Vehicle risk determination method, apparatus, electronic device, and computer medium

Abstract

The application relates to the technical field of vehicles and provides a vehicle risk determination method and device, electronic equipment and a computer medium. The method comprises the following steps: determining the driving track of a target vehicle according to the mobile signaling of the driver corresponding to the target vehicle; determining the initial estimated fuel consumption of the target vehicle based on the driving track; determining the target estimated fuel consumption of the target vehicle based on the initial estimated fuel consumption and an improved proximity algorithm; and determining the risk level of the target vehicle based on the target estimated fuel consumption and the actual fuel consumption of the target vehicle. The application accurately determines the driving track of the target vehicle through mobile signaling, preliminarily estimates the fuel consumption of the target vehicle based on the driving track, determines the final fuel consumption of the target vehicle according to the preliminarily estimated fuel consumption and the improved proximity algorithm, and determines the risk level of the target vehicle in combination with the actual fuel consumption, so that whether the target vehicle is abnormally used can be accurately determined according to the risk level of the target vehicle.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, specifically to a method, apparatus, electronic device, and computer medium for determining vehicle risks. Background Technology

[0002] Currently, data such as mileage and fuel invoice amounts are used to determine whether official vehicles are being used improperly. However, assessing the risk of misuse of official vehicles based solely on mileage and fuel invoice amounts is inaccurate because these data cannot provide the vehicle's travel history, and the fuel consumption data calculated from them cannot determine whether the trip was unusual. Therefore, it is impossible to accurately determine whether official vehicles are being used improperly. Summary of the Invention

[0003] This application provides a method, apparatus, electronic device, and computer medium for determining vehicle risks, in order to solve the current technical problem that it is impossible to accurately determine whether a public vehicle is being used abnormally.

[0004] Firstly, this application provides a method for determining vehicle risk, including:

[0005] The driving trajectory of the target vehicle is determined based on the movement signaling of the driver corresponding to the target vehicle;

[0006] The initial estimated fuel consumption of the target vehicle is determined based on the driving trajectory;

[0007] The target estimated fuel consumption of the target vehicle is determined based on the initial estimated fuel consumption combined with the improved nearest neighbor algorithm;

[0008] The risk level of the target vehicle is determined based on the target estimated fuel consumption and the actual fuel consumption of the target vehicle.

[0009] Optionally, the step of determining the target estimated fuel consumption of the target vehicle based on the initial estimated fuel consumption combined with the improved nearest neighbor algorithm includes:

[0010] Fuel consumption weights are determined based on the risk source data of the target vehicle;

[0011] The initial estimated fuel consumption dataset is determined based on the fuel consumption weights and the initial estimated fuel consumption.

[0012] The target expected fuel consumption of the target vehicle is determined based on the initial expected fuel consumption dataset and the improved nearest neighbor algorithm.

[0013] Optionally, the step of determining the target expected fuel consumption of the target vehicle based on the initial expected fuel consumption dataset and the improved nearest neighbor algorithm includes:

[0014] The target expected fuel consumption dataset is determined based on the initial expected fuel consumption dataset, the standard fuel consumption of the target vehicle, and the improved nearest neighbor algorithm.

[0015] The target expected fuel consumption of the target vehicle is obtained by averaging the target expected fuel consumption dataset.

[0016] Optionally, the distance calculation formula of the improved proximity algorithm includes the fuel consumption weight.

[0017] Optionally, the step of determining the driving trajectory of the target vehicle based on the movement signaling of the driver corresponding to the target vehicle includes:

[0018] The target vehicle's trajectory point dataset is determined based on the movement signaling of the driver corresponding to the target vehicle combined with the time-of-arrival positioning algorithm.

[0019] The driving trajectory of the target vehicle is determined based on the driving trajectory point dataset.

[0020] Optionally, the step of determining the initial estimated fuel consumption of the target vehicle based on the driving trajectory includes:

[0021] The mileage of the target vehicle is determined based on the driving trajectory.

[0022] The initial estimated fuel consumption of the target vehicle is calculated based on the mileage traveled.

[0023] Optionally, the step of determining the risk level of the target vehicle based on the target projected fuel consumption and the actual fuel consumption of the target vehicle includes:

[0024] The ratio of the target estimated fuel consumption to the actual fuel consumption of the target vehicle is calculated.

[0025] The risk level of the target vehicle is determined based on the result of the ratio calculation.

[0026] Secondly, this application provides a vehicle risk determination device, comprising:

[0027] The first determining module is used to determine the driving trajectory of the target vehicle based on the movement signaling of the driver corresponding to the target vehicle.

[0028] The second determining module is used to determine the initial estimated fuel consumption of the target vehicle based on the driving trajectory;

[0029] The third determining module is used to determine the target estimated fuel consumption of the target vehicle based on the initial estimated fuel consumption combined with the improved proximity algorithm;

[0030] The fourth determining module is used to determine the risk level of the target vehicle based on the target estimated fuel consumption and the actual fuel consumption of the target vehicle.

[0031] Thirdly, this application provides an electronic device including a processor and a memory storing a computer program, wherein the processor executes the program to implement the steps of the vehicle risk determination method described in the first or second aspect.

[0032] Fourthly, this application provides a computer medium, which is a computer-readable storage medium, on which a vehicle risk determination program is stored, and when the vehicle risk determination program is executed by a processor, it implements the steps of the vehicle risk determination method described in the first or second aspect.

[0033] The vehicle risk determination method, device, electronic equipment, and computer medium provided in this application accurately determine the driving trajectory of the target vehicle through mobile signaling, and preliminarily predict the fuel consumption of the target vehicle based on the driving trajectory. The final fuel consumption of the target vehicle is determined based on the preliminarily predicted fuel consumption combined with an improved proximity algorithm. The risk level of the target vehicle is determined based on the final predicted fuel consumption and the actual fuel consumption. Based on the risk level of the target vehicle, it can be accurately determined whether the target vehicle is being used abnormally. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 This is one of the flowcharts illustrating the vehicle risk determination method provided in the embodiments of this application;

[0036] Figure 2 This is a schematic diagram of a scenario for the vehicle risk determination method provided in the embodiments of this application;

[0037] Figure 3 This is a second schematic flowchart of the vehicle risk determination method provided in the embodiments of this application;

[0038] Figure 4 This is a schematic diagram illustrating a scenario using the KNN algorithm in existing technologies.

[0039] Figure 5 This application provides a third flowchart illustrating the vehicle risk determination method.

[0040] Figure 6This is a functional module diagram of an embodiment of the vehicle risk determination device of this application;

[0041] Figure 7 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0043] Figure 1 This is one of the flowcharts illustrating the vehicle risk determination method provided in this application. (Refer to...) Figure 1 This application provides a method for determining vehicle risk, which may include:

[0044] Step S100: Determine the driving trajectory of the target vehicle based on the movement signaling of the driver corresponding to the target vehicle;

[0045] The vehicle risk determination method in this embodiment can be applied to electronic devices such as smartphones, tablets, PCs, and servers. In this embodiment, to determine the risk of a bus trip, the bus currently requiring risk determination is designated as the target vehicle. Risk source data of the target vehicle during the specified trip is collected from a pre-set bus management system. Here, "bus" in this application refers to official vehicles. Risk source data may include actual fuel consumption, standard fuel consumption, mileage, number of refuelings, refueling amount, fuel type, vehicle brand, vehicle quality, and road conditions of the day. It may also include the mobile phone number of the driver corresponding to the target vehicle. The mobile signaling of the driver's mobile terminal during the current trip can be obtained based on the driver's mobile phone number. Here, mobile signaling refers to mobile communication signaling. In a mobile communication system, it is a useful signal that is distinct from communication signals. Signals other than voice signals are collectively referred to as "signaling".

[0046] After obtaining the movement signaling of the driver corresponding to the target vehicle during this trip, the bus's trajectory point dataset can be obtained by combining the movement signaling with the TOA (time of arrival) algorithm. Road matching is then performed based on this trajectory point dataset to obtain the target vehicle's travel trajectory. Accurately determining the target vehicle's trajectory using the driver's movement signaling allows for subsequent determination of the target vehicle's initial estimated fuel consumption, leading to a more accurate assessment of the target vehicle's risk level.

[0047] Step S200: Determine the initial estimated fuel consumption of the target vehicle based on the driving trajectory;

[0048] After determining the target vehicle's travel trajectory, this embodiment can determine the target vehicle's mileage for this trip based on the trajectory, and further calculate the target vehicle's fuel consumption for this trip based on the mileage and standard fuel consumption as the initial estimated fuel consumption. The calculated travel trajectory allows for a preliminary estimate of the target vehicle's fuel consumption for this trip, facilitating the subsequent determination of the target vehicle's target estimated fuel consumption based on the initial estimated fuel consumption and the improved proximity algorithm. This makes the subsequent determination of the target vehicle's risk level more accurate.

[0049] Step S300: Determine the target estimated fuel consumption of the target vehicle based on the initial estimated fuel consumption combined with the improved proximity algorithm;

[0050] It should be noted that this embodiment improves upon the original nearest neighbor algorithm, specifically using the KNN algorithm. KNN stands for K Nearest Neighbors, a classification algorithm primarily used for data classification. The principle of KNN is to determine the category of a sample point based on the categories of its K nearest neighbors. The specific improvement in this embodiment is the addition of a fuel consumption weight to the Euclidean distance calculation formula. This weight can be determined based on the vehicle's risk source data.

[0051] Therefore, after initially estimating the fuel consumption of the target vehicle for this trip, this embodiment can determine the fuel consumption weight of the target vehicle based on the risk source data of the target vehicle during the specified trip collected from the public transportation management system. Based on the determined fuel consumption weight and the initial estimated fuel consumption, an initial estimated fuel consumption dataset is determined, which includes multiple initial estimated fuel consumption data points. Furthermore, the target estimated fuel consumption of the target vehicle is determined based on the initial estimated fuel consumption dataset and the improved nearest neighbor algorithm. By combining the initial estimated fuel consumption with the improved nearest neighbor algorithm including fuel consumption weights, the fuel consumption of the target vehicle can be accurately determined as the target estimated fuel consumption, facilitating the subsequent accurate determination of the target vehicle's risk level based on the target estimated fuel consumption and the actual fuel consumption of the target vehicle.

[0052] Step S400: Determine the risk level of the target vehicle based on the target estimated fuel consumption and the actual fuel consumption of the target vehicle.

[0053] After determining the target estimated fuel consumption of the target vehicle, this embodiment compares the target estimated fuel consumption with the actual fuel consumption of the target vehicle during the current trip, and determines the risk level of the target vehicle based on the comparison result. In this embodiment, there can be multiple risk levels, such as no risk, low risk, medium risk, and high risk. Determining the risk level of the target vehicle by comparing the target estimated fuel consumption with the actual fuel consumption allows assessors to accurately determine whether there are any abnormalities in the target vehicle's current trip, such as whether the driver of the target vehicle is using the vehicle for personal purposes during the trip. The vehicle risk determination method provided in this application embodiment accurately determines the driving trajectory of the target vehicle based on mobile signaling, initially estimates the fuel consumption of the target vehicle based on the driving trajectory, determines the final fuel consumption of the target vehicle based on the initially estimated fuel consumption combined with an improved proximity algorithm, and determines the risk level of the target vehicle based on the final predicted fuel consumption and the actual fuel consumption. Based on the risk level of the target vehicle, it is possible to accurately determine whether there is any abnormal use of the target vehicle.

[0054] In one embodiment, the step of determining the driving trajectory of the target vehicle based on the movement signaling of the driver corresponding to the target vehicle includes:

[0055] Step S101: Determine the target vehicle's trajectory point dataset based on the mobile signaling of the driver corresponding to the target vehicle combined with the time-of-arrival positioning algorithm.

[0056] Step S102: Determine the driving trajectory of the target vehicle based on the driving trajectory point dataset.

[0057] After collecting the mobile phone number of the driver corresponding to the target vehicle, this embodiment can further obtain the mobile signaling corresponding to the mobile phone number. Based on the mobile signaling, the time it takes for the signal transmitted by the mobile terminal to reach the nearby base station is calculated. The transmitted signal needs to include the signal transmission time to determine the distance between the base station and the mobile station (i.e., the mobile terminal). Then, the driving trajectory points of the target vehicle are calculated based on the distance between the base station and the mobile station. The specific calculation process is as follows:

[0058] Reference Figure 2 , Figure 2 This is a schematic diagram of a scenario for the vehicle risk determination method provided in this application embodiment; this embodiment Figure 2There are three mobile base stations, BTS1, BTS2, and BTS3, and a mobile terminal X carried by the driver. Let T1, T2, and T3 be the times when the signal transmitted by mobile terminal X arrives at each base station (BTS1, BTS2, and BTS3), respectively, and let the base station times when mobile terminal X transmits its signal be T01, T02, and T03, respectively. Given that the coordinates of base stations BTS1, BTS2, and BTS3 are (X1, Y1), (X2, Y2), and (X3, Y3), respectively, and assuming the coordinates of mobile terminal X are (X, Y), the positional relationship expression is as follows:

[0059] (X-X1) 2 +(Y-Y1) 2 =C 2 *(T1-T01) 2

[0060] (X-X2) 2 +(Y-Y2) 2 =C 2 *(T2-T02) 2

[0061] (X-X3) 2 +(Y-Y3) 2 =C 2 *(T3-T03) 2

[0062] Where C is the electromagnetic wave transmission speed, X and Y are the horizontal and vertical coordinates of mobile terminal X, (X1, Y1), (X2, Y2), and (X3, Y3) are the coordinates of base stations BTS1, BTS2, and BTS3, respectively, T1, T2, and T3 are the times when the transmitted signal of mobile terminal X arrives at BTS1, BTS2, and BTS3, respectively, and the base station times when mobile terminal X transmits the signal are T01, T02, and T03, respectively.

[0063] Based on the above positional relationship expression, the coordinates of the mobile terminal at each time point in this trip can be calculated, which can represent the coordinates of the target vehicle at each time point in this trip, and form a dataset of the target vehicle's driving trajectory points from all the coordinates.

[0064] After obtaining the target vehicle's trajectory point dataset, the coordinates of each point in the dataset are connected sequentially, and the resulting trajectory is matched with various road trajectories. The road trajectory that most closely matches the resulting trajectory is identified as the target vehicle's trajectory. By combining the target vehicle's driver's movement signaling with a time-of-arrival (TOA) localization algorithm, the target vehicle's trajectory can be accurately determined. This allows for the subsequent determination of the target vehicle's initial estimated fuel consumption, leading to a more accurate assessment of the target vehicle's risk level.

[0065] Figure 3 This is a second schematic flowchart illustrating the vehicle risk determination method provided in this application's embodiments. (Refer to...) Figure 3 In one embodiment, the step of determining the initial estimated fuel consumption of the target vehicle based on the driving trajectory includes:

[0066] Step S201: Determine the mileage of the target vehicle based on the driving trajectory;

[0067] Step S202: Calculate the initial estimated fuel consumption of the target vehicle based on the mileage.

[0068] After determining the target vehicle's driving trajectory, this embodiment can calculate the target vehicle's mileage along that trajectory based on the trajectory and a map. Further, the mileage is multiplied by the obtained standard fuel consumption to obtain the fuel consumption required for that trajectory, serving as the initial estimated fuel consumption for the target vehicle. This embodiment, after obtaining an accurate driving trajectory, can first determine the mileage and then preliminarily estimate the target vehicle's fuel consumption based on that mileage to obtain the initial estimated fuel consumption. This facilitates the subsequent determination of the target vehicle's target estimated fuel consumption based on the initial estimated fuel consumption and the improved proximity algorithm, making the subsequently determined risk level of the target vehicle more accurate.

[0069] In one embodiment, the step of determining the target estimated fuel consumption of the target vehicle based on the initial estimated fuel consumption combined with the improved nearest neighbor algorithm includes:

[0070] Step S301: Determine fuel consumption weights based on the risk source data of the target vehicle;

[0071] Step S302: Determine the initial estimated fuel consumption dataset based on the fuel consumption weight and the initial estimated fuel consumption;

[0072] Step S303: Determine the target expected fuel consumption of the target vehicle based on the initial expected fuel consumption dataset and the improved nearest neighbor algorithm.

[0073] Reference Figure 4 , Figure 4 This is a schematic diagram illustrating a scenario using the KNN algorithm in existing technologies; for example... Figure 4As shown in the diagram, point 1 is the sample point, i.e., the point to be classified. Nearby are already classified points 2, 3, and 4. When K is 3, if among the three nearest classified points to the sample point, points 2 and 3 are yellow, and point 4 is red, then since the number of yellow points around point 1 is greater than the number of red points, the color category of the point to be classified, point 1, is determined to be yellow. Clearly, the traditional KNN algorithm is a non-parametric, lazy algorithm model. However, vehicle fuel consumption data is affected by various factors, which can influence our judgment results and cause classification errors. Therefore, this embodiment improves the traditional KNN algorithm to enhance the accuracy of classification.

[0074] It should be noted that the steps for fuel consumption analysis based on the KNN algorithm are as follows: 1. Construct a fuel consumption risk training dataset; specifically, obtain training samples for three types of fuel consumption through data analysis, and use p1, p2, and p3 to represent the high, medium, and low risk levels of fuel consumption, respectively. Classify the actual fuel consumption data x obtained from the bus management system. The distance between the actual data x to be classified and each training sample can be calculated. This distance is the similarity between the actual data and the sample data. The higher the similarity, the closer the actual data is to the sample data. For example, the similarity between sample x1 and p1, p2, and p3 are 0.9, 0.7, and 0.1, respectively, indicating that the actual fuel consumption data x1 is closer to the sample data p1, and the fuel consumption data may have a higher risk.

[0075] 2. Calculate the distance between the training fuel consumption risk dataset and the actual fuel consumption data; specifically, in the KNN algorithm, the method used to calculate the distance between the actual data and the sample data is usually to calculate the Euclidean distance, and its original calculation formula is as follows:

[0076]

[0077] Where, x k For actual fuel consumption data, y k The data is sampled, k = 1, 2, 3, ..., n.

[0078] The Euclidean distance between actual fuel consumption data and sample data is calculated using the Euler distance formula. This allows us to determine the degree of similarity between the sample data and actual fuel consumption data. A shorter distance indicates a higher degree of similarity, and vice versa.

[0079] 3. Select the K closest (most similar) points for fuel consumption risk assessment. Specifically, in step 2, the Euclidean distance between the actual fuel consumption data and each sample data is calculated, and K points from all sample data are extracted as samples to determine the fuel consumption risk category. The result with the highest frequency among the selected K points is the final fuel consumption risk assessment result. For example, in a fuel consumption risk level assessment, the K value of the KNN algorithm is 5, meaning the final result is based on the 5 closest points. If the 5 closest points are p1, p2, p1, p3, p1 (high risk, medium risk, high risk, low risk, high risk), then the final fuel consumption risk classification result of the KNN algorithm is high risk.

[0080] In this embodiment, the improvement to the nearest neighbor algorithm is to add a fuel consumption weight p to KNN. Specifically, the value of the fuel consumption weight can be determined based on various influencing factors such as vehicle brand, vehicle quality, and road conditions on the day in the risk source data of the target vehicle. For example, the value range of the fuel consumption weight p can be determined to be 0.8-1.2 based on the traffic congestion parameter, where 0.8 represents very good road conditions and 1.2 represents very congested road conditions.

[0081] Furthermore, the Euclidean distance formula for the improved nearest neighbor algorithm in this embodiment is as follows:

[0082]

[0083] Where, x k For the estimated fuel consumption value, y k Here, k = 1, 2, 3, ..., n, and p is the standard fuel consumption value.

[0084] Furthermore, a step size value is set for the determined fuel consumption weights, for example, a step size value of 0.05. Based on the step size value and the range of values ​​of the fuel consumption weights, multiple fuel consumption weight values ​​are determined. Each fuel consumption weight value is then multiplied by the initial estimated fuel consumption to obtain multiple fuel consumption values. The initial estimated fuel consumption dataset is formed from these multiple fuel consumption values.

[0085] After obtaining the initial expected fuel consumption dataset, the fuel consumption values ​​in the initial expected fuel consumption dataset are combined with the standard fuel consumption of the target vehicle and the improved proximity algorithm to calculate the target expected fuel consumption dataset. The target expected fuel consumption dataset is then obtained based on the target expected fuel consumption dataset. Furthermore, the target expected fuel consumption dataset of the target vehicle is determined based on the target expected fuel consumption dataset.

[0086] Further, the step of determining the target expected fuel consumption of the target vehicle based on the initial expected fuel consumption dataset and the improved nearest neighbor algorithm includes:

[0087] Step S3031: Determine the target expected fuel consumption dataset based on the initial expected fuel consumption dataset, the standard fuel consumption of the target vehicle, and the improved nearest neighbor algorithm;

[0088] Step S3032: Calculate the average value based on the target expected fuel consumption dataset to obtain the target expected fuel consumption of the target vehicle.

[0089] After obtaining the initial estimated fuel consumption dataset, each fuel consumption value in the initial estimated fuel consumption dataset is compared with the standard fuel consumption input into the Euclidean distance formula of the improved nearest neighbor algorithm to obtain a corresponding number of new fuel consumption values, forming the target estimated fuel consumption dataset. Further, the average value of each fuel consumption value in the target estimated fuel consumption dataset is calculated, and the calculated average value is determined as the target estimated fuel consumption of the target vehicle. The target estimated fuel consumption is the final estimated fuel consumption for this trip.

[0090] Figure 5 The third schematic flowchart of the vehicle risk determination method provided in this application embodiment. In one embodiment, the step of determining the risk level of the target vehicle based on the target expected fuel consumption and the actual fuel consumption of the target vehicle includes:

[0091] Step S401: Calculate the ratio between the target estimated fuel consumption and the actual fuel consumption of the target vehicle;

[0092] Step S402: Determine the risk level of the target vehicle based on the result of the ratio calculation.

[0093] After collecting the actual fuel consumption of the target vehicle and estimating its target estimated fuel consumption, this embodiment calculates the ratio between the target estimated fuel consumption and the actual fuel consumption. Specifically, the target estimated fuel consumption is used as the numerator, and the actual fuel consumption is used as the denominator for the ratio calculation. After the calculation, the ratio result is obtained. Further, the risk level of the target vehicle is determined based on the ratio result. Specifically, in this embodiment, the risk level can be divided into no risk, low risk, medium risk, and high risk. If the ratio result is less than or equal to 10%, the risk level of the target vehicle is determined to be no risk; if the ratio result is between 11% and 30%, the risk level is determined to be low risk; if the ratio result is between 31% and 60%, the risk level is determined to be medium risk; and if the ratio result is greater than 60%, the risk level is determined to be high risk. This embodiment can accurately determine the risk level of the target vehicle based on the comparison between the target estimated fuel consumption and the actual fuel consumption, allowing assessors to accurately determine whether there are any abnormalities in the target vehicle's current trip based on the risk level.

[0094] Furthermore, this application also provides a vehicle risk determination device.

[0095] Reference Figure 6 , Figure 6 This is a schematic diagram of the functional modules of an embodiment of the vehicle risk determination device of this application.

[0096] The vehicle risk determination device includes:

[0097] The first determining module 100 is used to determine the driving trajectory of the target vehicle based on the movement signaling of the driver corresponding to the target vehicle.

[0098] The second determining module 200 is used to determine the initial estimated fuel consumption of the target vehicle based on the driving trajectory;

[0099] The third determining module 300 is used to determine the target estimated fuel consumption of the target vehicle based on the initial estimated fuel consumption combined with the improved proximity algorithm;

[0100] The fourth determining module 400 is used to determine the risk level of the target vehicle based on the target estimated fuel consumption and the actual fuel consumption of the target vehicle.

[0101] Figure 7 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 7 As shown, the electronic device may include a processor 810, a communication interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other via the communication bus 840. The processor 810 can call a computer program in the memory 830 to execute the steps of the vehicle risk determination method, such as including:

[0102] The driving trajectory of the target vehicle is determined based on the movement signaling of the driver corresponding to the target vehicle;

[0103] The initial estimated fuel consumption of the target vehicle is determined based on the driving trajectory;

[0104] The target estimated fuel consumption of the target vehicle is determined based on the initial estimated fuel consumption combined with the improved nearest neighbor algorithm;

[0105] The risk level of the target vehicle is determined based on the target estimated fuel consumption and the actual fuel consumption of the target vehicle.

[0106] Furthermore, the logical instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0107] On the other hand, this application also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the steps of the vehicle risk determination method provided in the above embodiments, such as including:

[0108] The driving trajectory of the target vehicle is determined based on the movement signaling of the driver corresponding to the target vehicle;

[0109] The initial estimated fuel consumption of the target vehicle is determined based on the driving trajectory;

[0110] The target estimated fuel consumption of the target vehicle is determined based on the initial estimated fuel consumption combined with the improved nearest neighbor algorithm;

[0111] The risk level of the target vehicle is determined based on the target estimated fuel consumption and the actual fuel consumption of the target vehicle.

[0112] On the other hand, embodiments of this application also provide a computer medium, which is a computer-readable storage medium storing a vehicle risk determination program. The vehicle risk determination program is used to cause a processor to execute the steps of the methods provided in the above embodiments, including, for example:

[0113] The driving trajectory of the target vehicle is determined based on the movement signaling of the driver corresponding to the target vehicle;

[0114] The initial estimated fuel consumption of the target vehicle is determined based on the driving trajectory;

[0115] The target estimated fuel consumption of the target vehicle is determined based on the initial estimated fuel consumption combined with the improved nearest neighbor algorithm;

[0116] The risk level of the target vehicle is determined based on the target estimated fuel consumption and the actual fuel consumption of the target vehicle.

[0117] The processor-readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO)), optical memory (e.g., CD, DVD, BD, HVD), and semiconductor memory (e.g., ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)).

[0118] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0119] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for determining vehicle risk, characterized in that, include: The driving trajectory of the target vehicle is determined based on the movement signaling of the driver corresponding to the target vehicle; The initial estimated fuel consumption of the target vehicle is determined based on the driving trajectory; The target estimated fuel consumption of the target vehicle is determined based on the initial estimated fuel consumption combined with the improved nearest neighbor algorithm; The risk level of the target vehicle is determined based on the target estimated fuel consumption and the actual fuel consumption of the target vehicle. The step of determining the target estimated fuel consumption of the target vehicle based on the initial estimated fuel consumption combined with the improved nearest neighbor algorithm includes: Fuel consumption weights are determined based on the risk source data of the target vehicle; The initial estimated fuel consumption dataset is determined based on the fuel consumption weights and the initial estimated fuel consumption. The target estimated fuel consumption of the target vehicle is determined based on the initial estimated fuel consumption dataset and the improved nearest neighbor algorithm. The step of determining the target estimated fuel consumption of the target vehicle based on the initial estimated fuel consumption dataset and the improved nearest neighbor algorithm includes: The target expected fuel consumption dataset is determined based on the initial expected fuel consumption dataset, the standard fuel consumption of the target vehicle, and the improved nearest neighbor algorithm. The target expected fuel consumption of the target vehicle is obtained by averaging the target expected fuel consumption dataset. The Euclidean distance formula for the improved nearest neighbor algorithm is shown below: ； Where, x k For the estimated fuel consumption value, y k Here, k = 1, 2, 3, ..., n, and p is the standard fuel consumption value.

2. The vehicle risk determination method according to claim 1, characterized in that, The step of determining the driving trajectory of the target vehicle based on the movement signaling of the driver corresponding to the target vehicle includes: The target vehicle's trajectory point dataset is determined based on the movement signaling of the driver corresponding to the target vehicle combined with the time-of-arrival positioning algorithm. The driving trajectory of the target vehicle is determined based on the driving trajectory point dataset.

3. The vehicle risk determination method according to claim 1, characterized in that, The step of determining the initial estimated fuel consumption of the target vehicle based on the driving trajectory includes: The mileage of the target vehicle is determined based on the driving trajectory. The initial estimated fuel consumption of the target vehicle is calculated based on the mileage traveled.

4. The vehicle risk determination method according to claim 1, characterized in that, The step of determining the risk level of the target vehicle based on the target projected fuel consumption and the actual fuel consumption of the target vehicle includes: The ratio of the target estimated fuel consumption to the actual fuel consumption of the target vehicle is calculated. The risk level of the target vehicle is determined based on the result of the ratio calculation.

5. A vehicle risk determination device, characterized in that, include: The first determining module is used to determine the driving trajectory of the target vehicle based on the movement signaling of the driver corresponding to the target vehicle. The second determining module is used to determine the initial estimated fuel consumption of the target vehicle based on the driving trajectory; The third determining module is used to determine the target estimated fuel consumption of the target vehicle based on the initial estimated fuel consumption combined with the improved proximity algorithm; The fourth determining module is used to determine the risk level of the target vehicle based on the target estimated fuel consumption and the actual fuel consumption of the target vehicle; The third determining module is further configured to determine fuel consumption weights based on the risk source data of the target vehicle; determine an initial expected fuel consumption dataset based on the fuel consumption weights and the initial expected fuel consumption; and determine the target expected fuel consumption of the target vehicle based on the initial expected fuel consumption dataset and the improved nearest neighbor algorithm. The third determining module is further configured to determine a target expected fuel consumption dataset based on the initial expected fuel consumption dataset, the standard fuel consumption of the target vehicle, and the improved nearest neighbor algorithm; and to calculate the average value based on the target expected fuel consumption dataset to obtain the target expected fuel consumption of the target vehicle. The Euclidean distance formula for the improved nearest neighbor algorithm is shown below: ； Where, x k For the estimated fuel consumption value, y k Here, k = 1, 2, 3, ..., n, and p is the standard fuel consumption value.

6. An electronic device comprising a processor and a memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the vehicle risk determination method according to any one of claims 1 to 4.

7. A computer medium, said medium being a computer-readable storage medium, characterized in that, The computer-readable storage medium stores a vehicle risk determination program, which, when executed by a processor, implements the steps of the vehicle risk determination method according to any one of claims 1 to 4.

Images