Vehicle operation risk assessment method and device, computer equipment and storage medium

Abstract

The invention belongs to the technical field of vehicle insurance assessment, and discloses a vehicle operation risk assessment method and device, computer equipment and a storage medium. An accident record of a to-be-evaluated vehicle and driving behavior characteristic data of a driver are acquired, and the driving behavior characteristic data comprise bad driving behavior frequency, night driving duration, fatigue driving duration, load data, speed data and dangerous driving behavior frequency; determining a plurality of risk evaluation parameters based on an accident record and the driving behavior characteristic data; determining the risk level of each risk evaluation parameter according to a preset risk level division standard; and inputting the risk evaluation parameters and the corresponding risk levels into a risk evaluation model to obtain an estimated operation risk value of the to-be-evaluated vehicle, the risk evaluation model being constructed based on a dendritic cell algorithm. And the operation risk of the heavy-duty truck can be estimated more accurately.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle insurance assessment, and in particular to a method, apparatus, computer equipment, and storage medium for assessing vehicle operation risks. Background Art

[0002] With the rapid development of the logistics and transportation industry, heavy-duty trucks, as the core vehicles for freight transportation, are becoming increasingly important for operational safety and insurance risk assessment. Currently, insurance scoring systems for heavy-duty trucks rely primarily on static indicators, such as vehicle hardware parameters, driver experience, and historical accident records. These systems lack dynamic monitoring and analysis of real-time driving behavior and vehicle operating status. Due to limitations in data sources and algorithms, existing insurance assessment models are inaccurate in assessing the risk level of heavy-duty trucks. Summary of the Invention

[0003] To this end, the embodiments of the present application provide a vehicle operation risk assessment method, apparatus, computer equipment and storage medium, which can more accurately estimate the operation risk of heavy-loaded trucks and provide a reliable data basis for insurance scoring.

[0004] In a first aspect, the present application provides a method for assessing vehicle operation risk.

[0005] This application is achieved through the following technical solutions:

[0006] A vehicle operation risk assessment method includes:

[0007] Obtaining accident records of the vehicle to be assessed and driving behavior characteristic data of the driver, the driving behavior characteristic data including the frequency of bad driving behavior, duration of night driving, duration of fatigue driving, load data, speed data, and frequency of dangerous driving behavior;

[0008] Determining a plurality of risk assessment parameters based on the accident record and the driving behavior characteristic data;

[0009] Determine the risk level of each risk assessment parameter based on the preset risk level classification standards;

[0010] The risk assessment parameters and their corresponding risk levels are input into a risk assessment model to obtain an estimated operating risk value of the vehicle to be assessed. The risk assessment model is constructed based on a dendritic cell algorithm.

[0011] In a preferred example of the present application, it can be further configured to include:

[0012] The estimated operating risk value of the vehicle to be evaluated is pushed to the insurance pricing system.

[0013] In a preferred example of the present application, it can be further configured to determine multiple risk assessment parameters based on the accident record and the driving behavior characteristic data, including:

[0014] Based on the accident record and total mileage of the vehicle to be evaluated, the number of accidents per thousand kilometers is calculated as the first risk assessment parameter;

[0015] Based on the frequency of bad driving behaviors and the total mileage of the vehicle to be assessed, the bad driving frequency per thousand kilometers is calculated as the second risk assessment parameter;

[0016] Based on the night driving time and total driving time of the vehicle to be assessed, the night driving ratio is calculated as the third risk assessment parameter;

[0017] Based on the fatigue driving time and total driving time of the vehicle to be evaluated, the fatigue driving ratio is calculated as the fourth risk assessment parameter;

[0018] Calculate the load factor based on the load data and rated load of the vehicle to be assessed as the fifth risk assessment parameter;

[0019] Calculating a speeding threshold ratio based on the speed data of the vehicle to be assessed and the speed limit threshold as a sixth risk assessment parameter;

[0020] Based on the frequency of dangerous driving behaviors and the total mileage of the vehicle to be evaluated, the frequency of dangerous driving per thousand kilometers is calculated as the seventh risk assessment parameter.

[0021] In a preferred example of the present application, it can be further configured to determine the risk level of each risk assessment parameter according to a preset risk level classification standard, including:

[0022] Each risk assessment parameter is divided into a first risk level, a second risk level, a third risk level and a fourth risk level according to a preset risk level classification standard, wherein the preset risk level classification standard is obtained based on cluster analysis of historical data.

[0023] In a preferred example of the present application, the risk assessment parameters and their corresponding risk levels may be input into a risk assessment model to obtain an estimated operating risk value of the vehicle to be assessed. The risk assessment model is constructed based on a dendritic cell algorithm and includes:

[0024] Mapping the risk assessment parameters belonging to the third and fourth risk levels into pathogen-associated molecular pattern signals, mapping the risk assessment parameters belonging to the second risk level into danger signals, and mapping the risk assessment parameters belonging to the first risk level into safety signals;

[0025] calculating the signal concentration of the dendritic cell output signal according to the signal concentrations of the pathogen-associated molecular pattern signal, the danger signal, and the safety signal;

[0026] An estimated operational risk value is calculated based on the signal concentration of the output signal.

[0027] In a second aspect, the present application provides a vehicle operation risk assessment device.

[0028] This application is achieved through the following technical solutions:

[0029] A vehicle operation risk assessment device, configured to execute the vehicle operation risk assessment method described in the first aspect, comprising:

[0030] A data acquisition module is used to obtain the accident records of the vehicle to be evaluated and the driving behavior characteristic data of the driver, wherein the driving behavior characteristic data includes the frequency of bad driving behavior, the duration of night driving, the duration of fatigue driving, load data, speed data and the frequency of dangerous driving behavior;

[0031] A data preprocessing module, configured to determine a plurality of risk assessment parameters based on the accident record and the driving behavior characteristic data;

[0032] A grading module is used to determine the risk level of each risk assessment parameter based on the preset risk level classification standards;

[0033] The risk assessment module is used to input the risk evaluation parameters and their corresponding risk levels into a risk assessment model to obtain an estimated operating risk value of the vehicle to be assessed. The risk assessment model is constructed based on a dendritic cell algorithm.

[0034] In a preferred example of the present application, it can be further set that the level classification module is specifically used to: divide each risk assessment parameter into a first risk level, a second risk level, a third risk level and a fourth risk level according to a preset risk level classification standard, wherein the preset risk level classification standard is obtained based on a cluster analysis of historical data.

[0035] In a preferred example of the present application, it can be further configured that the risk assessment module is specifically used to:

[0036] Mapping the risk assessment parameters belonging to the third and fourth risk levels into pathogen-associated molecular pattern signals, mapping the risk assessment parameters belonging to the second risk level into danger signals, and mapping the risk assessment parameters belonging to the first risk level into safety signals;

[0037] calculating the signal concentration of the dendritic cell output signal according to the signal concentrations of the pathogen-associated molecular pattern signal, the danger signal, and the safety signal;

[0038] An estimated operational risk value is calculated based on the signal concentration of the output signal.

[0039] Thirdly, this application is achieved through the following technical solutions:

[0040] A computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the above-mentioned vehicle operation risk assessment methods when executing the computer program.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium.

[0042] This application is achieved through the following technical solutions:

[0043] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of any one of the above-mentioned vehicle operation risk assessment methods.

[0044] In summary, compared with the prior art, the technical solutions provided by the embodiments of the present application have at least the following beneficial effects:

[0045] This application obtains the accident record of the vehicle to be evaluated and the driving behavior characteristic data of the driver, the driving behavior characteristic data including the frequency of bad driving behavior, night driving time, fatigue driving time, load data, speed data and the frequency of dangerous driving behavior; based on the accident record and the driving behavior characteristic data, multiple risk assessment parameters are determined; according to the preset risk level classification standard, the risk level of each risk assessment parameter is determined; the risk assessment parameters and their corresponding risk levels are input into the risk assessment model to obtain the estimated operating risk value of the vehicle to be evaluated, and the risk assessment model is constructed based on the dendritic cell algorithm. By obtaining the accident record and multi-dimensional driving behavior characteristic data of heavy-loaded trucks, the risk factors in the driving process are fully considered, and the risk factors are identified and classified by the dendritic cell algorithm, thereby achieving an accurate evaluation of the operating risk of heavy-loaded trucks and providing a scientific basis for the insurance industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flowchart of a method for assessing vehicle operation risk provided in one embodiment of the present application;

[0047] Figure 2 A schematic structural diagram of a vehicle operation risk assessment device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0048] This specific embodiment is merely an explanation of the present application and is not a limitation of the present application. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed, but as long as they are within the scope of the claims of the present application, they are protected by the patent law.

[0049] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0050] In addition, the term "and / or" in this application is simply a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this application, unless otherwise specified, generally indicates that the related objects are in an "or" relationship.

[0051] In this application, the terms "first", "second", etc. are used to distinguish identical or similar items with substantially the same effects and functions. It should be understood that there is no logical or temporal dependency between "first", "second", and "nth", nor is there any limitation on the quantity and execution order.

[0052] In the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0053] The embodiments of the present application are described in further detail below with reference to the accompanying drawings.

[0054] Reference Figure 1 As shown, the first exemplary embodiment of the present application provides a method for assessing vehicle operation risk, which includes:

[0055] S1: Obtain the accident record of the vehicle to be evaluated and the driving behavior characteristic data of the driver, which includes the frequency of bad driving behavior, night driving time, fatigue driving time, load data, speed data and the frequency of dangerous driving behavior.

[0056] Specifically, the vehicle under evaluation is equipped with an onboard T-BOX and DMS system. These systems collect real-time driver behavior data, connect to the insurance company's system via an API, and retrieve historical accident records based on the vehicle's unique vehicle identifier. The vehicle under evaluation is a heavy-duty truck used for long-distance transport.

[0057] It should be noted that the on-board T-BOX is a component of the vehicle's networking, responsible for the real-time collection, processing, storage, and transmission of vehicle operating data. The on-board T-BOX connects to the vehicle's electronic control unit via an on-board bus (such as CAN or LIN) and communicates with a cloud server. The DMS (Driver Monitoring System) uses cameras and sensors to monitor driver fatigue, distraction, and dangerous driving behavior in real time.

[0058] In actual implementation, the unique identifier (VINN code) of the vehicle to be evaluated is used as the identifier for data association. The DMS system is used to obtain the frequency of bad driving behaviors of the driver of the vehicle to be evaluated, including the number of bad driving behavior warnings triggered by behaviors such as smoking, playing with mobile phones, not wearing seat belts, and looking away from the driving direction while driving. A night driving time period is pre-set, for example, the time period from 22:00 to 6:00 the next day is defined as night driving time. The driving time of the vehicle to be evaluated is obtained through the on-board T-BOX, and the night driving time of the vehicle to be evaluated between 22:00 and 6:00 the next day is counted. Continuous driving for more than 4 hours is defined as fatigue driving, and the fatigue driving time is counted; the load data of the vehicle to be evaluated is obtained; the vehicle speed of the vehicle to be evaluated is obtained; and the frequency of dangerous driving behaviors of the vehicle to be evaluated is obtained through the DMS system, including the number of dangerous driving warnings triggered by sudden acceleration, sudden deceleration, lane departure warnings, and emergency braking.

[0059] S2: Determine multiple risk assessment parameters based on accident records and driving behavior characteristic data.

[0060] S3: Determine the risk level of each risk assessment parameter based on the preset risk level classification standard.

[0061] S4: Input the risk assessment parameters and their corresponding risk levels into the risk assessment model to obtain the estimated operating risk value of the vehicle to be assessed. The risk assessment model is constructed based on the dendritic cell algorithm.

[0062] In some embodiments, after obtaining the predicted operating state of the vehicle to be evaluated, the method further includes:

[0063] The estimated operating risk value of the vehicle to be evaluated is pushed to the insurance pricing system so that the insurance pricing system can adjust the premium according to the estimated risk value of the vehicle to be evaluated.

[0064] In some embodiments, multiple risk assessment parameters are determined based on accident records and driving behavior characteristic data, including:

[0065] Based on the accident record and total mileage of the vehicle to be evaluated, the number of accidents per thousand kilometers is calculated as the first risk assessment parameter.

[0066] Specifically, the number of historical accidents is determined as x1 based on the accident record of the vehicle to be evaluated. The total mileage of the vehicle to be evaluated from the start of operation to the time of participation in the evaluation is L. total , the number of accidents per thousand kilometers is The number of accidents per thousand kilometers C1 is used as the risk assessment parameter.

[0067] Based on the frequency of bad driving behaviors and the total mileage of the vehicle to be evaluated, the bad driving frequency per thousand kilometers is calculated as the second risk assessment parameter.

[0068] Specifically, the frequency of bad driving behavior of the vehicle to be evaluated is x2, and the total mileage from the start of the vehicle to be evaluated to the time of participation in the evaluation is L total , the frequency of bad driving per thousand kilometers is The bad driving frequency per thousand kilometers C2 is used as the second risk assessment parameter.

[0069] Based on the night driving time and total driving time of the vehicle to be evaluated, the night driving ratio is calculated as the third risk assessment parameter.

[0070] Specifically, for example, the night driving time of the vehicle to be evaluated is x3, and the total mileage from the start of the vehicle to be evaluated to the time of participation in the evaluation is L total , the proportion of night driving is The night driving proportion C3 is used as the third risk assessment parameter.

[0071] Based on the fatigue driving time and total driving time of the vehicle to be evaluated, the fatigue driving ratio is calculated as the fourth risk assessment parameter.

[0072] Specifically, the fatigue driving time of the vehicle to be evaluated is obtained as x4, and the total driving time from the start of the vehicle to be evaluated to the time of participation in the evaluation is T total , the proportion of fatigue driving is The proportion of fatigue driving C4 is used as the fourth risk assessment parameter.

[0073] Based on the load data and rated load of the vehicle to be evaluated, the load factor is calculated as the fifth risk assessment parameter.

[0074] Specifically, based on the load data w and rated load W of the vehicle to be evaluated, the load factor of the vehicle is determined as The load factor C5 is used as the fifth risk assessment parameter.

[0075] Based on the speed data of the vehicle to be evaluated and the speed limit threshold, an overspeeding threshold ratio is calculated as a sixth risk assessment parameter.

[0076] Specifically, for example, based on the speed data of the vehicle to be evaluated and the speed limit threshold, the speeding threshold ratio between the real-time speed v and the speed limit threshold V is determined. The speeding threshold ratio C6 is used as the sixth risk assessment parameter.

[0077] Based on the frequency of dangerous driving behaviors and the total mileage of the vehicle to be evaluated, the frequency of dangerous driving per thousand kilometers is calculated as the seventh risk assessment parameter.

[0078] Specifically, based on the dangerous driving behavior data of the vehicle to be evaluated, the number of dangerous driving behaviors is determined to be x7, and the total mileage from the start of the vehicle to be evaluated to the time of participation in the evaluation is L total , then the number of dangerous driving times per thousand kilometers is The number of dangerous driving times per thousand kilometers C7 is used as the seventh risk assessment parameter.

[0079] In actual implementation, when calculating and generating the above-mentioned risk assessment parameters, the original driving behavior characteristic data obtained is first preprocessed to delete the outliers in the original data. Specifically, the outliers of continuous data are identified and deleted using the IQR criterion. For example, for the load data w, after obtaining the load data w, the load data w is arranged in ascending order, the median Q2 of all the data is calculated, and the data is divided into the first part and the second part according to the median Q2. The median Q1 of the first part and the median Q3 of the second part are calculated, and the interquartile range IQR = Q3-Q1 is determined;

[0080] Then determine the upper limit of the data α=Q3+1.5*IQR, the lower limit β=Q1-1.5*IQR,

[0081] The outlier value is {w||(w>α)∪(w<β)}.

[0082] At the same time, missing values ​​in continuous data can be interpolated using linear functions.

[0083] In some embodiments, the risk level of each risk assessment parameter is determined according to a preset risk level classification standard, including:

[0084] Each risk assessment parameter is divided into the first risk level, the second risk level, the third risk level and the fourth risk level according to the preset risk level classification standard. The preset risk level classification standard is obtained based on the cluster analysis of historical data.

[0085] Cluster analysis is performed using the operating data of the same type of heavy-duty trucks in the same operating scenario over a one-year period to determine the different risk level thresholds for each evaluation indicator, and then the above-mentioned risk evaluation indicators are divided into levels.

[0086] In some embodiments, the risk assessment parameters and their corresponding risk levels are input into a risk assessment model to obtain an estimated operational risk value of the vehicle to be assessed. The risk assessment model is constructed based on a dendritic cell algorithm and includes:

[0087] Mapping risk assessment parameters belonging to the third and fourth risk levels into pathogen-associated molecular pattern signals, mapping operational risk assessment indicators belonging to the second risk level into danger signals, and mapping operational risk assessment indicators belonging to the first risk level into safety signals;

[0088] Based on the signal concentrations of pathogen-associated molecular pattern signals, danger signals, and safety signals, the signal concentrations of dendritic cell output signals are calculated, including the signal concentrations of wave-expanding costimulatory molecules, semi-mature dendritic cell factors, and mature dendritic cell factors;

[0089] The operational risk value is estimated based on the signal concentration of the output signal.

[0090] The above-mentioned estimated operation risk value can be used to predict the operation status, including low-risk status, medium-risk status and high-risk status.

[0091] It should be noted that the dendritic cell algorithm abstracts the input antigen information into input signal features, obtains the output signal after calculation, and then determines the differentiation state of the dendritic cell. Finally, the abnormality of the antigen environment is evaluated according to the type of dendritic cell. In the dendritic cell algorithm, dendritic cells have three states: immature dendritic cells, semi-mature dendritic cells, and mature dendritic cells. The dendritic cell algorithm mainly has three input signals, namely: pathogen associated molecular patterns (PAMPs): indicating that the cell is damaged by pathogens or dies abnormally, which is an absolute danger signal; safe signals (SS): promoting normal cell apoptosis, indicating that the cell environment is safe; danger signals (DS): indicating that the cell environment may be dangerous, and the degree of danger is lower than the PAMP signal.

[0092] First, the risk assessment parameters of the vehicle to be assessed are mapped to various signals in the artificial immune system. The characteristic indicators of heavy-duty trucks represent antigens. Undifferentiated dendritic cells represent detectors; semi-mature dendritic cells indicate that the heavy-duty truck is in a risky operating state; and mature dendritic cells indicate that the heavy-duty truck is in a safe operating state.

[0093] The output signals of the dendritic cell algorithm include a costimulatory signal (CSM), a semi-mature signal (semi), and a mature signal (mat). The CSM indicates that a heavy-loaded truck may be in a risky operating state; the semi-mature signal (semi) indicates the safety level of the heavy-loaded truck's state, and the mature signal (mat) indicates the danger level of the heavy-loaded truck's state.

[0094] The data processing of input and output signals in the dendritic cell algorithm adopts a weighted approach as follows:

[0095]

[0096] Where Q c represents the signal concentration of the co-stimulatory molecule in the output signal, Q s represents the signal concentration of semi-mature dendritic cell factors in the output signal, Q m The signal concentration, C, represents the signal concentration of mature dendritic cell factors in the output signal. p The signal concentration of the pathogen-associated molecular pattern signal representing the input signal, C d The signal concentration representing the danger signal of the input signal, C s The signal density of the safety signal representing the input signal, w ij The weight representing the conversion between input and output signals. The concentration of the input signal refers to the number of times a specific signal appears within a certain period of time, that is, the frequency of a risk indicator becoming dangerous within a certain period of time. The weight is obtained from the expert's score.

[0097] Specifically, the conversion weight matrix of the dendritic cell algorithm signal is shown in Table 1 below:

[0098] Table 1

[0099] Weight Pathogen-associated molecular pattern signals Red flags Safety signal co-stimulatory molecules <![CDATA[w 11 ]]> <![CDATA[w 21 ]]> <![CDATA[w 31 ]]> semi-mature dendritic cell factor <![CDATA[w 12 ]]> <![CDATA[w 22 ]]> <![CDATA[w 32 ]]> Mature dendritic cell factor <![CDATA[w 13 ]]> <![CDATA[w 23 ]]> <![CDATA[w 33 ]]>

[0100] For example, a random sample of driving segments from a vehicle to be evaluated over a year is selected, with driving segments defined as those with a driving distance greater than 50 km. Different input signals are generated based on the characteristic indicators. An output signal is calculated based on the dendritic cell algorithm's co-stimulatory molecule signal concentration, the semi-mature dendritic cell factor signal concentration, and the mature dendritic cell factor signal concentration. When the co-stimulatory molecule concentration in the output signal reaches a predetermined concentration, the driving segment is analyzed.

[0101] When the cumulative signal concentration of semi-mature dendritic cell factors is greater than the cumulative signal concentration of mature dendritic cell factors, immature dendritic cells are transformed into semi-mature dendritic cells, which means that the operation of heavy-loaded trucks is safe; when the cumulative signal concentration of semi-mature dendritic cell factors is less than the cumulative signal concentration of mature dendritic cell factors, immature dendritic cells are transformed into mature dendritic cells, which means that the operation of heavy-loaded trucks is dangerous.

[0102] When the co-stimulatory molecule concentration of the output signal reaches a predetermined concentration, the contextual mature antigen value MCAV of the antigen (single segment) is calculated. MCAV reflects the degree of antigen abnormality and represents the risk value. Then:

[0103]

[0104] Where N m represents the number of mature dendritic cells, N s It indicates the number of semi-mature dendritic cells. When the MCAV value is in [0.0, 0.5), it is a normal antigen. When the MCAV value is in [0.5, 1.0], it is an abnormal antigen. The closer the MCAV value is to 1.0, the higher the risk value.

[0105] The heavy-duty truck risk assessment method based on a dendritic cell algorithm draws on artificial immune mechanisms. This mechanism mimics the signal processing mechanism of the natural immune system, using specific algorithms to determine the harmfulness of "antigens." In this mechanism, antigens represent risk factors in driving behavior, such as vehicle operating characteristics and driver profiles. The natural immune system protects the body by recognizing and processing antigen signals. Applying this principle to driving risk assessment, different risk factors in driving behavior can be likened to different types of antigens, each with varying degrees of impact on vehicle safety. Using a dendritic cell algorithm, these "antigens" can be identified and classified, enabling intelligent assessment of heavy-duty truck operating risks. This approach not only enables dynamic monitoring and assessment of vehicle operating risks but also provides a scientific basis for the insurance industry, enabling more accurate risk pricing and product design. This can help insurers optimize their billing strategies.

[0106] Another embodiment of the present application further provides a vehicle operation risk assessment device for executing the above method, referring to Figure 2 As shown, the device includes:

[0107] The data acquisition module 10 is used to obtain the accident records of the vehicle to be evaluated and the driving behavior characteristic data of the driver, the driving behavior characteristic data including the frequency of bad driving behavior, the duration of night driving, the duration of fatigue driving, load data, speed data and the frequency of dangerous driving behavior;

[0108] A data preprocessing module 20 is used to determine a plurality of risk assessment parameters based on the accident record and the driving behavior characteristic data;

[0109] A level classification module 30 is used to determine the risk level of each risk assessment parameter according to a preset risk level classification standard;

[0110] The risk assessment module 40 is used to input the risk evaluation parameters and their corresponding risk levels into the risk assessment model to obtain the estimated operating risk value of the vehicle to be assessed. The risk assessment model is constructed based on the dendritic cell algorithm.

[0111] In some embodiments, the level classification module 30 is specifically used to: classify each risk assessment parameter into a first risk level, a second risk level, a third risk level and a fourth risk level according to a preset risk level classification standard, wherein the preset risk level classification standard is obtained based on historical data cluster analysis.

[0112] In some embodiments, the risk assessment module 40 is specifically used to: map the risk assessment parameters belonging to the third risk level and the fourth risk level into pathogen-associated molecular pattern signals, map the risk assessment parameters belonging to the second risk level into danger signals, and map the risk assessment parameters belonging to the first risk level into safety signals; calculate the signal concentration of the dendritic cell output signal based on the signal concentrations of the pathogen-associated molecular pattern signals, danger signals, and safety signals; and calculate an estimated operating risk value based on the signal concentration of the output signal.

[0113] The specific definition of the vehicle operation risk assessment device provided in this embodiment can be found in the embodiment of the vehicle operation risk assessment method described above and will not be repeated here. Each module in the aforementioned vehicle operation risk assessment device can be implemented in whole or in part via software, hardware, or a combination thereof. Each of these modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0114] An embodiment of the present application provides a computer device, which may include a processor, a memory, a network interface, and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, the processor executes the steps of the vehicle operation risk assessment method as described in any of the above embodiments.

[0115] The working process, working details and technical effects of the computer device provided in this embodiment can be found in the embodiment of the vehicle operation risk assessment method above, and will not be described in detail here.

[0116] The present application provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program implements the steps of the vehicle operation risk assessment method described in any of the above-described embodiments. The computer-readable storage medium refers to a data storage medium, which may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick. The computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable device.

[0117] The working process, working details and technical effects of the computer-readable storage medium provided in this embodiment can be found in the embodiment of the vehicle operation risk assessment method above, and will not be described in detail here.

[0118] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0119] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0120] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, the division of the above-mentioned functional units and modules is only used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system described in this application is divided into different functional units or modules to complete all or part of the functions described above.

Claims

1. A method for assessing vehicle operation risk, characterized in that: include: Obtaining accident records of the vehicle to be assessed and driving behavior characteristic data of the driver, the driving behavior characteristic data including the frequency of bad driving behavior, duration of night driving, duration of fatigue driving, load data, speed data, and frequency of dangerous driving behavior; Determining a plurality of risk assessment parameters based on the accident record and the driving behavior characteristic data; Determine the risk level of each risk assessment parameter based on the preset risk level classification standards; The risk assessment parameters and their corresponding risk levels are input into a risk assessment model to obtain an estimated operating risk value of the vehicle to be assessed. The risk assessment model is constructed based on a dendritic cell algorithm.

2. The vehicle operation risk assessment method according to claim 1, characterized in that: Also includes: The estimated operating risk value of the vehicle to be evaluated is pushed to the insurance pricing system.

3. The vehicle operation risk assessment method according to claim 1, characterized in that: Based on the accident record and the driving behavior characteristic data, multiple risk assessment parameters are determined, including: Based on the accident record and total mileage of the vehicle to be evaluated, the number of accidents per thousand kilometers is calculated as the first risk assessment parameter; Based on the frequency of bad driving behaviors and the total mileage of the vehicle to be assessed, the bad driving frequency per thousand kilometers is calculated as the second risk assessment parameter; Based on the night driving time and total driving time of the vehicle to be assessed, the night driving ratio is calculated as the third risk assessment parameter; Based on the fatigue driving time and total driving time of the vehicle to be evaluated, the fatigue driving ratio is calculated as the fourth risk assessment parameter; Calculate the load factor based on the load data and rated load of the vehicle to be assessed as the fifth risk assessment parameter; Calculating a speeding threshold ratio based on the speed data of the vehicle to be assessed and the speed limit threshold as a sixth risk assessment parameter; Based on the frequency of dangerous driving behaviors and the total mileage of the vehicle to be evaluated, the frequency of dangerous driving per thousand kilometers is calculated as the seventh risk assessment parameter.

4. The vehicle operation risk assessment method according to claim 3, characterized in that: Determine the risk level of each risk assessment parameter based on the preset risk level classification standards, including: Each risk assessment parameter is divided into a first risk level, a second risk level, a third risk level and a fourth risk level according to a preset risk level classification standard, wherein the preset risk level classification standard is obtained based on cluster analysis of historical data.

5. The vehicle operation risk assessment method according to claim 4, characterized in that: The risk assessment parameters and their corresponding risk levels are input into a risk assessment model to obtain an estimated operational risk value of the vehicle to be assessed. The risk assessment model is constructed based on a dendritic cell algorithm and includes: Mapping the risk assessment parameters belonging to the third and fourth risk levels into pathogen-associated molecular pattern signals, mapping the risk assessment parameters belonging to the second risk level into danger signals, and mapping the risk assessment parameters belonging to the first risk level into safety signals; calculating the signal concentration of the dendritic cell output signal according to the signal concentrations of the pathogen-associated molecular pattern signal, the danger signal, and the safety signal; An estimated operational risk value is calculated based on the signal concentration of the output signal.

6. A vehicle operation risk assessment device, characterized in that: Used to perform the method according to any one of claims 1 to 5, comprising: A data acquisition module is used to obtain the accident records of the vehicle to be evaluated and the driving behavior characteristic data of the driver, wherein the driving behavior characteristic data includes the frequency of bad driving behavior, the duration of night driving, the duration of fatigue driving, load data, speed data and the frequency of dangerous driving behavior; A data preprocessing module, configured to determine a plurality of risk assessment parameters based on the accident record and the driving behavior characteristic data; A grading module is used to determine the risk level of each risk assessment parameter based on the preset risk level classification standards; The risk assessment module is used to input the risk evaluation parameters and their corresponding risk levels into a risk assessment model to obtain an estimated operating risk value of the vehicle to be assessed. The risk assessment model is constructed based on a dendritic cell algorithm.

7. The vehicle operation risk assessment device according to claim 6, characterized in that: The level classification module is specifically used to: classify each risk assessment parameter into the first risk level, the second risk level, the third risk level and the fourth risk level according to the preset risk level classification standard, wherein the preset risk level classification standard is obtained based on the historical data cluster analysis.

8. The vehicle operation risk assessment device according to claim 7, characterized in that: The risk assessment module is specifically used to: Mapping the risk assessment parameters belonging to the third and fourth risk levels into pathogen-associated molecular pattern signals, mapping the risk assessment parameters belonging to the second risk level into danger signals, and mapping the risk assessment parameters belonging to the first risk level into safety signals; calculating the signal concentration of the dendritic cell output signal according to the signal concentrations of the pathogen-associated molecular pattern signal, the danger signal, and the safety signal; An estimated operational risk value is calculated based on the signal concentration of the output signal.

9. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method according to any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images