0083] Method 2: The computing device obtains the first dangerous driving behavior data of the driver in the current time period from the second vehicle-mounted camera.

[0084] In this method, Figure 1 The vehicle-mounted camera shown is a second vehicle-mounted camera, and the second vehicle-mounted camera is a camera with an image processing function, such as an AI camera. The second vehicle-mounted camera may include a camera module and a processor, and the camera module is used to collect the driver image in real time and send the collected driver image to the processor. Figure 4 As shown, the processor processes the driver image based on computer vision technology to obtain the first dangerous driving behavior data shown on the left. Specifically, the processor performs image recognition processing on the driver image according to the preset M types of dangerous driving behaviors to obtain the dangerous driving behaviors of the driver in the current time period. For example, the processor identifies the facial features and behavioral features of the driver in the driver image. If the driver's eyes are identified as closed and the mouth is open, it can be determined that the driver is fatigued. If the seat belt is not identified in the driver image, it can be determined that the driver is not wearing a seat belt. In this way, the processor generates the first dangerous driving behavior data based on the identified dangerous driving behavior of the driver. It should be noted that the method for the processor to identify the dangerous driving behavior of the driver in the driver image in this manner is basically the same as the method for the computing device to identify the dangerous driving behavior of the driver in the driver image mentioned above. The above specific description can be referred to and will not be repeated here.

[0085] In some embodiments, the duration of the current time period is the duration that the first vehicle-mounted camera or the second vehicle-mounted camera captures the driver's image.

[0086] It should be noted that, in the embodiment of the present application, there is no order between obtaining the first dangerous driving behavior data and obtaining the above-mentioned corresponding relationship. That is, the computing device may first obtain the first dangerous driving behavior data, and then obtain the corresponding relationship between the number of occurrences of the dangerous driving behavior and the actual number of occurrences of the dangerous scene, or may first obtain the corresponding relationship between the number of occurrences of the dangerous driving behavior and the actual number of occurrences of the dangerous scene, and then obtain the first dangerous driving behavior data, or may simultaneously obtain the first dangerous driving behavior data and the corresponding relationship.

[0087] In some embodiments, the correspondence between the number of occurrences of dangerous driving behaviors and the actual number of occurrences of dangerous scenarios can be generated in advance. When performing driving risk warning, the computing device can directly obtain the generated correspondence, thereby avoiding the time resources and computing resources consumed by generating the correspondence, thereby achieving timely warning of driving risks. For example, the computing device generates a correspondence once a day, so that the correspondence is used in the driving risk warning process throughout the day.

[0088] In some embodiments, the above correspondence relationship may be generated when the computing device acquires the first dangerous driving behavior data. For example, the computing device acquires the first dangerous driving behavior data of the driver in the current time period, and in response to the acquired first dangerous driving behavior data, the computing device starts to generate the correspondence relationship.

[0089] Since most traffic accidents are caused by human factors, there is a correlation between the number of times a driver's dangerous driving behavior occurs and the number of times dangerous scenes occur. Based on this, the embodiment of the present application obtains the correspondence between the number of times a dangerous driving behavior occurs and the actual number of times a dangerous scene occurs, and based on the correspondence, accurately predicts one or more dangerous scenes that may be caused by the driver's dangerous driving behavior, thereby improving the accuracy of early warning of driving risks.

[0090] In the embodiment of the present application, the above correspondence relationship may be generated based on the historical dangerous driving behavior data and historical dangerous scene data of the driver. Optionally, the above correspondence relationship may also be generated based on the historical dangerous driving behavior data and historical dangerous scene data of other drivers.

[0091] S302: predict the number of times each dangerous scene occurs in the current time period according to the number of occurrences of each dangerous driving behavior in the first dangerous driving behavior data and the corresponding relationship.

[0092] For example, assuming that the current time period is 10 seconds, 1,000 driver images are collected within these 10 seconds, and the 1,000 driver images are analyzed to obtain the first dangerous driving behavior data: 10 fatigue driving and 5 times of not wearing a seat belt, so that the number of occurrences of fatigue driving is 10 and the number of occurrences of not wearing a seat belt is 5. The computing device predicts the number of times the driver has each dangerous scenario in the current time period based on the number of occurrences of each dangerous driving behavior in the first dangerous driving behavior data and the corresponding relationship.

[0093] In some embodiments, the number of times the driver encounters each dangerous scenario in the current time period can be determined by the following formula (1):

[0094] (1)

[0095] in, is the correspondence between the number of dangerous driving behaviors and the actual number of dangerous scenes. is a matrix with N rows and M columns. is the number of times the driver commits the i-th dangerous driving behavior within time period t, where i is greater than or equal to 1 and less than or equal to M. is the predicted number of times the driver will encounter the jth dangerous scenario within time period t, where j is greater than or equal to 1 and less than or equal to N.

[0096] Combined with the above example, take t as the current time period, the driver has 10 fatigue driving and 5 dangerous driving behaviors without wearing a seat belt in the current time period. Combined with Table 1, it can be determined that , , and the others are all 0. In this way, , Substituting into the above formula (1), we can predict the number of times the driver will encounter each dangerous scenario in the current time period: , to .

[0097] For example, assume that both M and N are 4, that is, the four dangerous driving behaviors are fatigue driving, distracted driving, drunk driving and not wearing seat belts in Table 1, and the four dangerous scenarios are lane deviation, pedestrian collision, front collision and safe vehicle distance in Table 2. Assume that the first dangerous driving behavior data shows that the driver has 10 cases of fatigue driving and 5 cases of not wearing seat belts in the current time period, and no distracted driving or drunk driving has occurred, then , , and are all 0. In this way, , Substituting into the above formula (1), we can get the following result:

[0098]

[0099] At this time, the correspondence between the number of dangerous driving behaviors and the actual number of dangerous scenes is a matrix with 4 rows and 4 columns, that is , where all parameters are known. is the number of lane deviations, is the number of pedestrian collisions, is the number of frontal collisions, is the number of safe vehicle distance occurrences.

[0100] In this way, the number of lane deviations that the driver will experience in the current time period can be predicted as ,The number of pedestrian collisions that the driver has in the current time period is ,The number of frontal collisions that the driver has in the current time period is ,The number of times the driver violates the safety distance in the current time period is .

[0101] S303: Generate warning information based on the predicted number of times the driver will encounter each dangerous scenario in the current time period.

[0102] The embodiment of the present application generates warning information by predicting the number of times the driver will encounter each dangerous scenario within the current time period, thereby accurately predicting the dangerous scenarios caused by the driver's current dangerous driving behavior, thereby improving the driving safety of the vehicle.

[0103] In the embodiment of the present application, the methods of generating warning information according to the predicted number of times the driver will encounter each dangerous scenario in the current time period include but are not limited to the following:

[0104] In the first approach, the warning information includes the number of times the driver is currently predicted to encounter each dangerous scenario in the current time period, e.g. Figure 5 As shown, the warning information includes the predicted number of times each of N dangerous scenarios will occur to the driver in the current time period.

[0105] In one implementation, the number of occurrences of each dangerous scenario in the warning information can be sorted from large to small according to the number of occurrences.

[0106] In one implementation, the warning information may include dangerous scenarios whose occurrence times are not zero, but exclude dangerous scenarios whose occurrence times are zero.

[0107] In the second method, the warning information includes one or more dangerous scenarios that are predicted to occur to the driver a non-zero number of times in the current time period, such as Figure 6 As shown, the warning information includes two dangerous scenarios: safe vehicle distance and pedestrian collision. It is predicted that the driver will encounter the safe vehicle distance dangerous scenario 10 times and the pedestrian collision will occur 1 time in the current time period.

[0108] After the warning information is generated according to the above method, the computing device sends the generated warning information to the warning system, and the warning system outputs the warning information to the driver, so that the driver can drive safely according to the warning information.

[0109] Optionally, if the computing device has a display function or a voice prompt function, the computing device may also directly output the warning information to the driver.

[0110] The driving risk warning method provided in the embodiment of the present application obtains the first dangerous driving behavior data of the driver in the current time period, and obtains the corresponding relationship between the number of occurrences of the dangerous driving behavior and the actual number of occurrences of the dangerous scene. The corresponding relationship can truly reflect the correlation between the number of occurrences of the dangerous driving behavior and the number of occurrences of the dangerous scene. In this way, the number of times the driver will have each dangerous scene in the current time period can be accurately predicted based on the corresponding relationship and the number of occurrences of each dangerous driving behavior in the first dangerous driving behavior data, and risk warnings can be made based on the accurately predicted number of possible occurrences of each dangerous scene, thereby improving the accuracy of driving risk warnings, and making warnings for various dangerous scenes that may be caused by the driver's dangerous driving behavior at the current moment.

[0111] Based on the above embodiments, Figure 7 The specific process of obtaining the correspondence between the number of occurrences of dangerous driving behaviors and the actual number of occurrences of dangerous scenarios in the above S301 is introduced in detail.

[0112] Figure 7 Another flowchart of the driving risk warning method provided in the embodiment of the present application is as follows: Figure 7 As shown, the corresponding relationship between the number of occurrences of dangerous driving behaviors and the actual number of occurrences of dangerous scenes in the above S301 may include:

[0113] S701. Obtain historical dangerous driving behavior data and historical dangerous scene data of the driver within a preset historical time period.

[0114] It should be noted that the historical dangerous driving behavior data includes the dangerous driving behaviors that actually occurred to the driver in the historical time period. The historical dangerous scene data includes the dangerous scenes that actually occurred to the driver in the historical time period.

[0115] The above-mentioned preset historical time period may be the historical time period closest to the current moment, for example, the preset historical time period may be 3 months before the current moment.

[0116] In some embodiments, if the dangerous driving behavior data is stored in Figure 2 The vehicle-mounted camera shown, so that the computing device can obtain the driver's historical dangerous driving behavior data within a preset historical time period from the vehicle-mounted camera.

[0117] In some embodiments, if the dangerous driving behavior data is stored in Figure 2 In the storage device of the computing device shown, the computing device can obtain the driver's historical dangerous driving behavior data within a preset historical time period from its own storage device.

[0118] In some embodiments, if the driver encounters a dangerous scenario, the data is stored in Figure 2 In the warning system shown, the computing device can obtain the driver's historical danger scene data within a preset historical time period from the warning system.

[0119] S702: Obtain the number of occurrences of each type of dangerous driving behavior of the driver in a historical time period based on the driver's historical dangerous driving data.

[0120] Specifically, the computing device may obtain the number of times the driver has performed each of the M types of dangerous driving behaviors in a historical time period according to the driver's historical dangerous driving behavior data, as shown in Table 3:

[0121] Table 3

[0122]

[0123] As shown in Table 3, the right side shows the number of times the driver has committed each dangerous driving behavior in the historical time period. For example, the number of times the driver has committed the second dangerous driving behavior in the historical time period is b2.

[0124] S703: According to the driver's historical dangerous scenario data, obtain the number of times each dangerous scenario occurs to the driver in a historical time period.

[0125] Similarly, the computing device may calculate the number of times each of the N dangerous scenarios actually occurred in the historical time period according to the driver's historical dangerous scenario data, as shown in Table 4:

[0126] Table 4

[0127]

[0128] As shown in Table 4, the right side shows the number of times each dangerous scenario actually occurred to the driver in the historical time period. For example, the number of times the second dangerous scenario actually occurred to the driver in the historical time period is a2.

[0129] S704. Obtain a correspondence between the number of times the dangerous driving behavior occurs and the actual number of times the dangerous scene occurs according to the number of times the driver occurs each dangerous driving behavior in the historical time period and the number of times the driver occurs each dangerous scene in the historical time period.

[0130] In some embodiments, if there is a linear mapping relationship between the number of occurrences of dangerous driving behaviors and the actual number of occurrences of dangerous scenarios, the linear mapping relationship is as shown in formula (2):

[0131] (2)

[0132] In formula (2), a1, a2 to aN are the number of times the driver encountered different types of dangerous scenarios in Table 4 during the historical period, b1, b2 to b M It is the number of times the driver has performed different types of dangerous driving behaviors in Table 3 during the historical period.

[0133] Substituting the data in Table 3 and Table 4 into formula (2) yields the matrix , the matrix As the correspondence between the number of occurrences of dangerous driving behaviors and the actual number of occurrences of dangerous scenarios.

[0134] In some embodiments, if there is a linear mapping relationship between the actual number of occurrences of dangerous scenarios and the number of occurrences of dangerous driving behaviors, the linear mapping relationship is as shown in formula (3):

[0135] (3)

[0136] In formula (3), a1, a2 to a N is the number of times the driver has encountered different types of dangerous scenarios in Table 4 in the historical period, b1, b2 to b M It is the number of times the driver has performed different types of dangerous driving behaviors in Table 3 during the historical period.

[0137] Substituting the data in Table 3 and Table 4 into formula (3) yields the matrix , the matrix As the correspondence between the number of dangerous driving behaviors and the actual number of dangerous scenes, the matrix It can be understood as a matrix A variation of .

[0138] In actual solution of the matrix and When , there may be a situation where the solution is not unique, in which case any solution can be selected. In other cases, there may be a situation where convergence does not occur during the solution process, in which case the solution with the smallest norm can be selected as the matrix solution. For the norm, any type of norm can be selected, such as the 2 norm.

[0139] The driving risk warning method provided in the embodiment of the present application obtains the driver's historical dangerous driving behavior data and historical dangerous scene data within a preset historical time period, and obtains the number of times the driver has each dangerous driving behavior within the historical time period based on the driver's historical dangerous driving behavior data, and obtains the number of times the driver has each dangerous scene within the historical time period based on the driver's historical dangerous scene data; then, based on the number of times the driver has each dangerous driving behavior within the historical time period and the number of times the driver has each dangerous scene within the historical time period, obtains the correspondence between the number of times the dangerous driving behavior occurs and the actual number of times the dangerous scene occurs, so that the correspondence can accurately reflect the correlation between the number of times the dangerous driving behavior occurs and the actual number of times the dangerous scene occurs, so that when a warning is issued based on the accurately determined corresponding relationship, the accuracy of the driving risk warning can be improved.

[0140] Based on the above embodiments, Figure 8 A detailed introduction is given to an implementation method of generating warning information according to the predicted number of times the driver will encounter each dangerous scenario within the current time period in the above S303.

[0141] Figure 8 Another flowchart of the driving risk warning method provided in the embodiment of the present application is as follows: Figure 8 As shown, in the above S303, according to the predicted number of times the driver will encounter each dangerous scenario in the current time period, the warning information is generated, which may include:

[0142] S801. Determine the probability of being warned of each dangerous scenario according to the predicted number of times the driver will encounter each dangerous scenario in the current time period.

[0143] Specifically, referring to the above formula (1), according to the number of times the driver has each dangerous driving behavior in the current time period, the number of times the driver has each dangerous scene in the current time period is predicted to be: 1,t 、a 2,t 、a 3,t ……a N,t .

[0144] Next, the probability of being warned of each dangerous scenario is determined based on the predicted number of times the driver will encounter each dangerous scenario in the current time period. For example, the probability of being warned of each dangerous scenario can be determined according to formula (4):

[0145] (4)

[0146] Among them, p j is the probability of being warned for the jth dangerous scenario, a j,t is the predicted number of times the driver will encounter the jth dangerous scenario within time period t, where j is greater than or equal to 1 and less than or equal to N. At this time, t is the current time period.

[0147] In this step, the probability of being warned for each dangerous scenario in the current time period can be determined according to the above formula (4).

[0148] S802: Determine at least one dangerous scenario to be warned according to the warning probability of each dangerous scenario.

[0149] The warning information includes at least one dangerous scenario to be warned.

[0150] In some embodiments, one or several dangerous scenes with the highest warning probability are determined as dangerous scenes to be warned.

[0151] In some embodiments, in order to ensure that dangerous scenes with a warning probability not equal to 0 have an equal chance of being warned, the above S702 determines at least one dangerous scene to be warned according to the warning probability of each dangerous scene, including step A and step B:

[0152] Step A, generate a random number.

[0153] Optionally, the random number follows a 0-1 even distribution.

[0154] Step B: determining at least one dangerous scene to be warned according to the warning probability of each dangerous scene and the random number.

[0155] Among them, according to the probability of being warned of each dangerous scene and the random number, at least one dangerous scene to be warned is determined, including the following two situations:

[0156] Case 1: When the random number is greater than the sum of the warning probabilities of the first k dangerous scenarios and less than or equal to the sum of the warning probabilities of the first k+1 dangerous scenarios, the k+1th dangerous scenario is determined to be the dangerous scenario to be warned.

[0157] Specifically, refer to formula (5):

[0158] (5)

[0159] in, is a random number, is the sum of the warning probabilities of the first k dangerous scenarios, The sum of the warning probabilities of the first k+1 dangerous scenarios, where k is a positive integer greater than or equal to 1 and less than or equal to N.

[0160] When random number When the above formula (5) is satisfied, the k+1th dangerous scene is regarded as the dangerous scene to be warned. =0.5, p1=0.1, p2=0.3, p3=0.2, If it is greater than the sum of p1 and p2 (i.e., 0.4) and less than the sum of p1, p2, and p3 (i.e., 0.6), it can be determined that k=2, and the third dangerous scenario (i.e., the front collision in Table 2) is determined as the dangerous scenario to be warned.

[0161] Case 2: When the random number is greater than the first value and less than or equal to the sum of the warning probabilities of the first k dangerous scenarios, the kth dangerous scenario is determined to be the dangerous scenario to be warned.

[0162] Specifically, if k is greater than 1, refer to formula (6):

[0163] (6)

[0164] When random number When the above formula (6) is satisfied, the kth dangerous scene is regarded as a dangerous scene to be warned. =0.2, p1=0.1, p2=0.3, p3=0.2, If it is less than the sum of p1 and p2 (i.e., 0.4) and greater than p1, the second dangerous scenario (i.e., the pedestrian collision in Table 2) is determined as the dangerous scenario to be warned.

[0165] If k=1, refer to formula (7):

[0166] (7)

[0167] When random number When the above formula (7) is satisfied, the kth dangerous scene is regarded as a dangerous scene to be warned. =0.1, p1=0.2, p2=0.3, p3=0.2, If it is less than p1 (i.e., 0.2) and greater than 0, the first dangerous scenario (i.e., the pedestrian collision in Table 2) is determined as the dangerous scenario to be warned.

[0168] In some embodiments of the present application, if the above-mentioned dangerous scenes to be warned include multiple ones, then each time a dangerous scene to be warned is determined, the warning probability of the determined dangerous scene to be warned is removed from the warning probability of the above-mentioned dangerous scenes. The warning probabilities of the remaining dangerous scenes are normalized, and the warning probabilities of the remaining dangerous scenes are re-determined. At the same time, the random number is re-determined, and the above-mentioned formula (5) or formula (6) or formula (7) is executed using the re-determined random number and the re-determined warning probabilities of each dangerous scene to determine the dangerous scene to be warned.

[0169] For example, assuming that there are two dangerous scenarios to be warned, the computing device first generates a random number 1, and determine the warning probability of each of the N dangerous scenarios according to the above formula (4). Then, determine the dangerous scenario 1 to be warned according to the above formula (5) or formula (6) or formula (7). Then, remove the warning probability of the dangerous scenario 1 to be warned from the warning probabilities of the above N dangerous scenarios, normalize the warning probabilities of the remaining N-1 dangerous scenarios, and re-determine the warning probability of each of the N-1 dangerous scenarios. At the same time, generate a random number 2, and the random number The warning probabilities of 2 and N-1 dangerous scenes are substituted into formula (5), formula (6) or formula (7) to determine the dangerous scene 2 to be warned.

[0170] The driving risk warning method provided in the embodiment of the present application determines the warning probability of each dangerous scenario based on the predicted number of times the driver will encounter each dangerous scenario within the current time period, determines at least one dangerous scenario to be warned based on the warning probability of each dangerous scenario, and carries the determined dangerous scenario to be warned in the warning information, so that the driver can directly obtain the dangerous scenarios that may occur at the moment through the warning information, which is convenient for the driver to take timely measures to improve the safety of vehicle driving.

[0171] above Figures 3 to 8 The embodiment shown describes in detail the dangerous driving warning method provided by the embodiment of the present application. The technical effect of the embodiment of the present application is further illustrated in combination with the experimental results. Specifically, the test is carried out in the simulator to obtain the ratio of the missed alarm rate of the present application to that of the prior art, and the ratio of the false alarm rate of the present application to that of the prior art, as shown in Table 5:

[0172] Table 5

[0173]

[0174] Among them, a false warning can be understood as a warning that should not have been given but was given, and a missed warning can be understood as a warning that should have been given but was not given. As shown in Table 5, the early warning method of the embodiment of the present application has a low false warning rate and a low missed warning rate compared to the existing early warning method. Compared with the existing early warning method, the early warning method of the embodiment of the present application significantly improves the accuracy of the early warning.

[0175] Based on the above embodiments, the embodiments of the present application also provide a method for predicting dangerous driving behavior.

[0176] Fig. 9 A flow chart of a method for predicting dangerous driving behavior provided in an embodiment of the present application. Fig. 9 As shown, the method of the embodiment of the present application includes:

[0177] S901. Obtain first dangerous scenario data that occurs to the vehicle within a first time period, and obtain a corresponding relationship between the number of occurrences of dangerous driving behaviors and the actual number of occurrences of dangerous scenarios.

[0178] The method for predicting dangerous driving behavior of a driver provided in the embodiment of the present application can be applied to the process of confirming the responsibility of a traffic accident. For example, based on the dangerous scene that occurred in the vehicle in the first time period, the dangerous driving behavior that the driver may have in the first time period is predicted.

[0179] The first time period may be the current time period or any historical time period.

[0180] In the embodiment of the present application, the methods for obtaining the first dangerous scene data occurring to the vehicle in the first time period include but are not limited to the following:

[0181] Method 1: A camera for photographing the external environment of the vehicle, such as a trip recorder, is installed on the vehicle. The driving environment images of the vehicle in a first time period are obtained from the camera, and the driving environment images are analyzed to obtain the first dangerous scene data occurring in the vehicle in the first time period.

[0182] Method 2: The driving environment images of the vehicle in the first time period can be obtained from roadside equipment, such as from cameras installed on both sides of the road, and these driving environment images are analyzed to obtain the first dangerous scene data that occurred to the vehicle in the first time period.

[0183] Optionally, the first dangerous scenario data includes dangerous scenarios that occur to the vehicle within a first time period, and the number of occurrences of each dangerous scenario.

[0184] It should be noted that, in the embodiment of the present application, there is no order between obtaining the first dangerous scene data and obtaining the correspondence between the number of occurrences of dangerous driving behaviors and the actual number of occurrences of dangerous scenes. In other words, the computing device may first obtain the first dangerous scene data and then obtain the correspondence, or may first obtain the correspondence and then obtain the first dangerous scene data, or may simultaneously obtain the first dangerous scene data and the correspondence.

[0185] Optionally, the above correspondence relationship may be generated in advance, or may be triggered and generated when the computing device acquires the first dangerous scenario data.

[0186] S902: predict the number of times the driver will perform each dangerous driving behavior in the first time period according to the number of occurrences of each dangerous scenario in the first dangerous scenario data and the corresponding relationship.

[0187] In some embodiments, the number of occurrences of each dangerous scenario in the current time period can be determined by the following formula (8):

[0188] (8)

[0189] in, is the correspondence between the number of dangerous driving behaviors and the actual number of dangerous scenes. is a matrix with M rows and N columns. is the number of times the driver commits the i-th dangerous driving behavior within time period t, where i is greater than or equal to 1 and less than or equal to M. is the predicted number of times the jth dangerous scenario occurs to the driver within time period t, where j is greater than or equal to 1 and less than or equal to N.

[0190] Combined with the above example, t is taken to represent the first time period. The dangerous scenarios that the vehicle encounters in the first time period are: 10 lane departures and 2 front collisions. Combined with Table 2, it can be determined that , , and the others are all 0. In this way, , Substituting into the above formula (8), the number of occurrences of each dangerous driving behavior of the driver in the first time period can be predicted.

[0191] S903: Generate prediction information according to the number of times the driver commits each dangerous driving behavior in the first time period.

[0192] The prediction information is used to indicate possible dangerous driving behavior of the driver during the first time period.

[0193] In some embodiments, the prediction information includes the number of times the driver commits each dangerous driving behavior within the first time period predicted in S902 above.

[0194] In some embodiments, the prediction information includes one or more dangerous driving behaviors whose predicted number of occurrences is not zero, for example, the prediction information includes the dangerous driving behavior predicted to occur the most frequently.

[0195] The method for predicting dangerous driving behaviors provided in the embodiment of the present application obtains the first dangerous scene data of the driver in the first time period, and obtains the corresponding relationship between the number of occurrences of the dangerous driving behavior and the actual number of occurrences of the dangerous scene, and the corresponding relationship can truly reflect the correlation between the number of occurrences of the dangerous driving behavior and the number of occurrences of the dangerous scene. In this way, the dangerous driving behaviors that the driver may have in the first time period can be accurately predicted based on the corresponding relationship and the number of occurrences of each dangerous scene in the first dangerous scene data.

[0196] Fig.10 A schematic diagram of a driving risk warning device provided in an embodiment of the present application. The warning device may be an electronic device or a component of an electronic device (e.g., an integrated circuit, a chip, etc.). The electronic device may be Figure 2 The computing device shown. Fig.10 As shown, the early warning device 100 may include: an acquisition unit 110 , a prediction unit 120 and a determination unit 130 .

[0197] The acquisition unit 110 is used to acquire the first dangerous driving behavior data of the driver in the current time period, and to acquire the corresponding relationship between the number of occurrences of the dangerous driving behavior and the actual number of occurrences of the dangerous scene;

[0198] The prediction unit 120 is used to predict the number of times the driver will encounter each dangerous scenario in the current time period according to the number of occurrences of each dangerous driving behavior in the first dangerous driving behavior data and the corresponding relationship;

[0199] The determination unit 130 is used to generate warning information according to the predicted number of times each dangerous scenario will occur to the driver in the current time period.

[0200] The driving risk warning device of the embodiment of the present application can be used to execute the technical solutions of the above-mentioned method embodiments. Its implementation principles and technical effects are similar and will not be repeated here.

[0201] In a possible implementation, the acquisition unit 110 is specifically used to acquire the driver's historical dangerous driving behavior data and historical dangerous scene data within a preset historical time period; obtain the number of times the driver has each dangerous driving behavior within the historical time period based on the driver's historical dangerous driving data, and obtain the number of times the driver has each dangerous scene within the historical time period based on the driver's historical dangerous scene data; and obtain the correspondence between the number of times the dangerous driving behavior occurs and the actual number of times the dangerous scene occurs based on the number of times the driver has each dangerous driving behavior within the historical time period and the number of times the driver has each dangerous scene within the historical time period.

[0202] Optionally, the warning information includes the predicted number of times the driver will encounter each dangerous scenario within the current time period.

[0203] In one possible implementation, the above-mentioned determination unit 130 is specifically used to determine the probability of being warned for each dangerous scenario based on the predicted number of times the driver will encounter each dangerous scenario in the current time period; based on the probability of being warned for each dangerous scenario, determine at least one dangerous scenario to be warned, and the warning information includes at least one dangerous scenario to be warned.

[0204] In a possible implementation, the determination unit 130 is specifically configured to generate a random number; and determine at least one dangerous scene to be warned according to the warning probability of each dangerous scene and the random number.

[0205] In one possible implementation, the above-mentioned determination unit 130 is specifically used to determine the k+1th dangerous scenario as the dangerous scenario to be warned when the random number is greater than the sum of the warning probabilities of the first k dangerous scenarios and is less than or equal to the sum of the warning probabilities of the first k+1 dangerous scenarios; and to determine the kth dangerous scenario as the dangerous scenario to be warned when the random number is greater than a first numerical value and is less than or equal to the sum of the warning probabilities of the first k dangerous scenarios; wherein, when k is greater than 1, the first numerical value is the sum of the warning probabilities of the first k-1 dangerous scenarios, and when k is equal to 1, the first numerical value is 0.

[0206] In a possible implementation, the acquisition unit 110 is specifically used to obtain a driver image captured by a first vehicle-mounted camera within a current time period; identify each dangerous driving behavior of the driver in the driver image according to a preset type of dangerous driving behavior; and obtain first dangerous driving behavior data based on each identified dangerous driving behavior of the driver.

[0207] In a possible implementation, the acquisition unit 110 is specifically used to obtain first dangerous driving behavior data of the driver in a current time period from a second vehicle-mounted camera, wherein the second vehicle-mounted camera is used to capture images of the driver, and perform dangerous driving behavior identification on the captured driver images according to a preset type of dangerous driving behavior to generate first dangerous driving behavior data.

[0208] Optionally, the duration of the current time period is the duration for the first vehicle-mounted camera to capture the driver's image.

[0209] The driving risk warning device of the embodiment of the present application can be used to execute the technical solutions of the above-mentioned method embodiments. Its implementation principles and technical effects are similar and will not be repeated here.

[0210] Fig.11 A schematic diagram of a structure of a device for predicting dangerous driving behavior provided in an embodiment of the present application. The prediction device may be an electronic device or a component of an electronic device (e.g., an integrated circuit, a chip, etc.). The electronic device may be Figure 2 The computing device shown. Fig.11 As shown, the prediction device 300 may include: an acquisition unit 310 , a prediction unit 320 and a determination unit 330 .

[0211] The acquisition unit 310 is used to acquire first dangerous scene data occurring in the vehicle within a first time period, and to acquire a corresponding relationship between the number of occurrences of dangerous driving behaviors and the actual number of occurrences of dangerous scenes.

[0212] The prediction unit 320 is used to predict the number of occurrences of each dangerous driving behavior of the driver in the first time period according to the number of occurrences of each dangerous scene in the first dangerous scene data and the corresponding relationship.

[0213] The determination unit 330 is used to generate prediction information according to the number of times each dangerous driving behavior of the driver occurs within the first time period.

[0214] The device for predicting dangerous driving behavior in the embodiment of the present application can be used to execute the technical solution of the above-mentioned dangerous driving behavior prediction method embodiment, and its implementation principle and technical effect are similar and will not be repeated here.

[0215] Fig.12 is a block diagram of a computing device involved in an embodiment of the present application, which may be Figure 2 The computing device shown is used to execute the driving risk warning method described in the above embodiment. Please refer to the description in the above method embodiment for details.

[0216] Fig.12The computing device 200 shown includes a memory 201, a processor 202, and a communication interface 203. The memory 201, the processor 202, and the communication interface 203 are communicatively connected to each other. For example, the memory 201, the processor 202, and the communication interface 203 can be communicatively connected by a network connection. Alternatively, the computing device 200 may further include a bus 204. The memory 201, the processor 202, and the communication interface 203 are communicatively connected to each other via the bus 204. Fig.12 The computing device 200 is a memory 201 , a processor 202 , and a communication interface 203 that are communicatively connected to each other via a bus 204 .

[0217] The memory 201 may be a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM). The memory 201 may store a program. When the program stored in the memory 201 is executed by the processor 202, the processor 202 and the communication interface 203 are used to execute the above-mentioned early warning method.

[0218] The processor 202 may be a general-purpose central processing unit (CPU), a microprocessor, an application specific integrated circuit (ASIC), a graphics processing unit (GPU), or one or more integrated circuits.

[0219] The processor 202 may also be an integrated circuit chip with signal processing capability. In the implementation process, the early warning method of the present application may be completed by an integrated logic circuit of hardware in the processor 202 or by instructions in the form of software. The above-mentioned processor 202 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 201, and the processor 202 reads the information in the memory 201, and completes the early warning method of the embodiment of the present application in combination with its hardware.

[0220] The communication interface 203 uses a transceiver module such as, but not limited to, a transceiver to implement communication between the computing device 200 and other devices or a communication network. For example, a data set can be obtained through the communication interface 203 .

[0221] When the computing device 200 described above includes a bus 204 , the bus 204 may include a path for transmitting information between various components of the computing device 200 (eg, the memory 201 , the processor 202 , and the communication interface 203 ).

[0222] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrated. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.

[0223] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. In addition, various method embodiments and various device embodiments can also refer to each other, and the same or corresponding contents in different embodiments can be quoted from each other without repeated description.

Claims

1. A driving risk warning method, characterized in that: include: Acquire first dangerous driving behavior data of the driver in a current time period, and acquire a correspondence between the number of occurrences of M types of dangerous driving behaviors and the actual number of occurrences of N types of dangerous scenes, wherein the first dangerous driving behavior data is obtained by analyzing driver images collected in the current time period, and the first dangerous driving behavior data includes the number of occurrences of each of the M types of dangerous driving behaviors by the driver in the current time period, and the correspondence is a matrix of N rows and M columns or a matrix of M rows and N columns, and both M and N are positive integers greater than 1; Performing matrix operations based on the number of occurrences of each dangerous driving behavior in the first dangerous driving behavior data and the corresponding relationship to predict the number of occurrences of each dangerous scenario by the driver in the current time period; According to the predicted number of times each dangerous scenario will occur to the driver in the current time period, a warning message is generated.

2. The method according to claim 1, characterized in that The obtaining of the correspondence between the number of occurrences of the M types of dangerous driving behaviors and the actual number of occurrences of the N types of dangerous scenarios includes: Acquire historical dangerous driving behavior data and historical dangerous scene data of the driver within a preset historical time period; According to the historical dangerous driving data of the driver, obtaining the number of times the driver has performed each dangerous driving behavior in the historical time period; According to the historical dangerous scene data of the driver, obtaining the number of times each dangerous scene occurred to the driver within the historical time period; According to the number of times the driver commits each dangerous driving behavior in the historical time period and the number of times the driver commits each dangerous scene in the historical time period, the corresponding relationship between the number of occurrences of the M dangerous driving behaviors and the actual number of occurrences of the N dangerous scenes is obtained.

3. The method according to claim 1 or 2, characterized in that: The warning information includes the predicted number of times the driver will encounter each dangerous scenario within the current time period.

4. The method according to claim 1 or 2, characterized in that: The generating of warning information according to the predicted number of times each dangerous scenario will occur to the driver in the current time period includes: Determining the probability of being warned of each of the dangerous scenarios according to the predicted number of times the driver will encounter each of the dangerous scenarios in the current time period; At least one dangerous scene to be warned is determined according to the probability of being warned of each dangerous scene, and the warning information includes the at least one dangerous scene to be warned.

5. The method according to claim 4, characterized in that The step of determining at least one dangerous scene to be warned according to the warning probability of each dangerous scene comprises: Generate a random number; At least one dangerous scene to be warned is determined according to the probability of being warned of each dangerous scene and the random number.

6. The method according to claim 5, characterized in that The step of determining at least one dangerous scene to be warned according to the probability of being warned of each dangerous scene and the random number comprises: If the random number is greater than the sum of the warning probabilities of the first k dangerous scenarios and less than or equal to the sum of the warning probabilities of the first k+1 dangerous scenarios, the k+1th dangerous scenario is determined as the dangerous scenario to be warned; When the random number is greater than the first value and less than or equal to the sum of the warning probabilities of the first k dangerous scenes, the kth dangerous scene is determined as the dangerous scene to be warned; Among them, when k is greater than 1, the first value is the sum of the warning probabilities of the first k-1 dangerous scenarios, and when k is equal to 1, the first value is 0.

7. The method according to claim 1 or 2, characterized in that: The obtaining of the first dangerous driving behavior data of the driver in the current time period includes: Obtaining a driver image captured by the first vehicle-mounted camera within a current time period; According to the preset types of the dangerous driving behaviors, identifying each of the dangerous driving behaviors performed by the driver in the driver image; The first dangerous driving behavior data is obtained according to each of the identified dangerous driving behaviors of the driver.

8. The method according to claim 1 or 2, characterized in that: The obtaining of the first dangerous driving behavior data of the driver in the current time period includes: The first dangerous driving behavior data of the driver in the current time period is obtained from a second vehicle-mounted camera, the second vehicle-mounted camera is used to capture the driver's image, and perform dangerous driving behavior identification on the captured driver image according to a preset type of the dangerous driving behavior to generate the first dangerous driving behavior data.

9. The method according to claim 7, characterized in that: The duration of the current time period is the duration during which the first vehicle-mounted camera captures the driver image.

10. A driving risk warning device, characterized in that: include: an acquisition unit, used to acquire first dangerous driving behavior data of the driver in a current time period, and acquire a correspondence between the number of occurrences of M kinds of dangerous driving behaviors and the actual number of occurrences of N kinds of dangerous scenes, wherein the first dangerous driving behavior data is obtained by analyzing driver images collected in the current time period, and the first dangerous driving behavior data includes the number of occurrences of each of the M kinds of dangerous driving behaviors of the driver in the current time period, and the correspondence is a matrix of N rows and M columns or a matrix of M rows and N columns, and both M and N are positive integers greater than 1; a prediction unit, configured to perform matrix operations based on the number of occurrences of each dangerous driving behavior in the first dangerous driving behavior data and the corresponding relationship, and predict the number of occurrences of each dangerous scenario by the driver in a current time period; The determination unit is used to generate warning information according to the predicted number of times each dangerous scenario occurs to the driver in the current time period.

11. A computing device, characterized in that: include: Memory, processor; The memory is used to store computer programs; The processor is used to execute the computer program to implement the driving risk warning method as described in any one of claims 1 to 9 above.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the driving risk warning method as described in any one of claims 1 to 9.

Images