Methods, devices, and storage media for identifying intentional vehicle collisions

Abstract

This invention provides a method, apparatus, and storage medium for identifying intentional vehicle collision accidents. The method includes: S1, calculating the feature score of vehicle characteristics; S2, obtaining the feature score of road grid features; S3, determining the road condition feature score based on the basic road condition information corresponding to the road where the accident occurred; S4, determining the intentional collision accident feature value of the vehicle in the accident; S5, when the intentional collision accident feature value is within the confidence interval of the historical intentional collision accident feature value distribution, the accident is judged to be a suspected intentional collision accident. By combining the vehicle's own driving data, the road data the vehicle traveled on, the road grid situation where the vehicle accident occurred, and historical intentional collision accident data to analyze whether a vehicle accident is an intentional collision accident, the accuracy of the judgment is improved, which helps to reduce insurance fraud by drivers.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, and in particular to a method, device and storage medium for identifying intentional vehicle collision accidents. Background Technology

[0002] Traffic accidents can occur while a vehicle is in motion due to factors such as the driver, vehicle condition, and road conditions. Knowing about an accident as soon as possible is crucial for roadside assistance, traffic control, and insurance claims. In the past, to find out about an accident, people at the scene had to report it. From a software perspective, this method is inconvenient for accident registration, and the authenticity of the accident is uncontrollable. There is a possibility that the driver may intentionally cause a traffic accident to commit insurance fraud. Summary of the Invention

[0003] The present invention provides a method, apparatus and storage medium for identifying intentional vehicle collision accidents, so as to identify collision accidents caused by the driver's subjective intent.

[0004] To achieve the above objectives, on the one hand, a method for identifying intentional vehicle collision accidents is provided, including: S1, acquire vehicle driving data within a first preset time period from before the accident to the time of the accident, and calculate the feature score of each selected vehicle feature within the first preset time period based on the vehicle driving data using a preset calculation method, wherein the vehicle driving data includes: vehicle speed and vehicle acceleration; the selected vehicle features include: one or more of the following: maximum vehicle speed, maximum vehicle acceleration, average vehicle speed, and average vehicle acceleration. S2, for the first road grid to which the location of the accident belongs, obtain the vehicle speed and vehicle acceleration of all vehicles passing through the first road grid within the first preset time period, and based on the vehicle speed and vehicle acceleration of all vehicles passing through the first road grid, use a preset processing method to obtain the feature score of each selected road grid feature within the first preset time period for the first road grid, wherein the road grid is obtained by pre-dividing the road with a selected length and width; the selected road grid features include one or more of the following for all vehicles passing through the road grid: maximum vehicle speed, maximum vehicle acceleration, average speed, and average acceleration. S3, based on the basic road condition information corresponding to the road where the accident occurred, determine the road condition feature score of the road within the first predetermined time period, wherein the basic road condition information includes: at least one information item related to the inherent attributes of the road and the number of deliberate collisions that occurred on the road up to the time the accident occurred; S4, using a pre-set calculation method, determine the intentional collision accident feature value of the vehicle in the accident based on the feature score of each selected vehicle feature in the first preset time period, the feature score of each selected road grid feature in the first road grid, and the road condition feature score of the road. S5, when the feature value of the vehicle in the accident is located within the confidence interval of the distribution of historical intentional collision feature values ​​obtained in advance, the accident is determined to be a suspected intentional collision accident, wherein the confidence interval of the distribution of historical intentional collision feature values ​​is calculated in advance using the previously collected historical intentional collision dataset.

[0005] Preferably, in the identification method, at least one information item related to the inherent attributes of the road includes one or more of the following: Road length, road width, road curvature, road gradient, road traffic flow, road traffic density, average vehicle speed on the road, and road grade.

[0006] Preferably, in the identification method, in step S4, the following formula is used to determine the characteristic value of the intentional collision of the vehicle in the accident. :

[0007] in, This indicates the vehicle's speed at the time the accident occurred. This indicates the vehicle's acceleration at the time the accident occurred. The preset characteristic coefficients for this intentional collision accident are the following: The feature score of the maximum vehicle speed within the first preset time period, the The feature score of the maximum vehicle acceleration within the first preset time period, the The feature score of the average vehicle speed within the first preset time period; The feature score of the average vehicle acceleration within the first preset time period; The feature score is the maximum vehicle speed value of all vehicles passing through the first road grid within the first preset time period. The feature score is the maximum value of vehicle acceleration for all vehicles passing through the first road grid within the first preset time period; The feature score of the average speed of all vehicles passing through the first road grid within the first preset time period; The feature score is the average acceleration of all vehicles passing through the first road grid within the first preset time period; The road condition feature score is the score of the road within the first preset time period.

[0008] Preferably, in the identification method, the vehicle speed is a three-dimensional spatial speed, and the vehicle acceleration is a three-dimensional spatial acceleration; in step S1, calculating the feature score of each selected vehicle feature within the first preset time period using a pre-set calculation method includes one or more of the following steps: (1) Calculate the feature score of the maximum vehicle speed within the first preset time period using the following formula:

[0009] in, For dynamic weights, , , These represent the x-axis, y-axis, and z-axis velocity components of the i-th vehicle speed maximum value among the k vehicle speed maximum values ​​acquired within the first preset time period, where... m and n represent the velocity factor coefficients of the velocity components along the x-axis, y-axis, and z-axis, respectively. The feature score of the maximum vehicle speed; (2) Calculate the feature score of the maximum vehicle acceleration during the first preset time period using the following formula:

[0010] Let represent the x-axis, y-axis, and z-axis acceleration components of the i-th vehicle acceleration maximum among the k vehicle acceleration maxima acquired within the first preset time period, where o, p, and q represent the acceleration factor coefficients of the x-axis, y-axis, and z-axis acceleration components, respectively. The feature score of the maximum acceleration of the vehicle; (3) The average vehicle speed during the first preset time period is the standard normalized average vehicle speed, which is calculated using the following formula:

[0011] in, For dynamic weights, , , These represent the x-axis, y-axis, and z-axis velocity components of the i-th standard-normalized vehicle average speed among the k standard-normalized vehicle average speeds obtained within the first preset time period. , , The velocity factor coefficients, representing the velocity components along the x, y, and z axes of the normalized vehicle average speed, respectively. The feature score for the standard normalized average vehicle speed; (4) The average vehicle acceleration during the first preset time period is the normalized average vehicle acceleration, which is calculated using the following formula:

[0012] in, For dynamic weights, These represent the x-axis, y-axis, and z-axis acceleration components of the i-th standard-normalized vehicle average acceleration among the k standard-normalized vehicle average accelerations obtained within the first preset time period. , , The acceleration factor coefficients represent the acceleration components along the x, y, and z axes of the normalized vehicle average acceleration, respectively. The characteristic score of the standard normalized average acceleration.

[0013] Preferably, in the identification method, the vehicle speed is a three-dimensional spatial speed, and the vehicle acceleration is a three-dimensional spatial acceleration; in step S2, obtaining the feature score of each selected road grid feature within the first preset time period using a pre-set processing method includes one or more of the following steps: (1) Calculate the feature score of the maximum vehicle speed of all vehicles passing through the first road grid within the first preset time period using the following formula. :

[0014] in, For dynamic weights, , , Let x, y, and z represent the velocity components of the i-th maximum vehicle speed value among the t maximum vehicle speed values ​​of t vehicles passing through the first road grid within the first preset time period, respectively; l, m, and n represent the velocity factor coefficients of the velocity components of the x, y, and z axes, respectively. (2) Calculate the feature score of the maximum vehicle acceleration of all vehicles passing through the first road grid within the first preset time period using the following formula. :

[0015] in, Let x, y, and z represent the acceleration components of the i-th maximum acceleration value among the t maximum acceleration values ​​of t vehicles passing through the first road grid within the first preset time period, respectively. o, p, and q represent the acceleration factor coefficients of the acceleration components along the x, y, and z axes, respectively. (3) The average speed of all vehicles passing through the first road grid within the first preset time period is the standard normalized average speed of all vehicles. The feature score of the standard normalized average speed of all vehicles is calculated using the following formula. :

[0016] in, For dynamic weights, 、 、 These represent the x-axis, y-axis, and z-axis velocity components of the i-th average speed among the t standard-normalized average speeds of the t vehicles that passed through the first road grid within the first preset time period. , , The velocity factor coefficients of the velocity components of the x-axis, y-axis and z-axis respectively; (4) The average acceleration of all vehicles passing through the first road grid within the first preset time period is the standard normalized average acceleration of all vehicles. The feature score of the standard normalized average acceleration of all vehicles is calculated using the following formula. :

[0017] in, For dynamic weights, These represent the x-axis, y-axis, and z-axis acceleration components of the i-th average acceleration among the t normalized average accelerations of t vehicles passing through the first road grid within the first preset time period. , , These represent the acceleration factor coefficients of the acceleration components along the x-axis, y-axis, and z-axis, respectively.

[0018] Preferably, in the identification method, in step S4, the road condition feature score is a road condition feature score that has been standardized, and the road condition feature score is determined using the following formula. :

[0019] Where q is the number of road condition information items included in the basic road condition information. This represents the value corresponding to the i-th traffic information item. express The corresponding dynamic weights.

[0020] Preferably, in the identification method, the step of calculating the confidence interval of the distribution of feature values ​​of the historical intentional collision accidents using a pre-collected dataset of historical intentional collision accidents includes: 1) Calculate the average value of the d historical intentional collision feature values ​​for d historical accidents in the historical intentional collision accident dataset. :

[0021] This represents the average characteristics of historical intentional collision accidents. Let represent the characteristic value of the historical intentional collision accident of the i-th historical accident out of d historical accidents; 2) Calculate the sample variance of the d historical intentional collision accident feature values. :

[0022] = .

[0023] Preferably, in the identification method, the confidence interval of the distribution of historical intentional collision accident feature values ​​is a 90% confidence interval, and the 90% confidence interval P is calculated by the following formula: -1.645 +1.645 .

[0024] On the other hand, a device for identifying intentional vehicle collision accidents is provided, including a memory and a processor, wherein the memory stores at least one program, which is executed by the processor to implement the method for identifying intentional vehicle collision accidents as described above.

[0025] In another aspect, a computer-readable storage medium is provided, wherein the storage medium stores at least one program that is executed by a processor to implement the method of intentionally causing a vehicle collision as described in any of the above descriptions.

[0026] The above technical solution has the following technical effects: By combining the vehicle's own driving data, road data, road grid data where the accident occurred, and historical data on intentional collisions, the accuracy of the judgment is improved, which helps to reduce insurance fraud by drivers. Attached Figure Description

[0027] Figure 1 This is a flowchart illustrating a method for identifying intentional vehicle collision accidents according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of a vehicle intentional collision identification device according to an embodiment of the present invention. Detailed Implementation

[0028] To further illustrate the various embodiments, the present invention provides accompanying drawings. These drawings are part of the disclosure of the present invention and are mainly used to illustrate the embodiments, and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these drawings, those skilled in the art should be able to understand other possible implementations and the advantages of the present invention. Components in the drawings are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0029] The present invention will now be further described in conjunction with the accompanying drawings and specific embodiments.

[0030] Example 1: Figure 1 This is a flowchart illustrating a method for identifying intentional vehicle collision accidents according to an embodiment of the present invention. Figure 1 The method for identifying intentional vehicle collision accidents in this embodiment includes: S1, acquire vehicle driving data within a first preset time period from before the accident to the time of the accident, and calculate the feature score of each selected vehicle feature within the first preset time period based on the vehicle driving data using a preset calculation method. The vehicle driving data includes vehicle speed and vehicle acceleration; the selected vehicle features include one or more of the following: maximum vehicle speed, maximum vehicle acceleration, average vehicle speed, and average vehicle acceleration. In practice, the aforementioned vehicles are new energy vehicles or other types of vehicles; S2, for the first road grid to which the accident occurred, obtain the vehicle speed and vehicle acceleration of all vehicles passing through the first road grid within a first preset time period, and based on the vehicle speed and vehicle acceleration of all vehicles passing through the first road grid, use a preset processing method to obtain the feature score of each selected road grid feature within the first preset time period for the first road grid. Here, the road grid is obtained by pre-dividing the road using a selected length and width as units; the selected road grid features include one or more of the following for all vehicles passing through the road grid: maximum vehicle speed, maximum vehicle acceleration, average speed, and average acceleration. S3. Based on the basic road condition information corresponding to the road where the accident occurred, determine the road condition characteristic score of the road within a first predetermined time period. The basic road condition information includes at least one information item related to the inherent attributes of the road and the number of intentional collisions that occurred on the road up to the time of the accident. In one specific implementation, at least one information item related to the inherent attributes of the road includes one or more of the following: road length, road width, road curvature, road slope, road traffic flow, road traffic density, average vehicle speed on the road, and road grade. In one specific implementation, the number of intentional collisions that occurred on the road at the time of the accident is obtained by acquiring a historical dataset of intentional collisions that occurred on the road; in another case, the aforementioned historical dataset of intentional collisions can be obtained from an insurance company and used as a historical sample dataset. S4. Using a pre-set calculation method, the characteristic value of the intentional collision accident of the vehicle in the accident is determined based on the characteristic score of each selected vehicle feature in the first preset time period, the characteristic score of each selected road grid feature in the first road grid, and the road condition characteristic score. In one specific implementation, the following formula is used to determine the characteristic value of a deliberate collision involving the vehicle in the accident. :

[0031] in, This indicates the vehicle's speed at the time the accident occurred. This indicates the vehicle's acceleration at the time the accident occurred. This is the preset characteristic coefficient of the intentional collision accident corresponding to this incident. The feature score is the maximum value of vehicle speed within the first preset time period. The feature score is the maximum value of vehicle acceleration within the first preset time period. The feature score of the average vehicle speed within the first preset time period; The feature score of the average vehicle acceleration within the first preset time period; The feature score represents the maximum vehicle speed of all vehicles passing through the first road grid within the first preset time period. The feature score is the maximum value of vehicle acceleration for all vehicles passing through the first road grid within the first preset time period. The characteristic score of the average speed of all vehicles passing through the first road grid within the first preset time period; The feature score is the average acceleration of all vehicles passing through the first road grid within the first preset time period. The road condition characteristic score is the score of the road within the first preset time period; In one specific implementation The velocity in a three-dimensional coordinate system. , , , respectively represent the vehicle velocity components in the x, y and z coordinate directions of the three-dimensional spatial coordinate system, and l, m, n represent the factor coefficients of each spatial velocity component. For three-dimensional spatial acceleration in a three-dimensional coordinate system, , , , These represent the vehicle acceleration components along the x, y, and z axes in the three-dimensional spatial coordinate system, respectively; o, p, and q represent the factor coefficients of each spatial acceleration component. In practice, the above three-dimensional spatial velocity is the three-dimensional spatial velocity per second obtained using high-precision positioning data. In one specific implementation, the characteristic coefficient of a deliberate collision accident is determined based on the location type to which the accident occurred. The value of is determined by the following: For example, the selected city or total area is pre-divided into multiple different geographical types, including: densely populated urban areas, general urban areas, suburbs, and other types of areas; the number of historical intentional collisions n occurring in each location type area within a predetermined time period up to the time of the accident, and the total number of historical collisions k occurring in the entire selected city or total area are counted; the corresponding n is selected based on the location type to which the current accident occurred, and then... To determine the coefficients .

[0032] S5. When the feature value of the vehicle in the accident is located within the confidence interval of the distribution of historical intentional collision feature values ​​obtained in advance, the accident is judged to be a suspected intentional collision accident. Here, the confidence interval of the distribution of historical intentional collision feature values ​​is calculated in advance using the previously collected historical intentional collision dataset.

[0033] In one specific implementation, the identification method of this invention is implemented as a corresponding software system, such as an intentional collision feature calculation system.

[0034] In one specific implementation, the confidence interval of the distribution of historical intentional collision accident feature values ​​is determined by selecting the mean and variance of the historical intentional collision accident feature values ​​from multiple historical accidents.

[0035] In one specific implementation of this invention, the time and location of the accident are reported by the corresponding vehicle-mounted terminal. The road grid to which the accident belongs can be determined based on the accident's location. In another implementation, the time and location of the accident can be obtained from accident information provided by an insurance company.

[0036] In one specific implementation of this invention, the vehicle terminal uses a positioning system, such as the BeiDou satellite high-precision navigation and positioning system, to collect real-time driving data and historical driving data of the vehicle. For example, this includes high-precision three-dimensional positioning data (longitude, latitude, vertical height) of the vehicle while it is in motion, i.e. (Lon, Lat, Hgt). The vehicle terminal can use the three-dimensional positioning data to calculate the three-dimensional spatial velocity value of the vehicle, such as the three-dimensional spatial velocity value (Vx, Vy, Vz) per second, and calculate the three-dimensional spatial acceleration value (Ax, Ay, Az) of the vehicle.

[0037] In one specific implementation, the road surface is divided into 4m×2m grids; the 4m×2m unit is merely an example and can be replaced with other suitable road grid division units. The three-dimensional spatial velocity values ​​(Vx, Vy, Vz) and three-dimensional acceleration values ​​(Ax, Ay, Az) of each vehicle are recorded when traveling on different road grids.

[0038] In one specific implementation, after obtaining vehicle driving data from the vehicle dimension and driving data of all vehicles for the road grid from the road grid dimension, a data cleaning and analysis system is preferably used to process the data to extract the selected vehicle features and road grid features, and further calculate the corresponding feature scores of each selected feature.

[0039] In one specific implementation, step S1, using a pre-set calculation method, calculates the feature score of each selected vehicle feature within a first preset time period, including one or more of the following steps: (1) Calculate the feature score of the maximum vehicle speed within the first preset time period using the following formula:

[0040] in, For dynamic weights, , , These represent the x-axis, y-axis, and z-axis velocity components of the i-th vehicle speed maximum among k data points (i.e., k vehicle speed maxima) acquired within the first preset time period. m and n represent the velocity factor coefficients of the velocity components along the x-axis, y-axis, and z-axis, respectively. The feature score is the maximum value of vehicle speed; the first preset time length is less than the first preset time period; in one implementation, the first preset time period is divided into k first preset time lengths; i=1 to k represents the data sequence i to k obtained; for example, the first preset time period can be divided into k time segments according to the selected time interval length, and the corresponding maximum value of vehicle speed in each of the k time segments can be obtained respectively; the meaning of k is the same in the subsequent calculation of the maximum value of vehicle acceleration, the average speed of vehicle, and the average acceleration of vehicle dimension; (2) Calculate the characteristic score of the maximum vehicle acceleration during the first preset time period using the following formula:

[0041] Let represent the x-axis, y-axis, and z-axis acceleration components of the i-th vehicle acceleration maximum among the k vehicle acceleration maxima acquired within the first preset time period, where o, p, and q represent the acceleration factor coefficients of the x-axis, y-axis, and z-axis acceleration components, respectively. The feature score for the maximum value of vehicle acceleration; i=1 to k represents the acquired data sequence i to k; (3) The average vehicle speed during the first preset time period is the standard normalized average vehicle speed, which is calculated using the following formula:

[0042] in, For dynamic weights, , , These represent the x-axis, y-axis, and z-axis velocity components of the i-th standard normalized vehicle average speed among the k standard normalized vehicle average speeds obtained within the first preset time period. , , The velocity factor coefficients represent the velocity components along the x, y, and z axes of the normalized average vehicle speed, respectively. The feature score for the standard normalized average vehicle speed; i=1 to k represents the acquired data sequence i to k; for example, the above average speed is the average speed per hour; (4) The average vehicle acceleration during the first preset time period is the normalized average vehicle acceleration, which is calculated using the following formula:

[0043] in, For dynamic weights, These represent the x-axis, y-axis, and z-axis acceleration components of the i-th standard-normalized vehicle average acceleration among the k standard-normalized vehicle average accelerations obtained within the first preset time period. , , These are the acceleration factor coefficients representing the acceleration components along the x, y, and z axes of the normalized vehicle average acceleration, respectively. This represents the characteristic score of the standard normalized average acceleration. i=1 to k represents the acquired data sequence i to k. In one specific implementation, in step S2, using a pre-set processing method, obtaining the feature score of each selected road grid feature within a first preset time period for the first road grid includes one or more of the following steps: (1) Use the following formula to calculate the feature score of the maximum vehicle speed of all vehicles passing through the first road grid within the first preset time period. :

[0044] in, For dynamic weights, , , Let represent the x-axis, y-axis, and z-axis velocity components of the t maximum vehicle speed values ​​within the first preset time period, i.e., the t maximum vehicle speed values ​​of the t vehicles passing through the first road grid, and l, m, and n represent the velocity factor coefficients of the x-axis, y-axis, and z-axis velocity components, respectively. In this formula, t is the number of all vehicles passing through the first road grid; i = 1 to t represents the acquired data sequence i to t. (2) Use the following formula to calculate the feature score of the maximum vehicle acceleration of all vehicles passing through the first road grid within the first preset time period. :

[0045] in, Let represent the x-axis, y-axis, and z-axis acceleration components of the ith vehicle acceleration maximum among the t vehicle acceleration maximum values ​​of t vehicles passing through the first road grid within the first preset time period; o, p, and q represent the acceleration factor coefficients of the x-axis, y-axis, and z-axis acceleration components, respectively; i = 1 to t represents the acquired data sequence i to t; where t is the total number of vehicles passing through the first road grid. (3) The average speed of all vehicles passing through the first road grid within the first preset time period is the standard normalized average speed of all vehicles. The feature score of the standard normalized average speed of all vehicles is calculated using the following formula. :

[0046] in, For dynamic weights, 、 、 These represent the x-axis, y-axis, and z-axis velocity components of the i-th average speed among the t standardized normalized average speeds of vehicles passing through the first road grid within the first preset time period. , , The velocity factor coefficients represent the velocity components of the x-axis, y-axis, and z-axis, respectively; i = 1 to t represents the acquired data sequence i to t; the average speed mentioned above is, for example, the average speed per hour; in this formula, t is the number of all vehicles passing through the first road grid. (4) The average acceleration of all vehicles passing through the first road grid within the first preset time period is the standard normalized average acceleration of all vehicles. The characteristic score of the standard normalized average acceleration of all vehicles is calculated using the following formula. :

[0047] in, For dynamic weights, These represent the x-axis, y-axis, and z-axis acceleration components of the i-th average acceleration among the t normalized average accelerations of t vehicles passing through the first road grid within the first preset time period. , , These represent the acceleration factor coefficients for the acceleration components along the x, y, and z axes, respectively. In this formula, t represents the total number of vehicles passing through the first road grid.

[0048] In one specific implementation, in step S4, the road condition feature score is the road condition feature score after standard normalization, and the road condition feature score is determined using the following formula. :

[0049] Where q is the number of road condition information items included in the basic road condition information. This represents the value corresponding to the i-th traffic information item. express The corresponding dynamic weights.

[0050] In one implementation, the dynamic weights in the embodiments of the present invention are preset; for example, they are preset based on historical incidents.

[0051] In one specific implementation A score between 0 and 0.24 indicates poor basic road health. A score between 0.25 and 0.49 indicates a generally average level of road condition health. A score between 0.50 and 0.74 indicates good basic road health. A value between 0.75 and 1 indicates excellent basic road condition health; the larger the feature value of basic road condition information, the better the basic road condition health.

[0052] In one specific implementation, the steps of calculating the confidence interval of the distribution of feature values ​​of historical intentional collision accidents using a pre-collected dataset of historical intentional collision accidents include: 1) Calculate the average of the d historical intentional collision feature values ​​for d historical accidents in the historical intentional collision accident dataset. :

[0053] This represents the average characteristics of historical intentional collision accidents. Let represent the characteristic value of the historical intentional collision accident of the i-th historical accident out of d historical accidents; In practical implementation, each historical intentional collision incident characteristic value The specific calculation method is the same as the calculation method for Cv mentioned above; that is...

[0054] in, This represents the vehicle speed at the time of the i-th accident, such as three-dimensional vehicle speed. Represents the vehicle acceleration at the time of the i-th accident, such as three-dimensional vehicle acceleration; The characteristic coefficient of the intentional collision accident corresponding to the i-th accident is preset. In one implementation, it is preset based on historical experience. This is the feature score of the maximum vehicle speed within the preset time period corresponding to the i-th accident. This is the feature score of the maximum vehicle acceleration value within the preset time period corresponding to the i-th accident. The feature score of the average vehicle speed within the preset time period corresponding to the i-th accident; The feature score of the average vehicle acceleration within the preset time period corresponding to the i-th accident; This is the feature score of the maximum vehicle speed of all vehicles passing through the first road grid within the preset time period corresponding to the i-th accident. The feature score is the maximum value of vehicle acceleration of all vehicles passing through the first road grid within the preset time period corresponding to the i-th accident. The feature score of the average speed of all vehicles passing through the first road grid within the preset time period corresponding to the i-th accident. The feature score is the average vehicle acceleration of all vehicles passing through the first road grid within the preset time period corresponding to the i-th accident. The road condition characteristic score is the road condition score for the road within the preset time period corresponding to the i-th accident.

[0055] 2) Calculate the sample variance of the feature values ​​of d historical intentional collision accidents. :

[0056] = .

[0057] In one specific implementation, the confidence interval for the distribution of historical intentional collision accident characteristic values ​​is a 90% confidence interval, and the 90% confidence interval P is calculated using the following formula: -1.645 +1.645 .

[0058] Where d is the total number of samples of historical intentional collision accident characteristic values.

[0059] like If so, the corresponding accident is considered to be a suspected intentional collision accident.

[0060] In other implementations, the confidence interval P can be selected from other appropriate percentage confidence intervals, such as selecting an appropriate percentage confidence interval from the range of 80%-95%.

[0061] In one specific implementation, after determining that an accident is a suspected intentional collision, targeted management is implemented. This information is transmitted to the insurance company, for example, through a vehicle-to-everything (V2X) system, as a warning of intentional collision risk. Based on this warning, the insurance company can, in conjunction with public security and traffic police departments, conduct on-site investigations based on the intentional collision severity report. Once the investigators confirm it as an actual intentional collision, the accident is recorded as a historical intentional collision, and its various characteristic values ​​are fed back to the corresponding intentional collision characteristic calculation system or device to iteratively calculate the average value of historical intentional collision characteristic values. Variance of historical intentional collision accident samples This allows for closed-loop management, which can reduce economic losses caused by insurance fraud through deliberate collisions.

[0062] Example 2: The present invention also provides a device for identifying intentional vehicle collision accidents, such as... Figure 2 As shown, the device includes a processor 201, a memory 202, a bus 203, and a computer program stored in the memory 202 and executable on the processor 201. The processor 201 includes one or more processing cores. The memory 202 is connected to the processor 201 via the bus 203. The memory 202 is used to store program instructions. When the processor executes the computer program, it implements the steps in the above-described method embodiment of Embodiment 1 of the present invention.

[0063] Furthermore, as an executable solution, the device for identifying intentional vehicle collisions can be a computer unit, which can be a desktop computer, laptop, handheld computer, or cloud server, among other computing devices. The computer unit may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above-described structure of the computer unit is merely an example and does not constitute a limitation on the computer unit. It may include more or fewer components, or combine certain components, or use different components. For example, the computer unit may also include input / output devices, network access devices, buses, etc., and this embodiment of the invention does not limit this.

[0064] Furthermore, as an executable solution, the processor can be a Central Processing Unit (CPU), or 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. The general-purpose processor can be a microprocessor or any conventional processor, etc. The processor is the control center of the computer unit, connecting various parts of the entire computer unit via various interfaces and lines.

[0065] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the computer unit by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital card (SD card), flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0066] Example 3: The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described in the embodiments of the present invention.

[0067] If the modules / units integrated in the computer unit are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction.

[0068] Although the invention has been specifically shown and described in conjunction with preferred embodiments, those skilled in the art should understand that various changes in form and detail may be made to the invention without departing from the spirit and scope of the invention as defined in the appended claims, all of which shall be within the scope of protection of the invention.

Claims

1. A method for identifying intentional vehicle collision accidents, characterized in that, include: S1, acquire vehicle driving data within a first preset time period from before the accident to the time of the accident, and calculate the feature score of each selected vehicle feature within the first preset time period based on the vehicle driving data using a preset calculation method, wherein the vehicle driving data includes: vehicle speed and vehicle acceleration; the selected vehicle features include: one or more of the following: maximum vehicle speed, maximum vehicle acceleration, average vehicle speed, and average vehicle acceleration. S2, for the first road grid to which the location of the accident belongs, obtain the vehicle speed and vehicle acceleration of all vehicles passing through the first road grid within the first preset time period, and based on the vehicle speed and vehicle acceleration of all vehicles passing through the first road grid, use a preset processing method to obtain the feature score of each selected road grid feature within the first preset time period for the first road grid, wherein the road grid is obtained by pre-dividing the road with a selected length and width; the selected road grid features include one or more of the following for all vehicles passing through the road grid: maximum vehicle speed, maximum vehicle acceleration, average speed, and average acceleration. S3, based on the basic road condition information corresponding to the road where the accident occurred, determine the road condition feature score of the road within the first preset time period, wherein the basic road condition information includes: at least one information item related to the inherent attributes of the road and the number of deliberate collisions that occurred on the road up to the time the accident occurred; S4, using a pre-set calculation method, determine the intentional collision accident feature value of the vehicle in the accident based on the feature score of each selected vehicle feature in the first preset time period, the feature score of each selected road grid feature in the first road grid, and the road condition feature score of the road. S5, when the feature value of the vehicle in the accident is located within the confidence interval of the distribution of historical intentional collision feature values ​​obtained in advance, the accident is determined to be a suspected intentional collision accident, wherein the confidence interval of the distribution of historical intentional collision feature values ​​is calculated in advance using the previously collected historical intentional collision dataset.

2. The identification method according to claim 1, characterized in that, At least one information item related to the inherent properties of the road includes one or more of the following: Road length, road width, road curvature, road gradient, road traffic flow, road traffic density, average vehicle speed on the road, and road grade.

3. The identification method according to claim 1, characterized in that, In step S4, the following formula is used to determine the characteristic value of the intentional collision of the vehicle in the accident. : in, This indicates the vehicle's speed at the time the accident occurred. This indicates the vehicle's acceleration at the time the accident occurred. The preset characteristic coefficients for this intentional collision accident are the following: The feature score of the maximum vehicle speed within the first preset time period, the The feature score of the maximum vehicle acceleration within the first preset time period, the The feature score of the average vehicle speed within the first preset time period; The feature score of the average vehicle acceleration within the first preset time period; The feature score is the maximum vehicle speed value of all vehicles passing through the first road grid within the first preset time period. The feature score is the maximum value of vehicle acceleration for all vehicles passing through the first road grid within the first preset time period; The feature score is the average speed of all vehicles passing through the first road grid within the first preset time period; The feature score is the average acceleration of all vehicles passing through the first road grid within the first preset time period; The road condition feature score is the score of the road within the first preset time period.

4. The identification method according to claim 1, characterized in that, The vehicle speed is a three-dimensional spatial speed, and the vehicle acceleration is a three-dimensional spatial acceleration; in step S1, using a pre-set calculation method, the feature score of each selected vehicle feature within the first preset time period is calculated, including one or more of the following steps: (1) Calculate the feature score of the maximum vehicle speed within the first preset time period using the following formula: in, For dynamic weights, , , These represent the x-axis, y-axis, and z-axis velocity components of the i-th vehicle speed maximum value among the k vehicle speed maximum values ​​obtained within the first preset time period, where... m and n represent the velocity factor coefficients of the velocity components along the x-axis, y-axis, and z-axis, respectively. The feature score of the maximum speed of the vehicle; (2) Calculate the feature score of the maximum vehicle acceleration during the first preset time period using the following formula: Let represent the x-axis, y-axis, and z-axis acceleration components of the i-th vehicle acceleration maximum among the k vehicle acceleration maxima acquired within the first preset time period, where o, p, and q represent the acceleration factor coefficients of the x-axis, y-axis, and z-axis acceleration components, respectively. The feature score of the maximum acceleration of the vehicle; (3) The average vehicle speed during the first preset time period is the standard normalized average vehicle speed, which is calculated using the following formula: in, For dynamic weights, , , These represent the x-axis, y-axis, and z-axis velocity components of the i-th standard-normalized vehicle average speed among the k standard-normalized vehicle average speeds obtained within the first preset time period. , , The velocity factor coefficients, representing the velocity components along the x, y, and z axes of the normalized vehicle average speed, respectively. The feature score for the standard normalized average vehicle speed; (4) The average vehicle acceleration during the first preset time period is the normalized average vehicle acceleration, which is calculated using the following formula: in, For dynamic weights, These represent the x-axis, y-axis, and z-axis acceleration components of the i-th standard-normalized vehicle average acceleration among the k standard-normalized vehicle average accelerations obtained within the first preset time period. , , The acceleration factor coefficients represent the acceleration components along the x, y, and z axes of the normalized vehicle average acceleration, respectively. The characteristic score of the standard normalized average acceleration.

5. The identification method according to claim 1, characterized in that, The vehicle speed is a three-dimensional spatial speed, and the vehicle acceleration is a three-dimensional spatial acceleration; in step S2, using a pre-set processing method, obtaining the feature score of each selected road grid feature within the first preset time period for the first road grid includes one or more of the following steps: (1) Calculate the feature score of the maximum vehicle speed of all vehicles passing through the first road grid within the first preset time period using the following formula. : in, For dynamic weights, , , Let x, y, and z represent the velocity components of the i-th maximum vehicle speed value among the t maximum vehicle speed values ​​of t vehicles passing through the first road grid within the first preset time period, respectively; l, m, and n represent the velocity factor coefficients of the velocity components of the x, y, and z axes, respectively. (2) Calculate the feature score of the maximum vehicle acceleration of all vehicles passing through the first road grid within the first preset time period using the following formula. : in, Let x, y, and z represent the acceleration components of the i-th vehicle's acceleration maximum value among the t maximum acceleration values ​​of t vehicles passing through the first road grid within the first preset time period, respectively. o, p, and q represent the acceleration factor coefficients of the acceleration components along the x, y, and z axes, respectively. (3) The average speed of all vehicles passing through the first road grid within the first preset time period is the standard normalized average speed of all vehicles. The feature score of the standard normalized average speed of all vehicles is calculated using the following formula. : in, For dynamic weights, 、 、 These represent the x-axis, y-axis, and z-axis velocity components of the i-th average speed among the t normalized average speeds of t vehicles passing through the first road grid within the first preset time period. , , The velocity factor coefficients of the velocity components of the x-axis, y-axis and z-axis respectively; (4) The average acceleration of all vehicles passing through the first road grid within the first preset time period is the standard normalized average acceleration of all vehicles. The feature score of the standard normalized average acceleration of all vehicles is calculated using the following formula. : in, For dynamic weights, These represent the x-axis, y-axis, and z-axis acceleration components of the i-th average acceleration among the t normalized average accelerations of t vehicles passing through the first road grid within the first preset time period. , , These represent the acceleration factor coefficients of the acceleration components along the x-axis, y-axis, and z-axis, respectively.

6. The identification method according to claim 1, characterized in that, In step S4, the road condition feature score is the road condition feature score after standard normalization, and the road condition feature score is determined using the following formula. : Where q is the number of road condition information items included in the basic road condition information. This represents the value corresponding to the i-th traffic information item. express The corresponding dynamic weights.

7. The identification method according to claim 1, characterized in that, The steps for calculating the confidence interval of the distribution of historical intentional collision feature values ​​using a pre-collected dataset of historical intentional collision accidents include: 1) Calculate the average value of the d historical intentional collision feature values ​​for d historical accidents in the historical intentional collision accident dataset. : This represents the average characteristics of historical intentional collision accidents. Let represent the characteristic value of the historical intentional collision accident of the i-th historical accident out of d historical accidents; 2) Calculate the sample variance of the d historical intentional collision accident feature values. : = 。 8. The identification method according to claim 7, characterized in that, The confidence interval for the distribution of the characteristic values ​​of the historical intentional collision accidents is a 90% confidence interval, and the 90% confidence interval P is calculated using the following formula: -1.645 +1.645 。 9. A device for identifying intentional vehicle collision accidents, characterized in that, The system includes a memory and a processor, the memory storing at least one program that is executed by the processor to implement the method for identifying intentional vehicle collisions as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The storage medium stores at least one program, which is executed by a processor to implement the method for deliberately causing a vehicle collision as described in any one of claims 1 to 8.

Images