Method, apparatus, device, and storage medium for predicting traffic accidents

Abstract

Provided are a method, apparatus, device, and storage medium for predicting traffic accidents. The method includes: obtaining the historical probability of a target vehicle based on historical traffic accidents on a target road; determining at least one first proportion corresponding to at least one monitorable factor; determining a first probability based on the historical probability and the at least one first proportion; and determining a prediction probability of the target vehicle based on the first probability, where the prediction probability is used to represent the likelihood of the target vehicle having a traffic accident on the target road. The method may involve technologies such as artificial intelligence for autonomous driving or assisted driving. The method can not only improve the accuracy of accident prediction, facilitate the improvement of the warning effect, but also reduce the implementation complexity and enhance the timeliness and practicality of prediction and warning.

Description

Technical Field

[0001] Embodiments of the present application relate to technical fields such as autonomous driving in artificial intelligence, and more specifically, to methods, devices, equipment, and storage media for predicting traffic accidents. Background Art

[0002] The effective control of safety risks is one of the signs that the entire road freight industry has matured. In the field of safety-assisted driving, there are extremely high driving risks lurking in large truck fleets. How to perform dynamic early warning on large trucks is one of the key issues faced by the implementation of vehicle-road collaboration.

[0003] In related technologies, an early warning system can obtain the historical probability of traffic accidents involving large trucks on the current road section where the large truck is located from a traffic management system, and directly use it as the prediction probability that the large truck will be involved in a traffic accident again when driving on the current road section where it is located, so as to achieve dynamic early warning of large trucks. Although using the historical probability as the prediction probability can achieve dynamic early warning of large trucks, the prediction accuracy is too low to reach the expected early warning effect. Summary of the Invention

[0004] Provided are a method, a device, equipment, and a storage medium for predicting traffic accidents, which can not only improve the accuracy of accident prediction, be beneficial to improving the early warning effect, but also reduce the implementation complexity, and improve the timeliness and practicality of prediction and early warning.

[0005] In a first aspect, a method for predicting traffic accidents is provided. In some possible implementation manners, the method includes:

[0006] Obtaining the historical probability of a target vehicle based on historical traffic accidents on a target road;

[0007] Determining at least one first proportion corresponding to at least one monitorable factor, where the at least one monitorable factor is a factor that can trigger a traffic accident of the target vehicle monitored by a roadside device, and the at least one first proportion is the proportion of traffic accidents triggered by the at least one monitorable factor in the historical traffic accidents;

[0008] Determining a first probability based on the historical probability and the at least one first proportion;

[0009] Determining the prediction probability of the target vehicle based on the first probability, where the prediction probability is used to represent the possibility that the target vehicle will have a traffic accident on the target road.

[0010] Based on the historical probability and at least one first proportion corresponding to at least one monitorable factor respectively, determine a first probability, and based on this first probability, determine the prediction probability; on the one hand, the historical probability can reflect the average level of traffic accidents occurring on the target road; on the other hand, by determining the first probability through the at least one first proportion and then determining the prediction probability based on the first probability, it can not only predict the possibility of a traffic accident occurring to the target vehicle, but also reduce the complexity of adjusting the historical probability based on the at least one monitorable factor.

[0011] In addition, since the probabilities of different monitorable factors triggering a traffic accident for the target vehicle may vary, based on this historical probability, in combination with the first proportion corresponding to each monitorable factor in the at least one monitorable factor, determine the first probability, and based on this first probability, determine the prediction probability; equivalently, considering the differences in the probabilities of different monitorable factors triggering a traffic accident for the target vehicle, correspondingly, the accuracy of accident prediction can be improved, which is beneficial to enhancing the early warning effect.

[0012] Moreover, since the actual situation of the at least one monitorable factor can be obtained through real-time monitoring, it is beneficial to improve the timeliness and practicality of prediction and early warning.

[0013] In summary, based on the historical probability and at least one first proportion corresponding to at least one monitorable factor respectively, determine the prediction probability of the target vehicle, which can not only improve the accuracy of accident prediction, be beneficial to enhancing the early warning effect, but also reduce the implementation complexity and improve the timeliness and practicality of prediction and early warning.

[0014] In some possible implementation manners, the determining the prediction probability of the target vehicle based on the first probability includes:

[0015] Determine the difference between 1 and the first probability as the prediction probability.

[0016] Construct the difference between 1 and the first probability as the prediction probability. Equivalently, transform the influence of the at least one monitorable factor on the traffic accident into the probability that none of the at least one monitorable factors trigger a traffic accident for the target vehicle. That is, taking the at least one monitorable factor as the granularity, using the probability theory of mutually exclusive events, determine the probability of the opposite event that none of the at least one monitorable factors trigger a traffic accident as the prediction probability, which can consider the probability of traffic accidents triggered by each monitorable factor as much as possible. Correspondingly, it can ensure the accuracy of accident prediction.

[0017] The determining the first probability based on the historical probability and at least one first proportion includes:

[0018] Based on the historical probability and the at least one first proportion, determine at least one second probability corresponding to the at least one monitorable factor, where the second probability corresponding to the same monitorable factor among the at least one monitorable factor is used to represent the possibility that the same monitorable factor does not trigger a traffic accident of the target vehicle;

[0019] Determine the first probability based on the at least one second probability.

[0020] In some possible implementation manners, the determining at least one second probability based on the historical probability and the at least one first proportion includes:

[0021] Determine at least one change amount based on the at least one first proportion, where the at least one change amount is the change amount of the at least one first proportion relative to the first average proportion respectively;

[0022] Add 1 to each of the at least one change amount to generate at least one weight corresponding to the at least one monitorable factor respectively;

[0023] Multiply each of the at least one weight by the historical probability to generate at least one third probability corresponding to the at least one monitorable factor respectively, where the third probability corresponding to the same monitorable factor among the at least one monitorable factor is used to represent the possibility that the same monitorable factor triggers a traffic accident of the target vehicle;

[0024] Use 1 to subtract each of the at least one third probability to generate at least one second probability.

[0025] In some possible implementation manners, the method further includes:

[0026] Obtain the distribution of the surrounding vehicles of the target vehicle through a road monitoring system;

[0027] Wherein, the determining the first probability based on the at least one second probability includes:

[0028] Determine the first probability based on the at least one second probability and the distribution of the surrounding vehicles of the target vehicle.

[0029] In some possible implementation manners, the determining the first probability based on the at least one second probability and the distribution of the surrounding vehicles of the target vehicle includes:

[0030] Based on the distribution of the surrounding vehicles of the target vehicle, determine the number of vehicles corresponding to each monitorable factor among the at least one monitorable factor;

[0031] Based on the at least one second probability and the number of vehicles corresponding to each monitorable factor among the at least one monitorable factor, determine at least one fourth probability corresponding to each of the at least one monitorable factor, and the fourth probability corresponding to the same monitorable factor among the at least one monitorable factor is used to represent the possibility that the same monitorable factor triggers traffic accidents for both the target vehicle and all vehicles corresponding to the same monitorable factor;

[0032] Determine the product of the at least one fourth probability as the first probability.

[0033] Obtain the distribution of the surrounding vehicles of the target vehicle through a road monitoring system. On the basis of considering the differences between the probabilities of traffic accidents triggered by different monitorable factors, the vehicles that may have traffic accidents with the target vehicle involved in each monitorable factor are considered. Equivalently, whether the target vehicle meets the conditions for a traffic accident is considered. Thus, the accuracy of accident prediction can be further improved.

[0034] In some possible implementation manners, the at least one monitorable factor includes at least one type of driving blind area; along the driving direction of the target vehicle, the at least one type of driving blind area includes at least one of the following: front blind area, rear blind area, left blind area or right blind area; or, the at least one type of driving blind area includes a full blind area or a semi-blind area.

[0035] Based on the historical probability and the first proportion corresponding to each driving blind area in at least one type of driving blind area, determine a prediction probability. On the one hand, the driving blind area is the main factor triggering traffic accidents, especially for vehicles with a long body and a large vehicle height. By detecting the actual situation of each driving blind area of the target vehicle, it can help the driver monitor the vehicle conditions in the blind area. By considering the differences between the probabilities of different driving blind areas triggering traffic accidents for the target vehicle, the accuracy of accident prediction can be further improved.

[0036] In some possible implementation manners, the method further includes:

[0037] Determine at least one second proportion corresponding to each of at least one non-monitorable factor;

[0038] Determine a target proportion among the at least one second proportion;

[0039] Adjust the prediction probability based on the target proportion.

[0040] In some possible implementation manners, the adjusting the prediction probability based on the target proportion includes:

[0041] Determine a target change amount based on the target proportion, where the target change amount is the change amount of the target proportion relative to the second average proportion;

[0042] Add 1 to the target change amount respectively to generate target weights;

[0043] Determine the product of the predicted probability and the target weight as the adjusted probability.

[0044] Similar to the monitorable factors, the probabilities of different unmonitorable factors triggering traffic accidents for the target vehicle may vary. Adjusting the predicted probability by the target proportion can further consider the impact of unmonitorable factors on traffic accidents on the basis of considering monitorable factors. In particular, for some unmonitorable factors that are particularly important for the probability of traffic accidents, the accuracy of accident prediction can be further improved.

[0045] In some possible implementations, determining the target proportion among the at least one second proportion includes:

[0046] Obtain a random variable uniformly distributed in the interval [0, 1];

[0047] Determine the target proportion among the at least one second proportion based on the random variable.

[0048] In some possible implementations, adjusting the predicted probability based on the target proportion includes:

[0049] Determine the second proportion greater than or equal to the random variable among the at least one second proportion as the target proportion; or

[0050] Determine the second proportion less than the random variable among the at least one second proportion as the target proportion.

[0051] In some possible implementations, adjusting the predicted probability based on the target proportion includes:

[0052] Determine the target interval The random variable is within the target interval, w i Represents the second proportion corresponding to the i-th unmonitorable factor among the at least one unmonitorable factor;

[0053] Determine the second proportion corresponding to the k-th unmonitorable factor among the at least one unmonitorable factor as the target proportion.

[0054] In some possible implementations, the at least one unmonitorable factor includes at least one type of driving behavior, and the at least one type of driving behavior includes at least one of the following behaviors: aggressive driving, fatigue driving, distracted driving, or dangerous driving.

[0055] In a second aspect, a device for predicting traffic accidents is provided, including:

[0056] An acquisition unit, configured to acquire the historical probability of the target vehicle based on historical traffic accidents on the target road;

[0057] A first determination unit, configured to determine at least one first proportion corresponding to at least one monitorable factor, where the at least one monitorable factor is a factor that can trigger a traffic accident of the target vehicle monitored by roadside equipment, and the at least one first proportion is the proportion of traffic accidents triggered by the at least one monitorable factor in the historical traffic accidents;

[0058] A second determination unit, configured to determine a first probability based on the historical probability and the at least one first proportion, where the first probability is the probability that none of the at least one monitorable factors triggers a traffic accident of the target vehicle;

[0059] A third determination unit, configured to determine the prediction probability of the target vehicle based on the first probability, where the prediction probability is used to represent the possibility of the target vehicle having a traffic accident on the target road.

[0060] In a third aspect, a terminal device is provided, including:

[0061] A processor and a memory, where the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the first aspect.

[0062] In a fourth aspect, a computer-readable storage medium is provided, which is used to store a computer program, and the computer program enables a computer to execute the method in the first aspect. Description of the Drawings

[0063] Figure 1 is a schematic block diagram of the system framework provided by the embodiments of the present application.

[0064] Figure 2 is a schematic flowchart of predicting traffic accidents provided by the embodiments of the present application.

[0065] Figures 3 to 5 is a schematic diagram of a target vehicle with at least one type of driving blind area provided by the embodiments of the present application.

[0066] Figure 6 is another schematic diagram of a target vehicle with at least one type of driving blind area provided by the embodiments of the present application.

[0067] Figure 7 and Figure 8 both are Figure 6 schematic diagrams of the target vehicle driving on the target road shown.

[0068] Figure 9 is a schematic block diagram of the device for predicting traffic accidents provided by the embodiments of the present application.

[0069] Figure 10 It is a schematic block diagram of a terminal device provided by an embodiment of the present application. Detailed implementation manners

[0070] Next, the technical solutions in the embodiments of the present application will be described with reference to the accompanying drawings.

[0071] It should be noted that the solution for predicting traffic accidents provided by the present application can be applied to any scenario that requires controlling vehicle safety risks.

[0072] For example, the solution for predicting traffic accidents provided by the present application may involve artificial intelligence technology.

[0073] Among them, artificial intelligence (AI) is to use a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results in terms of theory, method, technology, and application system. In other words, artificial intelligence is a comprehensive technology in computer science. It attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a way similar to human intelligence. Artificial intelligence is also to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning, and decision-making.

[0074] It should be understood that artificial intelligence technology is an interdisciplinary subject, involving a wide range of fields, including both hardware-level technologies and software-level technologies. The basic technologies of artificial intelligence generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, and mechatronics. The software technologies of artificial intelligence mainly include several major directions such as computer vision technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0075] With the research and progress of artificial intelligence technology, artificial intelligence technology has been studied and applied in multiple fields. For example, common ones include smart home, smart wearable devices, virtual assistants, smart speakers, smart marketing, driverless, autonomous driving, drones, robots, smart healthcare, smart customer service, etc. It is believed that with the development of technology, artificial intelligence technology will be applied in more fields and play an increasingly important role.

[0076] The solution for predicting traffic accidents provided by the present application may involve artificial intelligence-based autonomous driving technology or assisted driving technology, etc.

[0077] For example, the method for predicting traffic accidents in this application can be an autonomous driving technology. Based on this, the probability of a vehicle being involved in a traffic accident can be reduced during autonomous driving through the method provided in this application, thereby enhancing safety. Among them, autonomous driving technology can include technologies such as high-precision maps, environmental perception, behavior decision-making, path planning, and motion control. Autonomous driving technology has broad application prospects. Another example is that the method for predicting traffic accidents in this application can be an assisted driving technology. Based on this, the method provided in this application can assist the driver in driving the vehicle to reduce the probability of the vehicle being involved in a traffic accident, thereby enhancing safety.

[0078] In addition, the solution for predicting traffic accidents provided in this application is involved in various network frameworks, such as the Internet of Things (IOT) applied to the transportation industry or Cloud IOT applied to the transportation industry. The Internet of Things applied to the transportation industry can also be referred to as the vehicle network.

[0079] The Internet of Things refers to the use of various information sensors, radio frequency identification technologies, global positioning systems, infrared sensors, laser scanners and other devices and technologies to collect any objects or processes that need to be monitored, connected, and interacted in real time, and collect various information such as their sound, light, heat, electricity, mechanics, chemistry, biology, and location. Through various possible network accesses, it realizes the ubiquitous connection of things to things and things to people, and realizes the intelligent perception, identification, and management of items and processes. The Internet of Things is an information carrier based on the Internet, traditional telecommunications networks, etc. It enables all ordinary physical objects that can be independently addressed to form an interconnected network.

[0080] Cloud IOT aims to connect the information sensed by sensing devices and the received instructions in the traditional Internet of Things to the Internet, truly realizing networking, and realizing massive data storage and operation through cloud computing technology. Since the characteristic of the Internet of Things is the connection of things to things, and it can sense the current operating status of each "object" in real time, a large amount of data information will be generated in this process. How to summarize these information and how to screen useful information from the massive information for decision-making support in the subsequent development have become key issues affecting the development of the Internet of Things. Therefore, the Internet of Things Cloud based on cloud computing and cloud storage technologies has also become a powerful support for Internet of Things technologies and applications.

[0081] Figure 1 This is an example of the system framework 100 provided by the embodiments of this application.

[0082] As Figure 1 shown, the system framework 100 may include a traffic management system 101, a road monitoring system 102, an early warning system 103, and a vehicle 104. It should be noted that Figure 1The numbers of the traffic management system 101, the road monitoring system 102, the early warning system 103, and the vehicle 104 in it are only illustrative. According to the implementation requirements, there can be any number of traffic management systems 101, road monitoring systems 102, early warning systems 103, and vehicles 104.

[0083] Among them, the traffic management system 101 can be used to manage the driving information of the vehicle 104. For example, the statistical information of vehicle accidents on a certain section of the road, and again, the registration information of the vehicle 104. The road monitoring system 102 can be used to monitor the vehicle 104. For example, the road monitoring system 102 can be used to monitor the vehicles passing through a specific section in real time. The early warning system 103 can be used to predict the possibility of a vehicle accident for the vehicle 104, and then prompt the user with a warning message indicating that there is a risk of a vehicle accident for the vehicle 104. The traffic management system 101 can be connected to the road monitoring system 102, the early warning system 103, and the vehicle 104 through a network to receive or send messages.

[0084] In some embodiments of the present application, the traffic management system 101 can count or summarize the traffic accidents on a certain section of the road. For example, the traffic management system 101 can count or summarize the following information about the traffic accidents on a certain section of the road: vehicle models, factors causing vehicle accidents, and collision locations, etc. The traffic management system 101 can include any device or equipment with data processing capabilities in the traffic management database, or the traffic management system 101 can be a traffic management cloud platform.

[0085] In some embodiments of the present application, the road monitoring system 102 can monitor the vehicle 104 in real time through roadside devices. In other words, the road detection system 102 can include various types of roadside devices. The roadside devices can be installed on the roadside, and the roadside devices can be intelligent cameras, or any other device with shooting and computing capabilities installed on the roadside.

[0086] In some embodiments of the present application, the early warning system 103 is the execution body of the method for predicting traffic accidents provided in the embodiments of the present application, and is used to generate a warning notice for vehicle driving risks. Correspondingly, the prediction device for vehicle driving risks can be set in the early warning system 103. The early warning system 103 can be any device or equipment with computing functions, such as a smart phone, a tablet computer, a portable computer, a desktop computer, etc., and again, a vehicle networking cloud platform.

[0087] The vehicle 104 can be any type of vehicle, such as a truck, a lorry, or a sedan, etc. The vehicle 104 can be connected to the traffic management system 101, the road monitoring system 102, or the early warning system 103 via a network to receive or send messages. For example, the early warning system 103 can output a warning notice of the generated driving risk of the vehicle to the target vehicle 103.

[0088] It should be understood that the terms "system" and "network" can be used interchangeably herein.

[0089] Figure 2 It is a schematic flowchart of a method 200 for predicting traffic accidents provided by an embodiment of the present application. It should be understood that the method 200 can be executed by an early warning system or an early warning device. For example Figure 1 the early warning system 103 shown.

[0090] As Figure 2 shown, the method 200 may include:

[0091] S211, obtaining the historical probability of the target vehicle based on historical traffic accidents on the target road.

[0092] S212, determining at least one first proportion corresponding to at least one monitorable factor, where the at least one monitorable factor is a factor that can trigger a traffic accident of the target vehicle monitored by roadside equipment, and the at least one first proportion is the proportion of traffic accidents triggered by the at least one monitorable factor in the historical traffic accidents.

[0093] S213, determining a first probability based on the historical probability and the at least one first proportion.

[0094] S214, determining a prediction probability of the target vehicle based on the first probability, where the prediction probability is used to represent the possibility of the target vehicle having a traffic accident on the target road.

[0095] For example, the early warning system can obtain the historical probability and the at least one first proportion from the traffic management system, and determine the first probability based on the historical probability and the at least one first proportion, so as to determine the prediction probability based on the first probability. Optionally, the target vehicle can be Figure 1 the vehicle 104 shown. Optionally, the prediction probability can be used to generate a warning message. For example, when the prediction probability is greater than or equal to a certain threshold, the early warning system can send a warning message to the target vehicle or a vehicle that may have a traffic accident with the target vehicle.

[0096] In other words, the historical probability serves as a preliminary prediction probability of the target vehicle having a traffic accident, and the at least one first proportion is used to adjust the historical probability to determine the first probability.

[0097] Based on the historical probability and at least one first proportion corresponding to at least one monitorable factor respectively, determine a first probability, and determine a predicted probability based on the first probability; on the one hand, the historical probability can reflect the average level of traffic accidents occurring on the target road; on the other hand, determining the first probability based on the first proportion corresponding to each monitorable factor among the at least one monitorable factor, and then determining the predicted probability based on the first probability can not only predict the possibility of a traffic accident occurring to the target vehicle, but also reduce the complexity of adjusting the historical probability based on the at least one monitorable factor.

[0098] In addition, since the probabilities of different monitorable factors triggering traffic accidents to the target vehicle may vary, based on the historical probability, combining the first proportion corresponding to each monitorable factor among the at least one monitorable factor to determine the first probability, and determining the predicted probability based on the first probability is equivalent to considering the differences between the probabilities of different monitorable factors triggering traffic accidents to the target vehicle. Correspondingly, the accuracy of accident prediction can be improved, which is beneficial to improving the early warning effect.

[0099] In addition, since the actual situation of the at least one monitorable factor can be obtained through real-time monitoring, it is beneficial to improve the timeliness and practicality of prediction and early warning.

[0100] In summary, determining the predicted probability of the target vehicle based on the historical probability and at least one first proportion corresponding to at least one monitorable factor respectively can not only improve the accuracy of accident prediction, be beneficial to improving the early warning effect, but also reduce the implementation complexity and improve the timeliness and practicality of prediction and early warning.

[0101] The accuracy of predicting traffic accidents in the present application will be described below with reference to the experimental results in Table 1.

[0102] Table 1

[0103]

[0104] As shown in Table 1, the accuracy rate of predicting traffic accidents in the present application can be reflected by the false alarm ratio between the first scheme and the second scheme and the missed alarm ratio between the first scheme and the second scheme. Among them, the first scheme can be understood as a scheme for giving early warnings directly based on the historical probability, and the second scheme can be understood as a scheme for giving early warnings based on the predicted probability. That is, the scheme provided by the present application can be used as the second scheme. The false alarm ratio between the first scheme and the second scheme can be understood as the ratio between the false alarms of the first scheme and the false alarms of the second scheme. The missed alarm ratio between the first scheme and the second scheme can be understood as the ratio between the missed alarms of the first scheme and the missed alarms of the second scheme. It can be seen from Table 1 that the ratios of false alarms and missed alarms of the first scheme are respectively greater than those of the second scheme. That is to say, determining the predicted probability of the target vehicle based on the historical probability and at least one first proportion corresponding to at least one monitorable factor can not only improve the accuracy of accident prediction, but also help to improve the early warning effect.

[0105] It should be noted that the historical probability in the present application aims to reflect the average level of the target type of vehicle being involved in a traffic accident again when driving on the target road. The target vehicle belongs to the target type of vehicle. The present application does not limit the specific definition of the historical probability. For example, the historical probability is the traffic accident rate that occurs on the target road and involves the target type of vehicle. The historical probability can also be called the historical accident incidence rate. For another example, the historical probability can be the proportion of traffic accidents that occur on the target road and involve the target type of vehicle in the statistically traffic accidents. For another example, the historical probability can be the proportion of the target type of vehicle that has had a traffic accident on the target road in the statistically target type of vehicles.

[0106] In addition, the at least one first proportion aims to reflect the influence degree of the at least one monitorable factor on traffic accidents. For example, the at least one first proportion can also be called at least one weight. For example, the at least one first proportion can be understood as the proportion of traffic accidents triggered by the at least one monitorable factor as the main factor in the statistically traffic accidents.

[0107] In addition, the at least one monitorable factor is intended to reflect the factors that affect the probability of a traffic accident occurring. In other words, the at least one monitorable factor may trigger a traffic accident involving the target vehicle. For example, each of the at least one monitorable factors corresponds to a vehicle that may be involved in a traffic accident with the target vehicle. As another example, the at least one monitorable factor may be different classifications of a single monitorable factor. Of course, the at least one monitorable factor may also be a combined factor for multiple monitorable factors, and the present application does not make specific limitations in this regard. For example, the at least one monitorable factor may be different classifications of a driving blind spot. For example, assuming that the at least one monitorable factor is at least one type of driving blind spot, there is a vehicle in each type of driving blind spot that may be involved in a traffic accident with the target vehicle. For example, the at least one monitorable factor may also include other factors. For example, time period, congestion level, driver gender, category of the target road section, etc. The category of the target road section may include a straight road section, a T-junction, or a crossroads, etc.

[0108] In addition, the traffic accident in the present application can be understood not only as a collision between the target vehicle and other vehicles, but also as a collision between the target vehicle and any object or pedestrian.

[0109] As an example, the at least one monitorable factor may include at least one type of driving blind spot. Optionally, along the driving direction of the target vehicle, the at least one type of driving blind spot includes at least one of the following: front blind spot, rear blind spot, left blind spot, or right blind spot. Optionally, the at least one type of driving blind spot includes a full blind spot or a half blind spot.

[0110] Based on the historical probability and the first proportion corresponding to each driving blind spot in at least one type of driving blind spot, a prediction probability is determined. On the one hand, the driving blind spot is the most important factor triggering traffic accidents, especially for vehicles with a relatively long body and a relatively large vehicle height. By detecting the actual situation of each driving blind spot of the target vehicle, it can help the driver monitor the vehicle conditions in the blind spots. By considering the differences in the probabilities of different driving blind spots triggering traffic accidents involving the target vehicle, the accuracy of accident prediction can be further improved.

[0111] Figures 3 to 5 is a schematic diagram of a target vehicle having at least one type of driving blind spot provided by an embodiment of the present application. Figure 6 is another schematic diagram of a target vehicle having at least one type of driving blind spot provided by an embodiment of the present application.

[0112] The following combines Figures 3 to 6 to illustrate at least one type of driving blind spot in an embodiment of the present application.

[0113] As Figure 3As shown, the driving blind spots of vehicle 300 may include blind spot 310, blind spot 320, blind spot 321, blind spot 322, blind spot 323, blind spot 341, blind spot 342, and blind spot 343.

[0114] For example, blind spots 323 and 343 may be blind spots formed by the frame or side pillars of the windshield of the target vehicle 300. Optionally, blind spots 323 and 343 may be regarded as full blind spots.

[0115] For example, blind spots 321 and 341 may be areas outside the driver's line of sight and outside the line of sight of the rearview mirrors, which may include one rearview mirror inside the vehicle and two rearview mirrors outside the vehicle. Optionally, blind spots 321 and 341 may be regarded as full blind spots.

[0116] For example, blind spots 322 and 342 may be areas blocked by the car door. For example, as Figure 4 shown, due to the blockage of the car door, driver 350 cannot see pedestrian 352 in blind spot 322. Similarly, driver 350 also cannot see pedestrian 351 in blind spot 342. Optionally, blind spots 322 and 342 may be regarded as semi-blind spots.

[0117] For example, blind spot 310 may be an area blocked by the front of the vehicle. For example, as Figure 5 shown, due to the blockage of the front of the vehicle, the driver cannot see pedestrian 353 in blind spot 310. Optionally, blind spot 310 may be regarded as a semi-blind spot.

[0118] For example, blind spot 320 may be an area blocked by the carriage. Optionally, blind spot 320 may be regarded as a semi-blind spot.

[0119] As Figure 6 shown, the driving blind spots of vehicle 300 may include front blind spot 410, rear blind spot 420, left blind spot 430, and right blind spot 440.

[0120] For example, the blind spots shown in Figures 3 to 5 may be divided into front blind spot 410, rear blind spot 420, left blind spot 430, and right blind spot 440. For example, the front blind spot 410 may include blind spot 310. For example, the rear blind spot 420 is blind spot 320. For example, the left blind spot 430 may include blind spots 321, 322, and 323. For example, the right blind spot 440 may include blind spots 341, 342, and 343. Of course, blind spots 323 and 343 may also be regarded as blind spots in the front blind spot 410 respectively.

[0121] It should be understood that Figures 3 to 6These are merely examples of this application and should not be construed as limitations on this application. For example, in other alternative embodiments, the blind areas 323 and 343 can also be used as optional blind areas.

[0122] It should also be understood that this application does not limit the specific sizes of each of the at least one type of driving blind area. As an example, the sizes of each type of driving blind area in the at least one type of driving blind area can be determined based on information such as the frame of the target vehicle 300, the vehicle size, and the driver's height. As an example, the blind area 310 can include 1.2 m directly in front of the front of the target vehicle 300 and 1.5 m in the right front. As an example, a blind area with a maximum vertical distance from the target vehicle greater than or equal to a certain threshold can be determined as a full blind area. Of course, other criteria can also be used to determine the full blind area or the semi-blind area.

[0123] In some embodiments of this application, the first probability is the probability that none of the at least one monitorable factor triggers a traffic accident for the target vehicle, and S214 may include:

[0124] Determine the difference between 1 and the first probability as the prediction probability.

[0125] In other words, the probability principle of mutually exclusive events can be used to determine the prediction probability based on the first probability.

[0126] Constructing the difference between 1 and the first probability as the prediction probability is equivalent to converting the influence of the at least one monitorable factor on the traffic accident into the probability that none of the at least one monitorable factor triggers a traffic accident for the target vehicle. That is, with the at least one monitorable factor as the granularity, using the probability theory of mutually exclusive events, the probability of the opposite event that none of the at least one monitorable factor triggers a traffic accident is determined as the prediction probability, which can consider the probability of traffic accidents triggered by each monitorable factor as much as possible. Correspondingly, the accuracy of accident prediction can be ensured.

[0127] In some embodiments of this application, S213 may include:

[0128] Based on the historical probability and the at least one first proportion, determine at least one second probability corresponding to each of the at least one monitorable factor. The second probability corresponding to the same monitorable factor among the at least one monitorable factor is used to represent the possibility that the same monitorable factor does not trigger a traffic accident for the target vehicle.

[0129] For example, the product of the at least one second probability can be determined as the first probability.

[0130] In some embodiments of this application, the at least one second probability can be determined by the following method:

[0131] Determine at least one change amount based on the at least one first proportion, where the at least one change amount is the change amount of the at least one first proportion relative to the first average proportion respectively; add 1 to each of the at least one change amount to generate at least one weight corresponding to each of the at least one monitorable factor; multiply each of the at least one weight by the historical probability to generate at least one third probability corresponding to each of the at least one monitorable factor, and the third probability corresponding to the same monitorable factor among the at least one monitorable factor is used to represent the possibility that the same monitorable factor triggers a traffic accident of the target vehicle; use 1 to subtract each of the at least one third probability to generate at least one second probability.

[0132] For example, the at least one second probability can be determined by the following formula:

[0133] p 2i = 1 - p h (1 + u i - 1 / m);

[0134] where p 2i represents the i-th second probability among the at least one second probability, m represents the number of the at least one monitorable factor, p h represents the historical probability, u i represents the first proportion corresponding to the i-th monitorable factor among the at least one monitorable factor, and c i represents the number of vehicles corresponding to the i-th monitorable factor among the at least one monitorable factor.

[0135] In some embodiments of the present application, the method 200 may further include:

[0136] Obtain the distribution of the surrounding vehicles of the target vehicle through a road monitoring system.

[0137] Based on this, the first probability can be determined based on the at least one second probability and the distribution of the surrounding vehicles of the target vehicle.

[0138] For example, the first probability can be determined in the following manner:

[0139] Based on the distribution of the surrounding vehicles of the target vehicle, determine the number of vehicles corresponding to each of the at least one monitorable factor; based on the at least one second probability and the number of vehicles corresponding to each of the at least one monitorable factor, determine at least one fourth probability corresponding to each of the at least one monitorable factor, and the fourth probability corresponding to the same monitorable factor among the at least one monitorable factor is used to represent the possibility that the same monitorable factor triggers traffic accidents of the target vehicle and all vehicles corresponding to the same monitorable factor; determine the product of the at least one fourth probability as the first probability.

[0140] For example, the first probability can be determined in the following manner:

[0141]

[0142] where p1 represents the first probability, ∏ represents the product operation, m represents the number of the at least one monitorable factor, p h represents the historical probability, and u i represents the first proportion corresponding to the i-th monitorable factor among the at least one monitorable factor, and c i represents the number of vehicles corresponding to the i-th monitorable factor among the at least one monitorable factor.

[0143] By obtaining the distribution of the surrounding vehicles of the target vehicle through a road monitoring system, and on the basis of considering the differences between the probabilities of traffic accidents triggered by different monitorable factors, the vehicles that may be involved in a traffic accident with the target vehicle involved in each monitorable factor are considered. Equivalently, whether the target vehicle meets the conditions for a traffic accident is considered. Thus, the accuracy of accident prediction can be further improved.

[0144] In other words, the prediction probability can be determined according to the following formula:

[0145]

[0146] where p p represents the prediction probability, ∏ represents the product operation, m represents the number of the at least one monitorable factor, p h represents the historical probability, and u i represents the first proportion corresponding to the i-th monitorable factor among the at least one monitorable factor, and c i represents the number of vehicles corresponding to the i-th monitorable factor among the at least one monitorable factor.

[0147] Next, taking the at least one monitorable factor as at least one type of driving blind area as an example, the solution of the present application will be described.

[0148] The warning system preliminarily predicts the probability that the target vehicle is involved in a traffic accident due to surrounding vehicles: For example, the warning system obtains from the traffic management system the historical probability of vehicles of the type to which the target vehicle belongs being involved in traffic accidents on the current road, and this probability can be denoted as p h .

[0149] In addition, the warning system respectively denotes the at least one first proportion corresponding to the at least one type of driving blind area as u1, u2,..., u m, where m represents the number of at least one type of driving blind spot, and the m blind spots are respectively called blind spot 1, 2, ..., m. The classification of driving blind spots can be determined according to specific circumstances. For example, it can be based on the blind spot classification and the proportion of each type obtained from the traffic management system. Through u1, u2, ..., u m Quantify the influence degree of the at least one type of blind spot on the occurrence of traffic accidents for the target vehicle. That is, the higher the proportion of traffic accidents, the higher the degree of attention that the driving blind spot should receive, which can ensure the quantization accuracy of the at least one type of driving blind spot.

[0150] Subsequently, the warning system can be based on p h and u1, u2, ..., u m to determine the prediction probability.

[0151] For example, the warning system can obtain the proportion of traffic accidents caused by each driving blind spot relative to the first average proportion, that is, u1 - 1 / m, u2 - 1 / m, ..., u m - 1 / m; if other vehicles are located in the blind spots 1, 2, ..., m, the warning system can predict the probability of traffic accidents triggered by each type of driving blind spot, that is, p pre,1 = p h (1 + u1 - 1 / m), p pre,2 = p h (1 + u2 - 1 / m), ..., p pre,m = p h (1 + u m - 1 / m); further, the warning system can obtain the number of vehicles located in the blind spots 1, 2, ..., m of the target vehicle in real time from the road monitoring system, that is, c1, c2, ..., c m , thus, the probability of traffic accidents occurring between these vehicles and the target vehicle can be predicted as:

[0152]

[0153] In other words, can be used as the above first probability.

[0154] Figure 7 and Figure 8 are both Figure 6 the schematic diagrams of the target vehicle driving on the target road shown.

[0155] Such as Figure 7As shown in the figure, the target vehicle 300 is driving on the T-shaped road section 400. There is a vehicle 451 in the front blind area 410 that may collide with the target vehicle 300. There is a vehicle 453 in the rear blind area 420 that may collide with the target vehicle 300. There is a vehicle 452 in the left blind area 430 that may collide with the target vehicle 300. The vehicle 454 is not in the right blind area 440, that is, there is no vehicle in the right blind area 440 that may collide with the target vehicle 300.

[0156] In other words, the predicted probability can be expressed as:

[0157] p p = 1 - (1 - p pre,410 ) 1 (1 - p pre,420 ) 1 (1 - p pre,430 ) 1 (1 - p pre,440 ) 0 .

[0158] Where p pre,410 , p pre,420 , p pre,430 , p pre,440 respectively represent the probabilities of traffic accidents triggered by the front blind area 410, the rear blind area 420, the left blind area 430, and the right blind area 440 for the target vehicle 300.

[0159] As Figure 8 shown in the figure, the target vehicle 300 is driving on the straight road section 450. There is a vehicle 455 in the front blind area 410 that may collide with the target vehicle 300. There is a vehicle 456 in the rear blind area 420 that may collide with the target vehicle 300. There is no vehicle in the left blind area 430 that may collide with the target vehicle 300. There is a vehicle 457 in the right blind area 440 that may collide with the target vehicle 300.

[0160] In other words, the predicted probability can be expressed as:

[0161] p p = 1 - (1 - p pre,410 ) 1 (1 - p pre,420 ) 1 (1 - p pre,430 ) 0 (1 - p pre,440 ) 1 .

[0162] Where p pre,410 , p pre,420 , p pre,430 , p pre,440respectively represent the probabilities of traffic accidents triggered by the target vehicle 300 when the front blind area 410, rear blind area 420, left blind area 430, and right blind area 440 are triggered.

[0163] It should be understood that Figure 7 and Figure 8 are only examples of this application and should not be construed as limitations on this application. For example, in other alternative embodiments, the target vehicle 300 may be traveling on a crossroads.

[0164] In some embodiments of this application, the method 200 may further include:

[0165] S215, determining at least one second proportion corresponding to at least one non-monitorable factor respectively.

[0166] S216, determining a target proportion among the at least one second proportion.

[0167] S217, adjusting the prediction probability based on the target proportion.

[0168] For example, the monitoring system obtains the at least one second proportion from the traffic management system, determines the target proportion among the at least one second proportion, and then can adjust the prediction probability based on the target proportion.

[0169] Similar to the monitorable factors, the probabilities of traffic accidents triggered by different non-monitorable factors may vary. By adjusting the prediction probability with the target proportion, it is possible to further consider the impact of non-monitorable factors on traffic accidents on the basis of considering monitorable factors. In particular, for some non-monitorable factors that are particularly important for the probability of traffic accidents, the accuracy of accident prediction can be further improved.

[0170] For example, the prediction probability can be adjusted in the following manner:

[0171] Determine a target change amount based on the target proportion, where the target change amount is the change amount of the target proportion relative to the second average proportion; add 1 to the target change amount respectively to generate a target weight; determine the product of the prediction probability and the target weight as the adjusted probability.

[0172] Again, for example, the prediction probability can be corrected based on the following formula:

[0173] p t = p p (1 + w t - 1 / n);

[0174] where, p t represents the corrected value of the prediction probability, p p represents the prediction probability, w trepresents the target proportion, and n represents the number of the at least one unmonitorable factor.

[0175] In some embodiments of the present application, the at least one unmonitorable factor includes at least one type of driving behavior. For example, the at least one type of driving behavior includes at least one of the following behaviors: aggressive driving, fatigue driving, distracted driving, or dangerous driving.

[0176] It should be understood that the classification of driving behaviors in this application is only an example and should not be construed as limiting this application. Optionally, driving behaviors may be classified based on specific behaviors of the driver.

[0177] For example, the aggressive driving may include speeding at intersections, excessive speed, turning too quickly, overtaking and scratching, not keeping a safe distance, etc. Since the aggressive driving accounts for a large proportion of traffic accidents caused by the driver's behavior, for example, 80%, therefore, adjusting the predicted probability by the target proportion can further reduce or compensate for the impact of driving behavior on traffic accidents on the basis of considering the monitorable factors, and can further improve the accuracy of accident prediction.

[0178] For another example, fatigue driving can be understood as the driver driving a vehicle without adequate rest for a long time or in poor physical condition. For another example, distracted driving can be understood as the driver doing other distracting things while driving the vehicle. For example, making phone calls, looking at mobile phones, smoking, etc. For another example, dangerous driving can be understood as the driving behavior of a driver who lacks basic driving knowledge, or such dangerous driving can also be understood as driving behavior that seriously violates the regulations. For example, such driving behavior that seriously violates the regulations includes but is not limited to driving in the wrong direction or slipping.

[0179] The following uses the example where the at least one unmonitorable factor is at least one type of driving behavior to illustrate the solution of the present application.

[0180] The early warning system can obtain at least a second proportion corresponding to the at least one type of driving behavior from the traffic management system, that is, w1, w2, ..., w n , where n represents the number of the at least one type of driving behavior. The classification of driving behavior may depend on the specific situation. For example, the classification of driving behavior and the proportion of each type obtained from the traffic management system may be used as the basis. n Quantifying the degree of influence of the at least one type of driving behavior on the traffic accident of the target vehicle is equivalent to that a higher proportion of traffic accidents means a higher degree of attention should be paid to the driving behavior, which can ensure the quantification accuracy of the at least one type of driving behavior.

[0181] Then, the early warning system can be based on w1,w2,...,w n Adjust the predicted probability.

[0182] Since the behavior of the driver in the target vehicle cannot be monitored in real time, even if the driver's behavior can be monitored, it is difficult to determine the category to which the driver's behavior belongs. Based on this, the warning system needs to be based on w1, w2,..., w n to issue a random warning.

[0183] For example, assuming that the driver's behavior is the t-th type of driving behavior, that is, the above-mentioned target proportion, then the second proportion corresponding to the t-th type of driving behavior can be determined among w1, w2,..., w n i.e., w t ; based on this, the warning system can obtain w t the change amount relative to the second average proportion, that is, w t - 1 / n; thus, the prediction probability can be corrected to p p (1 + W t - 1 / n).

[0184] The implementation method for determining the target proportion will be described below.

[0185] In some embodiments of the present application, the target proportion can be determined in the following manner:

[0186] Obtain a random variable that follows a uniform distribution on the interval [0, 1]; determine the target proportion based on this random variable.

[0187] For example, determine the second proportion that is greater than or equal to the random variable among the at least one second proportion as the target proportion. Or, determine the second proportion that is less than the random variable among the at least one second proportion as the target proportion.

[0188] Or, determine the target interval the random variable is within the target interval, w i represents the second proportion corresponding to the i-th unmonitorable factor among the at least one unmonitorable factor; determine the second proportion corresponding to the k-th unmonitorable factor among the at least one unmonitorable factor as the target proportion.

[0189] In other words, the warning system can generate a random variable that follows a uniform distribution of 0 - 1, i.e., ξ; based on this, the warning system can determine the target proportion among w1, w2,..., w n i.e., w t . For example, if ξ is less than or equal to w k , then the warning system can determine w k as w t . Or, ξ is between w1 + w2 +... + w k and w1 + w2 +... + w k+1If it is between, the warning system can set w k as w t . Again, for example, if ξ is greater than w k , the warning system can set w k as w t . It should be noted that w k can be any one of w1, w2,..., w n . Further, if there are multiple w k that meet the conditions, one w k can also be selected from these multiple w k as w t . For example, the largest or smallest w k can be selected from these multiple w k as w t . Again, for example, the w k with the smallest or largest difference from the random variable can be selected from these multiple w k as w t

[0190] In addition, the present application does not limit the specific implementation manner of generating the random variable. For example, various tools or functions for generating random variables can be used to generate the random variable. Additionally, determining the target proportion based on the random variable is only an example of the present application. In other alternative embodiments, other methods can also be used to determine the target proportion among the at least one second proportion. For example, the target proportion can be determined randomly.

[0191] The preferred embodiments of the present application have been described in detail above with reference to the accompanying drawings. However, the present application is not limited to the specific details in the above embodiments. Within the technical concept of the present application, various simple modifications can be made to the technical solutions of the present application, and these simple modifications all fall within the protection scope of the present application. For example, among the various specific technical features described in the above specific embodiments, they can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, the present application does not separately describe various possible combination methods. Again, for example, any combination can be made between various different embodiments of the present application, as long as it does not violate the idea of the present application, it should also be regarded as the content disclosed by the present application.

[0192] It should also be understood that in various method embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0193] As described above in conjunction with Figures 1 to 8 , the method embodiments of the present application have been described in detail. Below in conjunction with Figures 9 to 10, describe the device embodiments of the present application in detail.

[0194] Figure 9 It is a schematic block diagram of a device 500 for predicting traffic accidents provided by an embodiment of the present application.

[0195] As Figure 9 shown, the device 500 may include:

[0196] An acquisition unit 510, configured to obtain the historical probability of a target vehicle based on historical traffic accidents on a target road;

[0197] A first determination unit 520, configured to determine at least one first proportion corresponding to at least one monitorable factor, where the at least one monitorable factor is a factor that can trigger a traffic accident of the target vehicle monitored by roadside equipment, and the at least one first proportion is the proportion of traffic accidents triggered by the at least one monitorable factor in the historical traffic accidents;

[0198] A second determination unit 530, configured to determine a first probability based on the historical probability and the at least one first proportion;

[0199] A third determination unit 540, configured to determine a prediction probability of the target vehicle based on the first probability, where the prediction probability is used to represent the possibility of the target vehicle having a traffic accident on the target road.

[0200] In some embodiments of the present application, the first probability is the probability that none of the at least one monitorable factor triggers a traffic accident of the target vehicle, and the third determination unit 540 is specifically configured to:

[0201] Determine the difference between 1 and the first probability as the prediction probability.

[0202] In some embodiments of the present application, the second determination unit 530 is specifically configured to:

[0203] Based on the historical probability and the at least one first proportion, determine at least one second probability corresponding to the at least one monitorable factor, where the second probability corresponding to the same monitorable factor in the at least one monitorable factor is used to represent the possibility that the same monitorable factor does not trigger a traffic accident of the target vehicle;

[0204] Determine the first probability based on the at least one second probability.

[0205] In some embodiments of the present application, the second determination unit 530 is specifically configured to:

[0206] Based on the at least one first proportion, determine at least one change amount, where the at least one change amount is the change amount of the at least one first proportion relative to the first average proportion;

[0207] Increment each of the at least one change amount by 1 to generate at least one weight corresponding to each of the at least one monitorable factor;

[0208] Multiply each of the at least one weight by the historical probability to generate at least one third probability corresponding to each of the at least one monitorable factor, and the third probability corresponding to the same monitorable factor among the at least one monitorable factor is used to represent the possibility that the same monitorable factor triggers a traffic accident of the target vehicle;

[0209] Subtract each of the at least one third probability from 1 to generate at least one second probability.

[0210] In some embodiments of the present application, the obtaining unit 510 is further configured to:

[0211] Obtain the distribution of surrounding vehicles of the target vehicle through a road monitoring system;

[0212] Wherein, the second determining unit 530 is specifically configured to:

[0213] Determine the first probability based on the at least one second probability and the distribution of surrounding vehicles of the target vehicle.

[0214] In some embodiments of the present application, the second determining unit 530 is specifically configured to:

[0215] Determine the number of vehicles corresponding to each of the at least one monitorable factor based on the distribution of surrounding vehicles of the target vehicle;

[0216] Determine at least one fourth probability corresponding to each of the at least one monitorable factor based on the at least one second probability and the number of vehicles corresponding to each of the at least one monitorable factor, and the fourth probability corresponding to the same monitorable factor among the at least one monitorable factor is used to represent the possibility that the same monitorable factor triggers traffic accidents of the target vehicle and all vehicles corresponding to the same monitorable factor;

[0217] Determine the product of the at least one fourth probability as the first probability.

[0218] In some embodiments of the present application, the at least one monitorable factor includes at least one type of driving blind area; along the driving direction of the target vehicle, the at least one type of driving blind area includes at least one of the following: front blind area, rear blind area, left blind area or right blind area; alternatively, the at least one type of driving blind area includes a full blind area or a half blind area.

[0219] In some embodiments of the present application, the third determining unit 540 is further configured to:

[0220] Determine at least one second proportion corresponding to at least one non-monitorable factor respectively;

[0221] Determine a target proportion from the at least one second proportion;

[0222] Adjust the prediction probability based on the target proportion.

[0223] In some embodiments of the present application, the third determination unit 540 is specifically configured to:

[0224] Determine a target change amount based on the target proportion, where the target change amount is the change amount of the target proportion relative to the second average proportion;

[0225] Add 1 to the target change amount respectively to generate a target weight;

[0226] Determine the product of the prediction probability and the target weight as the adjusted probability.

[0227] In some embodiments of the present application, the third determination unit 540 is specifically configured to:

[0228] Obtain a random variable that follows a uniform distribution on the interval [0, 1];

[0229] Determine the target proportion based on the random variable.

[0230] In some embodiments of the present application, the third determination unit 540 is specifically configured to:

[0231] Determine, as the target proportion, the second proportion in the at least one second proportion that is greater than or equal to the random variable; or

[0232] Determine, as the target proportion, the second proportion in the at least one second proportion that is less than the random variable.

[0233] In some embodiments of the present application, the third determination unit 540 is specifically configured to:

[0234] Determine a target interval The random variable is within the target interval, w i represents the second proportion corresponding to the i-th non-monitorable factor among the at least one non-monitorable factor;

[0235] Determine, as the target proportion, the second proportion corresponding to the k-th non-monitorable factor among the at least one non-monitorable factor.

[0236] In some embodiments of the present application, the at least one non-monitorable factor includes at least one type of driving behavior, and the at least one type of driving behavior includes at least one of the following behaviors: aggressive driving, fatigued driving, distracted driving, or dangerous driving.

[0237] It should be understood that the device embodiments and the method embodiments can correspond to each other, and similar descriptions can refer to the method embodiments. To avoid repetition, they will not be elaborated here. Specifically, Figure 9 the illustrated device 500 may correspond to the corresponding entity in the method 200 implementing the embodiments of the present application, and the foregoing and other operations and / or functions of each module in the device 500 respectively serve to implement Figure 2 the corresponding processes in the respective methods in, and for the sake of brevity, will not be elaborated here.

[0238] The device 500 of the embodiments of the present application has been described above from the perspective of functional modules in combination with the accompanying drawings. It should be understood that the functional modules can be implemented in the form of hardware, or in the form of instructions in software, or in a combination of hardware and software modules. Specifically, the steps of the method embodiments in the present application can be completed by the integrated logic circuit in hardware in the processor and / or instructions in software form. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by the combination of the hardware and software modules in the decoding processor. Optionally, the software module can 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, an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps in the above method embodiments.

[0239] Figure 10 is a schematic block diagram of the terminal device 600 provided by the embodiments of the present application.

[0240] As Figure 10 shown, the terminal device 600 may include:

[0241] a memory 610 and a processor 620. The memory 610 is used to store a computer program 611 and transmit the program code 611 to the processor 620. In other words, the processor 620 can call and run the computer program 611 from the memory 610 to implement the method in the embodiments of the present application.

[0242] For example, the processor 620 can be used to execute the steps in the above method 200 according to the instructions in the computer program 611.

[0243] In some embodiments of the present application, the processor 620 may include but is not limited to:

[0244] General-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like.

[0245] In some embodiments of the present application, the memory 610 includes, but is not limited to:

[0246] Volatile memory and / or non-volatile memory. Among them, the non-volatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synch link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0247] In some embodiments of the present application, the computer program 611 can be divided into one or more modules, and the one or more modules are stored in the memory 610 and executed by the processor 620 to complete the method for recording a page provided by the present application. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 611 in the terminal device 600.

[0248] As Figure 10 shown, the terminal device 600 may further include:

[0249] A transceiver 630, which can be connected to the processor 620 or the memory 610.

[0250] Among them, the processor 620 can control the transceiver 630 to communicate with other devices. Specifically, it can send information or data to other devices, or receive information or data sent by other devices. The transceiver 630 can include a transmitter and a receiver. The transceiver 630 can further include an antenna, and the number of antennas can be one or more.

[0251] It should be understood that each component in the terminal device 600 is connected through a bus system. Among them, the bus system includes not only a data bus, but also a power bus, a control bus, and a status signal bus.

[0252] According to one aspect of the present application, a computer storage medium is provided, on which a computer program is stored. When the computer program is executed by a computer, the computer can execute the methods in the above method embodiments. Or rather, the embodiments of the present application also provide a computer program product containing instructions. When the instructions are executed by a computer, the computer executes the methods in the above method embodiments.

[0253] According to another aspect of the present application, a computer program product or a computer program is provided. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods in the above method embodiments.

[0254] In other words, when implemented using software, it can be implemented in the form of a computer program product in whole or in part. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions according to the embodiments of this application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can 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 can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wirelessly (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a digital video disc (DVD)), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0255] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0256] In several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there can be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of devices or modules can be in an electrical, mechanical, or other form.

[0257] The module described as a separate component may or may not be physically separated. The component shown as a module may or may not be a physical module, that is, it may be located in one place or may be distributed across multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. For example, in each embodiment of this application, each functional module can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0258] As described above, the above are only specific embodiments of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, which should all be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of this claim.

Claims

1. A method for predicting traffic accidents, characterized in that, Including: Obtaining the historical probability of the target vehicle based on historical traffic accidents on the target road; Determining at least one first proportion corresponding to at least one monitorable factor, where the at least one monitorable factor is a factor that can trigger a traffic accident of the target vehicle monitored by roadside equipment, and the at least one first proportion is the proportion of traffic accidents triggered by the at least one monitorable factor in the historical traffic accidents; Determining a first probability based on the historical probability and the at least one first proportion; Determining a prediction probability of the target vehicle based on the first probability, where the prediction probability is used to represent the possibility of the target vehicle having a traffic accident on the target road; Wherein, the first probability is calculated according to the following formula: The prediction probability is calculated according to the following formula: p1 represents the first probability, ∏ represents the product operation, m represents the number of the at least one monitorable factor, p h represents the historical probability, u i represents the first proportion corresponding to the i-th monitorable factor among the at least one monitorable factor, c i represents the number of vehicles corresponding to the i-th monitorable factor among the at least one monitorable factor.

2. The method according to claim 1, characterized in that, The at least one monitorable factor includes at least one type of driving blind area; along the driving direction of the target vehicle, the at least one type of driving blind area includes at least one of the following: front blind area, rear blind area, left blind area or right blind area; alternatively, the at least one type of driving blind area includes a full blind area or a semi-blind area.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Determining at least one second proportion corresponding to at least one unmonitorable factor; Determining a target proportion among the at least one second proportion; Adjusting the prediction probability based on the target proportion.

4. The method according to claim 3, wherein The adjusting the prediction probability based on the target proportion includes: Determining a target change amount based on the target proportion, where the target change amount is the change amount of the target proportion relative to the second average proportion; Adding 1 to the target change amount respectively to generate a target weight; Determining the product of the prediction probability and the target weight as the adjusted probability.

5. The method according to claim 3, characterized in that, The determining the target proportion among the at least one second proportion includes: Obtaining a random variable that follows a uniform distribution on the interval [0, 1]; Determining the target proportion among the at least one second proportion based on the random variable.

6. The method according to claim 5, characterized in that, The adjusting the prediction probability based on the target proportion includes: Determining the second proportion that is greater than or equal to the random variable among the at least one second proportion as the target proportion; or Determining the second proportion that is less than the random variable among the at least one second proportion as the target proportion.

7. The method according to claim 5, wherein The adjusting the prediction probability based on the target proportion includes: Determine the target interval The random variable is within the target interval, w i represents the second proportion corresponding to the i-th unmonitorable factor among the at least one unmonitorable factor; Determining the second proportion corresponding to the k-th unmonitorable factor among the at least one unmonitorable factor as the target proportion.

8. A device for predicting traffic accidents, characterized in that, Including: An obtaining unit, configured to obtain the historical probability of the target vehicle based on historical traffic accidents on the target road; A first determining unit, configured to determine at least one first proportion corresponding to at least one monitorable factor, where the at least one monitorable factor is a factor that can trigger a traffic accident of the target vehicle monitored by roadside equipment, and the at least one first proportion is the proportion of traffic accidents triggered by the at least one monitorable factor in the historical traffic accidents; A second determining unit, configured to determine a first probability based on the historical probability and the at least one first proportion; A third determination unit, configured to determine a prediction probability of the target vehicle based on the first probability, where the prediction probability is used to represent the possibility that the target vehicle has a traffic accident on the target road; Wherein, the first probability is calculated according to the following formula: The prediction probability is calculated according to the following formula: p1 represents the first probability, ∏ represents the product operation, m represents the number of the at least one monitorable factor, p h represents the historical probability, u i represents the first proportion corresponding to the i-th monitorable factor among the at least one monitorable factor, c i represents the number of vehicles corresponding to the i-th monitorable factor among the at least one monitorable factor.

9. A terminal device, characterized in that, including: A processor and a memory, where the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, For storing a computer program, which causes a computer to execute the method according to any one of claims 1 to 7.

Images