A vehicle collision recognition method, device, storage medium and electronic device

Abstract

The present application relates to a vehicle collision recognition method, device, storage medium and electronic device, and relates to the technical field of collision recognition. The method includes: determining first collision information according to GPS data, determining the recorder video as second collision information, and determining whether there is a risk of collision occurring for the target vehicle according to the first collision information and the second collision information; if so, determining the actual dangerous driving operations of the target driver within a preset time period before the current time according to the in-vehicle video, and determining the actual driving conditions of the target vehicle before the current time; verifying whether there is a risk of collision occurring for the target vehicle according to each actual dangerous driving operation, actual driving conditions, at least one target dangerous driving operation that the target driver is prone to, and the corresponding target driving conditions. If so, a safety warning is sent to the terminal of the collision verification personnel. The present application has the effect of improving the timeliness of rescuing personnel in a collision accident.

Description

Technical Field

[0001] This application relates to the field of collision recognition technology, and specifically relates to a vehicle collision recognition method, device, storage medium, and electronic device. Background Art

[0002] In recent years, with the continuous development of the Chinese economy and the improvement of people's living standards, cars have gradually become necessities for more and more families, and domestic consumers' enthusiasm for car consumption has only increased. As of the end of September 2023, the national motor vehicle ownership has reached 430 million vehicles, of which cars still dominate, reaching 330 million vehicles. This figure has increased significantly compared with previous years, reflecting the huge scale and strong demand of the Chinese car market. Against this background, road traffic congestion in various cities has also intensified, resulting in an increasing number of vehicle collision accidents. The negative impacts brought by vehicle collision accidents are also multi-faceted, not only involving economic losses, but also possibly having a profound impact on personal health, social resources, and the environment. Therefore, there is an urgent need for an effective monitoring mechanism or effective recognition mechanism for vehicle collision accidents.

[0003] Currently, the commonly used method for identifying vehicle collision accidents is as follows: after a vehicle collision accident occurs, it mainly relies on the vehicle owner and relevant personnel to report the accident, or the corresponding safety customer service personnel of the vehicle factory actively call to inquire about the relevant situation of the accident and the safety status of the vehicle owner when they detect that the vehicle is abnormal. After confirming that a collision accident has occurred, a targeted response is made. In this way, the identification and confirmation link for vehicle collision accidents involves telephone communication, which takes a long time. Once the collision accident is relatively serious, the timeliness of rescue for the personnel involved in the collision accident is poor. Summary of the Invention

[0004] To improve the timeliness of rescue for personnel involved in a collision accident, this application provides a vehicle collision recognition method, device, storage medium, and electronic device.

[0005] In the first aspect of this application, a vehicle collision recognition method is provided, which specifically includes:

[0006] When the target vehicle generates vibrations at the current time, obtain the recorder video and GPS data of the target vehicle before and after the current time, and obtain the in-vehicle video within a preset time period before the current time of the target vehicle. The GPS data is used to represent the position information and speed information of the target vehicle;

[0007] According to the GPS data, determine the first collision information, determine the recorder video as the second collision information, and determine whether there is a risk of collision occurring for the target vehicle according to the first collision information and the second collision information;

[0008] If so, at least one actual dangerous driving operation within a preset time period before the current time of the target driver is determined according to the in-vehicle video, and the actual driving condition of the target vehicle before the current time is determined;

[0009] According to each of the actual dangerous driving operations, the actual driving condition, at least one target dangerous driving operation that the target driver is prone to, and the corresponding target driving condition, it is verified whether there is a risk of collision occurring for the target vehicle. If so, a safety warning is sent to the terminal of the collision verification personnel. The target driving condition is a driving condition that is prone to cause a collision accident when there is a corresponding target dangerous driving operation.

[0010] By adopting the above technical solution, when the target vehicle vibrates, the recorder video, GPS data, and in-vehicle video are obtained. Then, the speed change situation of the target vehicle during driving is analyzed through GPS data, and thus the first collision information is determined. At the same time, the recorder video is determined as the second collision information. By combining the first collision information and the second collision information, it is analyzed and determined whether there is a risk of collision occurring for the target vehicle. If there is a risk of collision occurring, based on the target dangerous driving operation and the corresponding target driving condition, combined with the actual dangerous driving operation and actual driving condition of the target driver, the possibility of collision of the current target vehicle is analyzed, and then it is verified whether the target vehicle actually has a risk of collision occurring, so as to more accurately evaluate the collision situation of the target vehicle. Finally, after verifying that there is a risk of collision occurring, if the target vehicle is likely to have a collision accident, a safety warning is directly sent to the collision verification personnel. Once the target vehicle collides, personnel can go to the scene in time to provide rescue, thereby improving the timeliness of rescue for the personnel in the collision accident.

[0011] Optionally, the verifying whether there is a risk of collision occurring for the target vehicle according to each of the actual dangerous driving operations, the actual driving condition, at least one target dangerous driving operation that the target driver is prone to, and the corresponding target driving condition specifically includes:

[0012] Obtain the historical dangerous driving operations of the driver in the vehicle when historical vehicles collided, count the first occurrence times of each of the historical dangerous driving operations, and select the first number of historical dangerous driving operations from each of the historical dangerous driving operations in descending order of the first occurrence times to be determined as the target dangerous driving operations;

[0013] Obtain the historical driving conditions of the vehicle when a historical driver had a collision accident during a single target dangerous driving operation, count the second occurrence times of each of the historical driving conditions, and select the second quantity of historical driving conditions from each of the historical driving conditions in descending order of the second occurrence times to determine the target driving conditions corresponding to the target dangerous driving operation;

[0014] Calculate the first weight of each of the target dangerous driving operations, and calculate the second weights of the respective target driving conditions corresponding to each of the target dangerous driving operations. The first weight is the ratio of the first occurrence times of each target dangerous driving operation to the sum of the first occurrence times of all target dangerous driving operations, and the second weight is the ratio of the second occurrence times of a single target driving condition corresponding to the target dangerous driving operation to the sum of the second occurrence times of all the corresponding target driving conditions;

[0015] Based on each of the actual dangerous driving operations, the actual driving conditions, the first weight, and the respective second weights, verify whether the target vehicle has a risk of collision occurrence.

[0016] By adopting the above technical solutions, the larger the first occurrence times, the more likely the corresponding historical dangerous driving operation is to cause a collision accident, thereby determining the target dangerous driving operation; the larger the second occurrence times, when the target dangerous driving operation appears during driving, the more likely the vehicle is to have a collision accident when in the corresponding historical driving conditions, thereby determining the corresponding target driving conditions. Finally, combining the first weight of the target dangerous driving operation and the second weights of the respective target driving conditions, analyze and determine the likelihood of the target vehicle having a collision at the current time, thereby completing the verification of whether the target vehicle has a risk of collision occurrence and achieving an accurate assessment of the collision situation of the target vehicle.

[0017] Optionally, the verifying whether the target vehicle has a risk of collision occurrence based on each of the actual dangerous driving operations, the actual driving conditions, the first weight, and the respective second weights specifically includes:

[0018] Determine the target dangerous driving operations with the actual driving conditions in the respective corresponding target driving conditions as key driving operations, and when the actual dangerous driving operation is a key driving operation, determine the corresponding actual dangerous driving operation as a reference driving operation;

[0019] Calculate the first product of the first weight of each of the reference driving operations and the second weight of the corresponding actual driving condition, and sum the respective first products to obtain the sum of the first products;

[0020] If the sum of the first products is greater than a preset product sum threshold, verify that the target vehicle has a risk of collision occurrence.

[0021] By adopting the above technical solution, the larger the first product is, the greater the possibility that the target driver will have a collision accident when making the corresponding reference driving operation. The larger the sum of the first products is, the greater the possibility that the target driver will have a collision accident currently. Finally, if the sum of the first products is greater than the product sum threshold, it indicates that the possibility of a collision accident occurring currently is relatively high. Then, it is verified that this target vehicle does have a risk of collision, so as to more accurately evaluate the collision occurrence situation of the target vehicle.

[0022] Optionally, the method further includes:

[0023] If there is no risk of collision for the target vehicle, determine the current driving condition of the target vehicle, and determine the target dangerous driving operations with the current driving condition in the corresponding target driving conditions as important driving operations;

[0024] Calculate the second product of the first weight of each of the important driving operations and the second weight of the corresponding current driving condition, and sum up the second products to obtain the sum of the second products;

[0025] If the sum of the second products is greater than the preset product sum threshold, when there is at least one important driving operation for the target driver, determine the corresponding important driving operation as a risk driving operation, and determine the important driving operations other than the risk driving operation as remaining driving operations;

[0026] Select the largest second product from the second products corresponding to each of the remaining driving operations, and determine the remaining driving operation corresponding to the largest second product as a vigilant driving operation, and send a reminder message to the in-vehicle terminal of the target vehicle for the vigilant driving operation.

[0027] By adopting the above technical solution, the larger the second product is, the easier it is to cause a collision accident when the target driver makes the corresponding important driving operation under the current driving condition. The larger the sum of the second products is, the easier it is for the target vehicle to have a collision accident under the current driving condition. If the sum of the second products is greater than the product sum threshold, it indicates that the target vehicle is relatively likely to have a collision accident under the current driving condition, and the target driver needs to be vigilant about his driving operations. Further, the remaining driving operation corresponding to the largest second product has a greater impact on accelerating the occurrence of a collision accident. Then, it is determined as a vigilant driving operation, and a reminder message is sent to the in-vehicle terminal of the target vehicle for this vigilant driving operation, so as to timely remind the target driver to avoid this vigilant driving operation, and thus better avoid the occurrence of a collision accident.

[0028] Optionally, the method further includes:

[0029] If the sum of the second products is not greater than a preset product sum threshold, calculate the third product of the first weight of each of the risky driving operations and the second weight of the corresponding target driving conditions;

[0030] Sum the third products corresponding to the same target driving condition to obtain the corresponding sum of the third products, and select the largest sum of the third products from the sums of the third products;

[0031] When the largest sum of the third products is greater than the preset product sum threshold, determine the target driving condition corresponding to the largest sum of the third products as the vigilant driving condition. If the vigilant driving condition is different from the current driving condition, send a reminder message to the in-vehicle terminal of the target vehicle for the vigilant driving condition.

[0032] By adopting the above technical solution, if the sum of the second products is not greater than the product sum threshold, it indicates that the possibility of a collision accident occurring to the target vehicle under the current driving condition is relatively small. Further, the larger the sum of the third products, the greater the possibility of a collision accident occurring to the target vehicle under the corresponding target driving condition after the current time. If the largest sum of the third products is greater than the product sum threshold, it indicates that the possibility of a collision accident occurring under the target driving condition corresponding to the largest sum of the third products is relatively large. Then, determine this target driving condition as the vigilant driving condition. Further, if this vigilant driving condition is different from the current driving condition, then send a reminder message to the in-vehicle terminal of the target vehicle for this vigilant driving condition, so as to remind the target driver to avoid switching to this vigilant driving condition currently and avoid the occurrence of a collision accident.

[0033] Optionally, the method further includes:

[0034] Obtain the historical risky driving operations of the driver in the vehicle when a historical vehicle collision occurs, count the first occurrence times of each of the historical risky driving operations, and select the first number of historical risky driving operations from the historical risky driving operations in descending order of the first occurrence times to determine the target risky driving operations;

[0035] Obtain the historical area on the vehicle where the collision position is located when a collision accident occurs under a single target risky driving operation of the historical driver, count the third occurrence times of each of the historical areas, and select the third number of historical areas from the historical areas in descending order of the third occurrence times to determine the target area of the corresponding target risky driving operation;

[0036] Calculate the first weight of each of the target dangerous driving operations, and calculate the third weight of each target area corresponding to each of the target dangerous driving operations. The first weight is the ratio of the first occurrence times of each target dangerous driving operation to the sum of the first occurrence times of all target dangerous driving operations. The third weight is the ratio of the third occurrence times of a single target area corresponding to a target dangerous driving operation to the sum of the third occurrence times of all target areas corresponding to the target dangerous driving operation;

[0037] During the driving of the target vehicle, if the target driver performs a target dangerous driving operation, determine the corresponding target dangerous driving operation as an operation to be recorded, and establish a mapping relationship between each operation to be recorded and the corresponding occurrence time node in the real-time video. The real-time video is the driving video obtained in real time from the driving recorder in the target vehicle;

[0038] When the target vehicle switches from the driving state to the normal parking state and there are unknown collision marks, based on each of the mapping relationships, the first weight, and the corresponding third weights, investigate the cause of the appearance of the unknown collision marks.

[0039] By adopting the above technical solution, the larger the first occurrence times, the more likely the corresponding historical dangerous driving operation is to cause a collision accident, and thus the target dangerous driving operation is determined; the larger the third occurrence times, on the premise of performing a single target dangerous driving operation, the more likely the collision position is to be in the corresponding historical area, and thus the target area is determined. Finally, in combination with the mapping relationship, the first weight of the target dangerous driving operation, and the third weights of the corresponding target areas, targeted investigation is carried out on the corresponding time nodes in the real-time video, so as to more efficiently and accurately investigate the cause of the appearance.

[0040] Optionally, the investigation of the cause of the appearance of the unknown collision marks based on each of the mapping relationships, the first weight, and the corresponding third weights specifically includes:

[0041] Determine the target area where the unknown collision marks are located as the key area, determine the target dangerous driving operations in the corresponding target areas where the key area exists as the collision-inducing operations, determine the operations to be recorded existing in each of the collision-inducing operations as the final operations, and determine the corresponding final time nodes according to the mapping relationships of the final operations;

[0042] Calculate the fourth product of the first weight of each of the final operations and the third weight of the corresponding key area;

[0043] According to each of the fourth weights, determine the playback order of the corresponding final time nodes in the real-time video, and based on each of the playback orders, investigate the cause of the appearance of the unknown collision marks. The larger the fourth product, the more forward the corresponding playback order.

[0044] By adopting the above technical solution, the larger the fourth product, when the target driver makes the corresponding final operation and a collision occurs, it is easier for this unknown collision mark to appear. Then, the playback order of the corresponding final time nodes in the real-time video is more forward, and it is easier to discover the cause of the unknown collision mark. Finally, according to each playback order, personnel can screen the real-time video targeted and quickly investigate the cause.

[0045] In the second aspect of the present application, a vehicle collision recognition device is provided, which specifically includes:

[0046] A data acquisition module, configured to acquire the recorder video and GPS data of the target vehicle before and after the current time when the target vehicle generates vibrations at the current time, and acquire the in-vehicle video within a preset time period before the current time of the target vehicle. The GPS data is used to represent the position information and speed information of the target vehicle;

[0047] A risk determination module, configured to determine the first collision information according to the GPS data, determine the recorder video as the second collision information, and determine whether there is a risk of a collision occurring for the target vehicle according to the first collision information and the second collision information;

[0048] A working condition determination module, configured to, if so, determine at least one actual dangerous driving operation of the target driver within a preset time period before the current time according to the in-vehicle video, and determine the actual driving working condition of the target vehicle before the current time;

[0049] A risk warning module, configured to verify whether there is a risk of a collision occurring for the target vehicle according to each of the actual dangerous driving operations, the actual driving working condition, at least one target dangerous driving operation that the target driver is prone to and the corresponding target driving working condition. If so, send a safety warning to the terminal of the collision verification personnel. The target driving working condition is a driving working condition that is prone to cause a collision accident when there is a corresponding target dangerous driving operation.

[0050] By adopting the above technical solution, the data acquisition module acquires the recorder video, GPS data, and in-vehicle video. The risk determination module determines whether there is a risk of a collision occurring for the target vehicle based on the first collision information and the second collision information. Then, when the working condition determination module determines that there is a risk of a collision occurring, it determines the actual dangerous driving operation and the actual driving working condition. Finally, the risk warning module verifies whether there is a risk of a collision occurring for the target vehicle. If so, it sends a safety warning to the terminal of the collision verification personnel.

[0051] In a third aspect of the present application, a computer-readable storage medium is provided. A computer program is stored in the computer-readable storage medium. When the computer program is loaded and executed by a processor, the method steps described in any one of the first aspects are executed.

[0052] In a fourth aspect of the present application, an electronic device is provided, specifically including:

[0053] A processor, a memory, and a computer program stored in the memory and capable of running on the processor. The processor is used to load and execute the computer program stored in the memory, so that the electronic device executes the method described in any one of the first aspects.

[0054] In summary, the present application includes at least one of the following beneficial technical effects: By analyzing the speed change of the target vehicle during driving through GPS data, the first collision information is determined. At the same time, the recorder video is determined as the second collision information. By combining the first collision information and the second collision information, it is analyzed and determined whether there is a risk of collision for the target vehicle. If there is a risk of collision, based on the target dangerous driving operation and the corresponding target driving condition, combined with the actual dangerous driving operation and actual driving condition of the target driver, the possibility of collision of the current target vehicle is analyzed, and then it is verified whether the target vehicle actually has a risk of collision, so as to more accurately evaluate the collision situation of the target vehicle. Finally, after verifying that there is a risk of collision, if the target vehicle is likely to have a collision accident, a safety warning is directly sent to the collision verification personnel. Once the target vehicle collides, personnel can go to the scene in time to provide rescue, thereby improving the timeliness of rescue for personnel involved in collision accidents. Description of the Drawings

[0055] Figure 1 is a flowchart of a vehicle collision recognition method provided by an embodiment of the present application;

[0056] Figure 2 is a flowchart of another vehicle collision recognition method provided by an embodiment of the present application;

[0057] Figure 3 is a structural diagram of a vehicle collision recognition device provided by an embodiment of the present application;

[0058] Figure 4 is a structural diagram of another vehicle collision recognition device provided by an embodiment of the present application.

[0059] Description of the drawing reference numerals: 11, data acquisition module; 12, risk determination module; 13, operating condition determination module; 14, risk warning module; 15, operation reminder module; 16, operating condition reminder module; 17, cause investigation module. Detailed implementation manners

[0060] In order to enable those skilled in the art to better understand the technical solutions in this specification, the following will clearly and completely describe the technical solutions in the embodiments of this specification with reference to the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments.

[0061] In the description of the embodiments of this application, words such as "exemplary", "for example", or "for illustration" are used to indicate examples, illustrations, or explanations. Any embodiment or design solution described as "exemplary", "for example", or "for illustration" in the embodiments of this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, using words such as "exemplary", "for example", or "for illustration" aims to present relevant concepts in a specific manner.

[0062] In the description of the embodiments of this application, the term "and / or" only describes the association relationship of associated objects and indicates that three relationships may exist. For example, A and / or B may indicate: A exists alone, B exists alone, and both A and B exist simultaneously. In addition, unless otherwise specified, the meaning of the term "plural" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the technical features indicated. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0063] See Figure 1 , the embodiments of this application disclose a flowchart of a vehicle collision recognition method, which can be implemented depending on a computer program or run on a vehicle collision recognition device based on the von Neumann architecture. This computer program can be integrated in an application or run as an independent tool-type application, and specifically includes:

[0064] S101: When the target vehicle generates vibrations at the current time, obtain the recorder video and GPS data of the target vehicle before and after the current time, and obtain the in-vehicle video within a preset duration before the current time of the target vehicle.

[0065] Specifically, in the embodiments of the present application, the target vehicle is a moving vehicle for real-time collision monitoring, and a driving recorder is installed on the target vehicle. At the current time, if vibration data of the target vehicle is obtained through the driving recorder, it indicates that the target vehicle vibrates currently; if vibration data of the target vehicle is not obtained through the driving recorder, it indicates that the target vehicle does not vibrate currently. When the target vehicle vibrates at the current time, it may be caused by a collision of the target vehicle. Then, the recorder video and GPS data before and after the current time are obtained through the driving recorder. Specifically, it may be the video and GPS data recorded by the driving recorder within 3 seconds before the current time and within 3 seconds after the current time. In other embodiments, it may also be the video and GPS data recorded by the driving recorder within 4 seconds before the current time and within 3 seconds after the current time. Among them, the recorder video may be a real-time image video in front of the target vehicle recorded by the driving recorder. In other embodiments, the recorder video may also be a real-time image video of the front, rear, left, and right of the target vehicle recorded by the driving recorder. The GPS data includes, but is not limited to, the longitude and latitude of the position of the target vehicle before and after the current time, as well as the driving speed, etc., so as to characterize the position information and speed information of the target vehicle.

[0066] Further, the in-vehicle video within a preset duration before the current time is obtained through the in-vehicle camera. Specifically, after obtaining the consent of the driver in the target vehicle, the camera activation permission is obtained, and the video information of the driver's seat in the vehicle is obtained in real time through the camera, and the in-vehicle video within the preset duration before the current time is retrieved from the video information. In addition, the execution subject of a vehicle collision recognition method disclosed in the embodiments of the present application may be a server, and the server is wirelessly connected to the camera, the driving recorder, and the in-vehicle terminal of the target vehicle. The server may be an independent physical server or a server cluster composed of multiple physical servers. In other embodiments, the execution subject of a vehicle collision recognition method may also be the in-vehicle terminal itself of the target vehicle.

[0067] S102: Determine the first collision information according to the GPS data, determine the recorder video as the second collision information, and determine whether there is a risk of collision occurring for the target vehicle according to the first collision information and the second collision information.

[0068] Specifically, after the GPS data is determined, the GPS data is analyzed through a preset three-stage evaluation algorithm for GPS to determine the speed change of the target vehicle before and after the current time, and then the first collision information is determined. In other embodiments, the speed change curve can also be plotted based on the speeds of the target vehicle before and after the current time through a preset MATLAB tool, and then the first collision information is determined. Exemplarily, the first collision information can be: the information of three speed change stages of uniform speed driving - steep speed drop - speed stillness. Further, the recorder video is determined as the second collision information. Finally, based on the preset YOLO algorithm, the first collision information and the second collision information are analyzed. The specific process is as follows: the targets such as pedestrians, vehicles or obstacles in the second collision information (recorder video) are quickly identified through the YOLO algorithm. If a target is identified and the first collision information is uniform speed driving - steep speed drop - speed stillness, it indicates that the target vehicle may have become stationary due to a collision, and then it is determined that there is a risk of collision for the target vehicle.

[0069] S103: If so, based on the in-vehicle video, at least one actual dangerous driving operation within a preset duration before the current time of the target driver is determined, and the actual driving condition of the target vehicle before the current time is determined.

[0070] Specifically, if it is determined that there is a risk of collision for the target vehicle, then through a preset operation recognition model, based on the in-vehicle video, the driving operations or driving actions of the target driver in the vehicle are recognized. The operation recognition model can be a trained convolutional neural network model or a trained recurrent neural network model. The training process is briefly described as follows: the driving video marked with correct driving operations is used as a training sample and input into the model for training, and the model parameters are adjusted and optimized through the reverse gradient algorithm until the model converges, and finally the operation recognition model is obtained. This is the prior art and will not be elaborated here. In other embodiments, the driving operations of the target driver when operating the steering wheel, stepping on the accelerator and braking during driving can also be obtained through a steering sensor, an accelerator pedal position sensor, a brake pedal position sensor, etc.

[0071] Further, the identified driving operations are then compared with a plurality of preset dangerous driving operations, and the similarity is specifically calculated. If the similarity exceeds the preset similarity threshold, the actual dangerous driving operations that exist are determined. Among them, dangerous driving operations refer to some driving operations with potential safety hazards during the process of a driver driving a vehicle. Exemplarily, dangerous driving operations include, but are not limited to, suddenly turning the steering wheel, slamming on the accelerator, slamming on the brakes, and not using the turn signal correctly. Further, by analyzing the obtained GPS data, the driving trajectory of the target vehicle before the current time is determined, and then the actual driving conditions of the target vehicle are determined. In other embodiments, the actual driving conditions of the target vehicle before the current time can also be obtained in real time through a navigation tool in the vehicle. It should be noted that the driving conditions of the vehicle include, but are not limited to, starting conditions, accelerating conditions, turning conditions, uphill and downhill conditions, and reversing conditions, etc. It should be noted that a feasible way to calculate the similarity is as follows: the identified driving operations and the dangerous driving operations are respectively mapped into a high-dimensional vector space to obtain corresponding vectors, and then the cosine similarity between the two vectors is calculated to determine the similarity.

[0072] S104: According to each actual dangerous driving operation, the actual driving conditions, at least one target dangerous driving operation that the target driver is prone to, and the corresponding target driving conditions, verify whether there is a risk of collision for the target vehicle. If so, send a safety warning to the terminal of the collision verification personnel.

[0073] Specifically, through a search engine or a crawler, historical news and information about vehicle collision accidents are obtained. The historical news and information include, but are not limited to, the driving operation conditions and driving condition information of the driver during the collision accident, etc. Based on the historical news and information, the historical dangerous driving operations of the driver in the vehicle during the collision of the historical vehicle are determined, and the first occurrence times of each historical dangerous driving operation are counted. The larger the first occurrence times, the more likely the corresponding historical dangerous driving operation is to cause a collision accident. Then, in the order from largest to smallest of the first occurrence times, the first number of historical dangerous driving operations is selected from each historical dangerous driving operation and determined as the target dangerous driving operations, that is, the dangerous driving operations that are likely to cause collision accidents. Based on the above historical news and information, when a collision accident occurs under a single target dangerous driving operation by the historical driver, the historical driving conditions of the vehicle are determined, and the second occurrence times of each historical driving condition are counted. The larger the second occurrence times, the more likely it is that when the target dangerous driving operation occurs during driving, the vehicle is in the corresponding historical driving condition and a collision accident will occur. In the order from largest to smallest of the second occurrence times, the second number of historical driving conditions is selected from each historical driving condition and determined as the target driving conditions corresponding to the target dangerous driving operations, that is, the driving conditions that are likely to cause collision accidents.

[0074] Further, calculate the first weight of each target dangerous driving operation and the second weight of each target driving condition corresponding to each target dangerous driving operation. The first weight is the ratio of the first occurrence times of each target dangerous driving operation to the sum of the first occurrence times of all target dangerous driving operations. The second weight is the ratio of the second occurrence times of a single target driving condition corresponding to the target dangerous driving operation to the sum of the second occurrence times of all corresponding target driving conditions. After the first weight and the corresponding second weights are determined, combined with the actual dangerous driving operations and actual driving conditions of the target driver within a preset duration before the current time, further verify the existence of the current collision risk of the target vehicle, so as to more accurately evaluate the collision situation of the target vehicle. A feasible verification method is as follows: Determine the target dangerous driving operations with actual driving conditions in each corresponding target driving condition as key driving operations. When the actual dangerous driving operation is a key driving operation, determine the corresponding actual dangerous driving operation as a reference driving operation. Then, calculate the first product of the first weight of each reference driving operation and the second weight of the corresponding actual driving condition. The larger the first product, the greater the possibility of a collision accident when the target driver makes the corresponding reference driving operation. Sum up the first products to obtain the sum of the first products. The larger the sum of the first products, the greater the possibility of a collision accident for the target driver currently. Finally, compare the sum of the first products with a preset product sum threshold. If the sum of the first products is greater than the product sum threshold, it indicates that the possibility of a current collision accident is relatively large, and then verify that this target vehicle indeed has a collision risk.

[0075] Further, when verifying that the target vehicle has a collision risk, send a safety warning to the terminal of the collision verification personnel. The terminal can be a personal computer or a smartphone, and the collision verification personnel can be auto repair personnel near the target vehicle, so that the collision verification personnel can go to the location of the target vehicle for accident investigation, provide rescue in time once a collision accident occurs, and at the same time help auto repair personnel actively acquire customers.

[0076] In other embodiments, if there is no current risk of a collision occurring for the target vehicle, then the driving condition of the target vehicle at the current time is obtained, that is, the current driving condition. At the same time, the target dangerous driving operations that have the current driving condition among the corresponding various target driving conditions are determined as important driving operations. Calculate the second product of the first weight of each important driving operation and the second weight of the corresponding current driving condition. The larger the second product, the easier it is to cause a collision accident when the target driver makes the corresponding important driving operation under the current driving condition. Further, sum up the respective second products to obtain the corresponding sum of second products. The larger the sum of second products, the more likely the target vehicle is to have a collision accident under the current driving condition. If the sum of second products is greater than the product sum threshold, it indicates that the target vehicle is relatively likely to have a collision accident under the current driving condition, and the target driver needs to be vigilant about their driving operations. Then, when there is at least one important driving operation for the target driver currently, in order to avoid a subsequent collision accident, it is necessary to pay attention to the driving operations of the target driver after the current time. Next, the corresponding important driving operations are determined as risk driving operations, and the important driving operations other than the risk driving operations are determined as remaining driving operations. Select the largest second product from the second products corresponding to the respective remaining driving operations. The remaining driving operation corresponding to the largest second product has a greater impact on accelerating the occurrence of a collision accident, so it is determined as a vigilant driving operation, and a reminder message is sent to the in-vehicle terminal of the target vehicle for this vigilant driving operation, so as to timely remind the target driver to avoid this vigilant driving operation, and thus better avoid the occurrence of a collision accident.

[0077] In another embodiment, if the sum of second products is not greater than the product sum threshold, it indicates that the possibility of a collision accident occurring for the target vehicle under the current driving condition is relatively small. Then, calculate the third product of the first weight of each risk driving operation and the second weight of the corresponding various target driving conditions. Next, sum up the respective third products corresponding to the same target driving condition to obtain the corresponding sum of third products. The larger the sum of third products, the greater the possibility of a collision accident occurring for the target vehicle under the corresponding target driving condition after the current time. Then, select the largest sum of third products from the respective sums of third products. If the largest sum of third products is greater than the product sum threshold, it indicates that the possibility of a collision accident occurring under the target driving condition corresponding to the largest sum of third products is relatively large, so that target driving condition is determined as a vigilant driving condition. Further, if this vigilant driving condition is different from the current driving condition, then for this vigilant driving condition, a reminder message is sent to the in-vehicle terminal of the target vehicle, so as to remind the target driver to avoid switching to this vigilant driving condition currently.

[0078] See Figure 2, The flowchart of another vehicle collision recognition method disclosed in the embodiments of the present application can be implemented depending on a computer program or run on a vehicle collision recognition device based on the von Neumann architecture. This computer program can be integrated into an application or run as an independent tool application. Specifically, it includes:

[0079] S201: When the target vehicle generates vibrations at the current time, obtain the recorder video and GPS data of the target vehicle before and after the current time, and obtain the in-vehicle video within a preset duration before the current time of the target vehicle.

[0080] S202: According to the GPS data, determine the first collision information, determine the recorder video as the second collision information, and based on the first collision information and the second collision information, determine whether there is a risk of a collision occurring for the target vehicle.

[0081] S203: If so, according to the in-vehicle video, determine at least one actual dangerous driving operation within a preset duration before the current time of the target driver, and determine the actual driving conditions of the target vehicle before the current time.

[0082] S204: According to each actual dangerous driving operation, the actual driving conditions, at least one target dangerous driving operation that the target driver is prone to, and the corresponding target driving conditions, verify whether there is a risk of a collision occurring for the target vehicle. If so, send a safety warning to the terminal of the collision verification personnel.

[0083] Specifically, reference can be made to steps S101 - S104, which will not be elaborated here.

[0084] S205: Obtain the historical dangerous driving operations of the in-vehicle driver when historical vehicles had collisions, count the first occurrence times of each historical dangerous driving operation, and select the first number of historical dangerous driving operations from each historical dangerous driving operation in descending order of the first occurrence times to be determined as the target dangerous driving operations.

[0085] Specifically, reference can be made to step S104, which will not be elaborated here.

[0086] S206: Obtain the historical areas on the vehicle where the collision positions were located when historical drivers had collision accidents under a single target dangerous driving operation, count the third occurrence times of each historical area, and select the third number of historical areas from each historical area in descending order of the third occurrence times to determine the target areas corresponding to the target dangerous driving operations.

[0087] S207: Calculate the first weight of each target dangerous driving operation, and calculate the third weight of each target area corresponding to each target dangerous driving operation.

[0088] Specifically, after determining the target dangerous driving operation, based on the above historical news information, determine the historical area on the vehicle where the collision position is located when the historical driver has a collision accident when making a single target dangerous driving operation. The historical news information also includes the collision position where the vehicle has a collision. Count the third occurrence times of the historical areas, and select the third number of historical areas from each historical area in descending order of the third occurrence times to determine the target area corresponding to the target dangerous driving operation, that is, the area on the vehicle where collisions are likely to occur. Exemplarily, if the target dangerous driving operation is changing lanes without turning on the turn signal, then the corresponding target area is usually the rear side area of the vehicle. Further, the first weight is the ratio of the first occurrence times of each target dangerous driving operation to the sum of the first occurrence times of all target dangerous driving operations, and the third weight is the ratio of the third occurrence times of the single target area corresponding to the target dangerous driving operation to the sum of the third occurrence times of the corresponding all target areas.

[0089] S208: During the driving process of the target vehicle, if the target driver has a target dangerous driving operation, then determine the corresponding target dangerous driving operation as the operation to be recorded, and establish a mapping relationship between each operation to be recorded and the corresponding occurrence time node in the real-time video.

[0090] S209: When the target vehicle switches from the driving state to the normal parking state and there are unknown collision marks, based on each mapping relationship, the first weight, and the corresponding third weights, investigate the cause of the appearance of the unknown collision marks.

[0091] Specifically, when the target vehicle is in motion, the driving operations of the target driver are obtained in real time through an in-vehicle camera. If the target driver performs a target dangerous driving operation, the corresponding target dangerous driving operation is determined as an operation to be recorded. Then, through the monitoring video of the camera, the occurrence time node of this operation to be recorded is determined. Finally, a mapping relationship is established between each operation to be recorded and the corresponding occurrence time node in the real-time video, where the real-time video is the driving video obtained in real time from the driving recorder in the target vehicle. Further, when the target vehicle switches from the driving state to the normal parking state, it indicates that the driving of the target driver has ended. If relevant information about unknown collision marks is received from the terminal of the target driver, it indicates that after the driving ends, there are collision marks on the target vehicle that were not detected during the driving process due to a collision accident. Here, the unknown collision marks are collision marks on the target vehicle for which the time, location, and cause of generation are uncertain during driving. Exemplarily, the unknown collision marks can be brand-new scratches. Further, it is necessary to investigate the cause of the generation of the unknown collision marks. A feasible investigation method is as follows: The target area where the unknown collision marks are located is determined as the key area, and the target dangerous driving operations in the corresponding target areas that contain this key area are determined as the collision-inducing operations. Then, the operations to be recorded existing in each collision-inducing operation are determined as the final operations. Next, according to the mapping relationship of this final operation, the corresponding final time node is determined.

[0092] Further, calculate the fourth product of the first weight of each final operation and the third weight of the corresponding key area. Finally, according to the fourth weight, determine the playback order of the corresponding final time nodes in the real-time video. The larger the fourth product, the more likely it is for the unknown collision marks to appear when the target driver performs the corresponding final operation and causes a collision. Then, the playback order of the corresponding final time nodes is more forward. Exemplarily, the fourth weight corresponding to the final operation A is the largest, and the final time node corresponding to the final operation A is a. Then, the video starts playing from the final time node a in the real-time video first, so that personnel can quickly find the cause of the appearance of the unknown collision marks from the real-time video. Further, sequentially mark each final time node in the real-time video according to the playback order to obtain the marked video. Finally, send the marked video to the terminal of the target driver so that they can screen the real-time video targeted according to the sequential marking and quickly investigate the cause.

[0093] In other embodiments, calculate the weighted product of the first weight of at least one actual dangerous driving operation existing in each target dangerous driving operation and the third weight of the corresponding target area, sum up the weighted products to obtain the summation result of the corresponding actual dangerous driving operation, and then sum up the summation results to obtain the final summation result. If the final summation result is greater than the preset summation threshold, it indicates that the probability of the target vehicle colliding at the current time is relatively high. Then, verify that there is indeed a risk of collision for the target vehicle, so as to more accurately evaluate the collision situation of the target vehicle. At the same time, select the weighted products in the same target area for summation to obtain the corresponding weighted product sum, select the largest weighted product sum from the weighted product sums, and determine the target area corresponding to the largest weighted product sum as the investigation area, that is, the most likely collision area when a collision occurs. Finally, while sending a safety warning to the collision verification personnel, send this investigation area together. Once a collision accident actually occurs, targeted rescue tools can be prepared in advance according to this investigation area, thereby improving the efficiency of on-site rescue.

[0094] The implementation principle of a vehicle collision recognition method according to an embodiment of the present application is as follows: Analyze the speed change situation of the target vehicle during driving through GPS data analysis to determine the first collision information. At the same time, determine the recorder video as the second collision information. Combine the first collision information and the second collision information to analyze and determine whether there is a risk of collision for the target vehicle. If there is a risk of collision, based on the target dangerous driving operation and the corresponding target driving conditions, combined with the actual dangerous driving operation and actual driving conditions of the target driver, analyze the probability of the current target vehicle of the target vehicle colliding, and then verify whether there is indeed a risk of collision for the target vehicle, so as to more accurately evaluate the collision situation of the target vehicle. Finally, after verifying that there is a risk of collision, it is highly probable that a collision accident will occur for the target vehicle. Then, directly send a safety warning to the collision verification personnel. Once the target vehicle collides, personnel can go to the scene in time to provide rescue, thereby improving the timeliness of rescuing the personnel in the collision accident.

[0095] The following is an embodiment of the device of the present application, which can be used to execute the method embodiment of the present application. For the details not disclosed in the embodiment of the device of the present application, please refer to the method embodiment of the present application.

[0096] Please refer to Figure 3 , which is a schematic structural diagram of a vehicle collision recognition device provided by an embodiment of the present application. The vehicle collision recognition device can be implemented as all or part of the device through software, hardware, or a combination of both. The device includes a data acquisition module 11, a risk determination module 12, a working condition determination module 13, and a risk warning module 14.

[0097] A data acquisition module 11, configured to obtain the recorder video and GPS data of the target vehicle before and after the current time when the target vehicle generates vibrations at the current time, and obtain the in-vehicle video within a preset duration before the current time of the target vehicle. The GPS data is used to represent the position information and speed information of the target vehicle;

[0098] A risk determination module 12, configured to determine the first collision information according to the GPS data, determine the recorder video as the second collision information, and determine whether there is a risk of a collision occurring for the target vehicle according to the first collision information and the second collision information;

[0099] A working condition determination module 13, configured to, if so, determine at least one actual dangerous driving operation of the target driver within a preset duration before the current time according to the in-vehicle video, and determine the actual driving working condition of the target vehicle before the current time;

[0100] A risk warning module 14, configured to verify whether there is a risk of a collision occurring for the target vehicle according to each actual dangerous driving operation, the actual driving working condition, at least one target dangerous driving operation that the target driver is prone to, and the corresponding target driving working condition. If so, send a safety warning to the terminal of the collision verification personnel. The target driving working condition is a driving working condition that is prone to cause a collision accident when there is a corresponding target dangerous driving operation.

[0101] Optionally, the risk warning module 14 is specifically configured to:

[0102] Obtain the historical dangerous driving operations of the in-vehicle driver when historical vehicles had collisions, count the first occurrence times of each historical dangerous driving operation, and select the first number of historical dangerous driving operations from each historical dangerous driving operation in descending order of the first occurrence times to determine the target dangerous driving operations;

[0103] Obtain the historical driving working conditions of the vehicle when historical drivers had collision accidents under a single target dangerous driving operation, count the second occurrence times of each historical driving working condition, and select the second number of historical driving working conditions from each historical driving working condition in descending order of the second occurrence times to determine the target driving working conditions corresponding to the corresponding target dangerous driving operations;

[0104] Calculate the first weight of each target dangerous driving operation, and calculate the second weight of each target driving working condition corresponding to each target dangerous driving operation. The first weight is the ratio of the first occurrence times of each target dangerous driving operation to the sum of the first occurrence times of all target dangerous driving operations, and the second weight is the ratio of the second occurrence times of a single target driving working condition corresponding to the target dangerous driving operation to the sum of the second occurrence times of all target driving working conditions corresponding to the target dangerous driving operation;

[0105] Verify whether there is a risk of collision for the target vehicle based on each actual dangerous driving operation, actual driving condition, first weight, and corresponding second weights.

[0106] Optionally, the risk warning module 14 is specifically configured to:

[0107] Determine the target dangerous driving operations with actual driving conditions in the corresponding target driving conditions as key driving operations, and when the actual dangerous driving operation is a key driving operation, determine the corresponding actual dangerous driving operation as a reference driving operation;

[0108] Calculate the first product of the first weight of each reference driving operation and the second weight of the corresponding actual driving condition, and sum up the first products to obtain the sum of the first products;

[0109] If the sum of the first products is greater than the preset product sum threshold, verify that there is a risk of collision for the target vehicle.

[0110] Optionally, as Figure 4 shown, the device further includes an operation reminder module 15, which is specifically configured to:

[0111] If there is no risk of collision for the target vehicle, determine the current driving condition of the target vehicle, and determine the target dangerous driving operations with the current driving condition in the corresponding target driving conditions as important driving operations;

[0112] Calculate the second product of the first weight of each important driving operation and the second weight of the corresponding current driving condition, and sum up the second products to obtain the sum of the second products;

[0113] If the sum of the second products is greater than the preset product sum threshold, when there is at least one important driving operation for the target driver, determine the corresponding important driving operation as a risk driving operation, and determine the important driving operations other than the risk driving operation as remaining driving operations;

[0114] Select the largest second product from the second products corresponding to each remaining driving operation, and determine the remaining driving operation corresponding to the largest second product as a vigilant driving operation, and send a reminder message to the in-vehicle terminal of the target vehicle for the vigilant driving operation.

[0115] Optionally, the device further includes a condition reminder module 16, which is specifically configured to:

[0116] If the sum of the second products is not greater than the preset product sum threshold, calculate the third product of the first weight of each risk driving operation and the second weight of the corresponding target driving conditions;

[0117] Sum the third products corresponding to the same target driving condition to obtain the sum of the corresponding third products, and select the largest sum of the third products from the sums of the third products;

[0118] When the largest sum of the third products is greater than the preset product sum threshold, determine the target driving condition corresponding to the largest sum of the third products as the vigilant driving condition. If the vigilant driving condition is different from the current driving condition, send a reminder message to the in-vehicle terminal of the target vehicle for the vigilant driving condition.

[0119] Optionally, the device further includes a cause investigation module 17, which is specifically used for:

[0120] Obtain the historical dangerous driving operations of the driver in the vehicle when a historical vehicle collision occurs, count the first occurrence times of each historical dangerous driving operation, and select the first number of historical dangerous driving operations from each historical dangerous driving operation in descending order of the first occurrence times to determine the target dangerous driving operations;

[0121] Obtain the historical area where the collision location is located on the vehicle when a historical driver has a collision accident under a single target dangerous driving operation, count the third occurrence times of each historical area, and select the third number of historical areas from each historical area in descending order of the third occurrence times to determine the target area corresponding to the target dangerous driving operation;

[0122] Calculate the first weight of each target dangerous driving operation, and calculate the third weight of each target area corresponding to each target dangerous driving operation. The first weight is the ratio of the first occurrence times of each target dangerous driving operation to the sum of the first occurrence times of all target dangerous driving operations, and the third weight is the ratio of the third occurrence times of a single target area corresponding to the target dangerous driving operation to the sum of the third occurrence times of all corresponding target areas;

[0123] During the driving process of the target vehicle, if the target driver has a target dangerous driving operation, determine the corresponding target dangerous driving operation as the operation to be recorded, and establish a mapping relationship between each operation to be recorded and the corresponding occurrence time node in the real-time video. The real-time video is the driving video obtained in real time from the driving recorder in the target vehicle;

[0124] When the target vehicle switches from the driving state to the normal parking state and there are unknown collision marks, based on each mapping relationship, the first weight, and the corresponding third weights, investigate the cause of the appearance of the unknown collision marks.

[0125] Optionally, the cause investigation module 17 is specifically used for:

[0126] Determine the target area where the unknown collision trace is located as the key area, determine the target dangerous driving operation with the key area in each corresponding target area as the induced collision operation, determine the operation to be recorded in each induced collision operation as the final operation, and determine the corresponding final time node according to the mapping relationship of the final operation;

[0127] Calculate the fourth product of the first weight of each final operation and the third weight of the corresponding key area;

[0128] Determine the playback order of the corresponding final time node in the real-time video according to each fourth weight, and based on each playback order, investigate the cause of the appearance of the unknown collision trace. The larger the fourth product, the more forward the corresponding playback order.

[0129] It should be noted that when the vehicle collision recognition device provided in the above embodiment executes the vehicle collision recognition method, only the above division of each functional module is used for illustration. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the vehicle collision recognition device and the vehicle collision recognition method embodiment provided in the above embodiment belong to the same concept, and the implementation process is detailed in the method embodiment, which will not be repeated here.

[0130] The embodiment of the present application also discloses a computer-readable storage medium, and the computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, a vehicle collision recognition method of the above embodiment is adopted.

[0131] Among them, the computer program can be stored in a computer-readable medium. The computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some middleware form, etc. The computer-readable medium includes any entity or device, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium that can carry the computer program code. It should be noted that the computer-readable medium includes but is not limited to the above components.

[0132] Among them, through this computer-readable storage medium, a vehicle collision recognition method of the above embodiment is stored in the computer-readable storage medium, and is loaded and executed on the processor to facilitate the storage and application of the above method.

[0133] An embodiment of this application also discloses an electronic device. When a computer program stored in a computer-readable storage medium is loaded and executed by a processor, the above-mentioned vehicle collision recognition method is adopted.

[0134] Among them, the electronic device can be a desktop computer, a laptop computer, or a cloud server, etc. And the electronic device includes but is not limited to a processor and a memory. For example, the electronic device can also include input and output devices, network access devices, and a bus, etc.

[0135] Among them, the processor can adopt a central processing unit (CPU). Of course, according to the actual usage situation, other 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, etc. can also be adopted. The general-purpose processor can adopt a microprocessor or any conventional processor, etc. This application does not make any restrictions in this regard.

[0136] Among them, the memory can be an internal storage unit of the electronic device. For example, the hard disk or memory of the electronic device, or it can also be an external storage device of the electronic device. For example, a plug-in hard disk, a smart media card (SMC), a secure digital card (SD), or a flash card (FC), etc. equipped on the electronic device. And the memory can also be a combination of the internal storage unit and the external storage device of the electronic device. The memory is used to store the computer program and other programs and data required by the electronic device. The memory can also be used to temporarily store the data that has been output or will be output. This application does not make any restrictions in this regard.

[0137] Among them, through this electronic device, the above-mentioned vehicle collision recognition method of the embodiment is stored in the memory of the electronic device and is loaded and executed on the processor of the electronic device, which is convenient for use.

[0138] The above are only exemplary embodiments of the present disclosure and should not be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure still fall within the scope covered by the present disclosure. This application aims to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The description and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A vehicle collision recognition method, characterized in that, The method includes: When the target vehicle generates vibrations at the current time, obtain the recorder video and GPS data of the target vehicle before and after the current time, and obtain the in-vehicle video within a preset duration before the current time of the target vehicle. The GPS data is used to characterize the position information and speed information of the target vehicle; According to the GPS data, determine the first collision information, determine the recorder video as the second collision information, and determine whether there is a risk of collision occurring for the target vehicle according to the first collision information and the second collision information; If so, according to the in-vehicle video, determine at least one actual dangerous driving operation within a preset duration before the current time of the target driver, and determine the actual driving condition of the target vehicle before the current time; Verify whether there is a risk of collision occurring for the target vehicle according to each of the actual dangerous driving operations, the actual driving condition, at least one target dangerous driving operation that the target driver is prone to, and the corresponding target driving condition. If so, send a safety warning to the terminal of the collision verification personnel. The target driving condition is a driving condition that is prone to cause a collision accident when there is a corresponding target dangerous driving operation. Among them, the step of verifying whether there is a risk of collision occurring for the target vehicle according to each of the actual dangerous driving operations, the actual driving condition, at least one target dangerous driving operation that the target driver is prone to, and the corresponding target driving condition specifically includes: Obtain the historical dangerous driving operations of the in-vehicle driver when historical vehicles had collisions, count the first occurrence times of each of the historical dangerous driving operations, and select a first number of historical dangerous driving operations from each of the historical dangerous driving operations in descending order of the first occurrence times to be determined as the target dangerous driving operations; Obtain the historical driving conditions of the vehicle when historical drivers had collision accidents under a single target dangerous driving operation, count the second occurrence times of each of the historical driving conditions, and select a second number of historical driving conditions from each of the historical driving conditions in descending order of the second occurrence times to be determined as the target driving conditions corresponding to the corresponding target dangerous driving operations; Calculate the first weight of each of the target dangerous driving operations, and calculate the second weight of each of the target driving conditions corresponding to each of the target dangerous driving operations. The first weight is the ratio of the first occurrence times of each target dangerous driving operation to the sum of the first occurrence times of all target dangerous driving operations, and the second weight is the ratio of the second occurrence times of a single target driving condition corresponding to a target dangerous driving operation to the sum of the second occurrence times of all target driving conditions corresponding to the target dangerous driving operation; Based on each of the actual dangerous driving operations, the actual driving condition, the first weight, and the corresponding second weights, verify whether there is a risk of collision occurring for the target vehicle.

2. The vehicle collision recognition method according to claim 1, wherein The step of verifying whether there is a risk of collision occurring for the target vehicle based on each of the actual dangerous driving operations, the actual driving condition, the first weight, and the corresponding second weights specifically includes: Identify the target dangerous driving operations that exist in the corresponding target driving conditions as key driving operations in the actual driving condition. When the actual dangerous driving operation is a key driving operation, identify the corresponding actual dangerous driving operation as a reference driving operation; Calculate the first product of the first weight of each reference driving operation and the second weight of the corresponding actual driving condition, and sum up the first products to obtain the sum of the first products; If the sum of the first products is greater than a preset product sum threshold, verify that there is a risk of collision for the target vehicle.

3. The vehicle collision recognition method according to claim 1, wherein, The method further includes: If there is no risk of collision for the target vehicle, determine the current driving condition of the target vehicle, and identify the target dangerous driving operations that exist in the corresponding target driving conditions as important driving operations; Calculate the second product of the first weight of each important driving operation and the second weight of the corresponding current driving condition, and sum up the second products to obtain the sum of the second products; If the sum of the second products is greater than a preset product sum threshold, when there is at least one important driving operation for the target driver, identify the corresponding important driving operation as a risk driving operation, and identify the important driving operations other than the risk driving operation as remaining driving operations; Select the largest second product from the second products corresponding to each remaining driving operation, and identify the remaining driving operation corresponding to the largest second product as a vigilant driving operation, and send a reminder message to the in-vehicle terminal of the target vehicle for the vigilant driving operation.

4. The vehicle collision recognition method according to claim 3, characterized in that The method further includes: If the sum of the second products is not greater than a preset product sum threshold, calculate the third product of the first weight of each risk driving operation and the second weight of the corresponding target driving conditions; Sum up the third products corresponding to the same target driving condition to obtain the corresponding sum of the third products, and select the largest sum of the third products from the sums of the third products; When the largest sum of the third products is greater than a preset product sum threshold, identify the target driving condition corresponding to the largest sum of the third products as a vigilant driving condition. If the vigilant driving condition is different from the current driving condition, send a reminder message to the in-vehicle terminal of the target vehicle for the vigilant driving condition.

5. The vehicle collision recognition method according to claim 1, characterized in that, The method further includes: Obtain the historical dangerous driving operations of the driver in the vehicle when a historical vehicle collided, count the first occurrence times of each historical dangerous driving operation, and select the first number of historical dangerous driving operations from the historical dangerous driving operations in descending order of the first occurrence times as target dangerous driving operations; Obtain the historical areas on the vehicle where the collision position was located when the historical driver had a collision accident under a single target dangerous driving operation, count the third occurrence times of each historical area, and select the third number of historical areas from the historical areas in descending order of the third occurrence times to determine the target areas of the corresponding target dangerous driving operations; Calculate the first weight of each of the target dangerous driving operations, and calculate the third weight of each target area corresponding to each of the target dangerous driving operations. The first weight is the ratio of the first occurrence times of each target dangerous driving operation to the sum of the first occurrence times of all target dangerous driving operations. The third weight is the ratio of the third occurrence times of a single target area corresponding to a target dangerous driving operation to the sum of the third occurrence times of all target areas corresponding to the target dangerous driving operation; During the driving process of the target vehicle, if the target driver performs a target dangerous driving operation, determine the corresponding target dangerous driving operation as an operation to be recorded, and establish a mapping relationship between each operation to be recorded and the corresponding occurrence time node in the real-time video. The real-time video is the driving video obtained in real time from the driving recorder in the target vehicle; When the target vehicle switches from the driving state to the normal parking state and there are unknown collision marks, based on each of the mapping relationships, the first weight, and the corresponding third weights, investigate the cause of the appearance of the unknown collision marks.

6. The vehicle collision recognition method according to claim 5, wherein, The investigation of the cause of the appearance of the unknown collision marks based on each of the mapping relationships, the first weight, and the corresponding third weights specifically includes: Determine the target area where the unknown collision mark is located as the key area, determine the target dangerous driving operations in the corresponding target areas where the key area exists as the collision-inducing operations, determine the operations to be recorded existing in each of the collision-inducing operations as the final operations, and determine the corresponding final time nodes according to the mapping relationships of the final operations; Calculate the fourth product of the first weight of each of the final operations and the third weight of the corresponding key area; According to each of the fourth products, determine the playback order of the corresponding final time nodes in the real-time video, and based on each of the playback orders, investigate the cause of the appearance of the unknown collision marks. The larger the fourth product, the earlier the corresponding playback order.

7. A vehicle collision recognition device for implementing the vehicle collision recognition method according to any one of claims 1 to 6, characterized in that, Including: A data acquisition module (11), configured to, when the target vehicle generates vibration at the current time, acquire the recorder video and GPS data before and after the current time of the target vehicle, and acquire the in-vehicle video within a preset time period before the current time of the target vehicle. The GPS data is used to represent the position information and speed information of the target vehicle; A risk determination module (12), configured to determine the first collision information according to the GPS data, determine the recorder video as the second collision information, and determine whether there is a risk of collision occurring for the target vehicle according to the first collision information and the second collision information; A working condition determination module (13), configured to, if so, determine at least one actual dangerous driving operation of the target driver within a preset time period before the current time according to the in-vehicle video, and determine the actual driving working condition of the target vehicle before the current time; A risk warning module (14) is configured to verify whether there is a risk of a collision occurring for the target vehicle based on each of the actual dangerous driving operations, the actual driving conditions, at least one target dangerous driving operation that the target driver is prone to, and the corresponding target driving conditions. If so, a safety warning is sent to the terminal of the collision verification personnel, and the target driving conditions are driving conditions that are prone to cause a collision accident when there is a corresponding target dangerous driving operation.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by a processor, the method described in any one of claims 1-6 is adopted.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, When the processor loads and executes the computer program, the method described in any one of claims 1-6 is adopted.

Images