Insurance premium evaluation method, device and equipment for intelligent driving vehicle, and medium

Abstract

The invention provides an insurance premium evaluation method and device for an intelligent driving vehicle, equipment and a medium. The method comprises the following steps: acquiring multi-level data of a sensor; generating a first sensing parameter based on the sensor multi-level data; generating a second sensing parameter based on the sensor service life and the sensor quality guarantee period; performing simulation scene configuration based on the first sensing parameter and the second sensing parameter to obtain a target simulation scene, and performing driving decision simulation on the intelligent driving vehicle in the target simulation scene to obtain risk loss simulation data corresponding to different driving scenes; determining scene accident loss of the intelligent driving vehicle based on the risk loss simulation data; and determining an intelligent driving scene occurrence probability based on the intelligent driving scene mileage and the total mileage of the vehicle, and evaluating the reference premium of the intelligent driving vehicle based on the intelligent driving scene occurrence probability, the scene accident loss of the intelligent driving vehicle, the premium rate and the expected mileage of the intelligent driving vehicle. Therefore, rapid and accurate premium evaluation of the vehicle is effectively realized.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the field of vehicle premium evaluation, and in particular, to a premium evaluation method, device, equipment and medium suitable for an intelligent driving vehicle. BACKGROUND

[0002] Intelligent driving technology uses a large number of sensor devices to detect driving environment information, and uses artificial intelligence technology to complete part or even all operation control of the vehicle. Vehicle insurance benchmark premium calculation and evaluation is a core problem of vehicle underwriting, which directly affects the premium income of the insurance company.

[0003] In related technologies, the traditional vehicle insurance benchmark premium calculation uses an actuarial statistical model, which relies on the statistical loss of various types of vehicles in the past to calculate the benchmark premium pricing of new vehicle types.

[0004] However, the existing technology has low accuracy in premium estimation. SUMMARY

[0005] The embodiments described herein provide a premium evaluation method, device, equipment and medium for an intelligent driving vehicle, which overcome the above problems.

[0006] In a first aspect, according to the content of the present disclosure, a premium evaluation method for an intelligent driving vehicle is provided, comprising:

[0007] Obtaining sensor multi-level data, the sensor multi-level data comprising: sensor technical parameters, sensor detection parameters, and sensor safety and quality parameters;

[0008] Generating a first perception parameter based on the sensor multi-level data, the first perception parameter being used to describe a joint distribution of detection capability of a perception system, the first perception parameter being constructed from a single-item distribution of detection capability corresponding to each vehicle detection position covered by multiple sensors, the single-item distribution of detection capability corresponding to each vehicle detection position being determined from the sensor multi-level data;

[0009] Generating a second perception parameter based on the service life of the sensor and the warranty period of the sensor, the second perception parameter being used to describe the failure probability of the sensor after use;

[0010] Configuring a target simulation scene based on the first perception parameter and the second perception parameter, and simulating driving decisions of the intelligent driving vehicle in the target simulation scene to obtain risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenes;

[0011] Determining the scene accident loss of the intelligent driving vehicle based on the risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenes;

[0012] determine a smart driving scene occurrence probability based on the smart driving scene mileage and the total vehicle mileage, and evaluate a benchmark premium of the smart driving vehicle based on the smart driving scene occurrence probability, the scene accident loss of the smart driving vehicle, an insurance premium rate, and an expected mileage of the smart driving vehicle.

[0013] In a second aspect, according to the content of the present disclosure, a premium evaluation device for a smart driving vehicle is provided, comprising:

[0014] The acquisition module is configured to acquire sensor multi-level data, wherein the sensor multi-level data comprises sensor technical parameters, sensor detection parameters, and sensor safety and quality parameters.

[0015] The first generation module is configured to generate a first perception parameter based on the sensor multi-level data, wherein the first perception parameter is used to describe a joint distribution of detection capabilities of a perception system, and the first perception parameter is constructed from a single-item distribution of detection capabilities corresponding to each vehicle detection position covered by multiple sensors, and the single-item distribution of detection capabilities corresponding to each vehicle detection position is determined from the sensor multi-level data.

[0016] The second generation module is configured to generate a second perception parameter based on a sensor service life and a sensor warranty period, wherein the second perception parameter is used to describe a failure probability of a sensor after use.

[0017] The first determination module is configured to perform simulation scene configuration based on the first perception parameter and the second perception parameter, to obtain a target simulation scene, and to perform driving decision simulation on the smart driving vehicle in the target simulation scene, to obtain risk loss simulation data of the smart driving vehicle corresponding to different driving scenes.

[0018] The second determination module is configured to determine a scene accident loss of the smart driving vehicle based on the risk loss simulation data of the smart driving vehicle corresponding to different driving scenes.

[0019] The evaluation module is configured to determine a smart driving scene occurrence probability based on the smart driving scene mileage and the total vehicle mileage, and to evaluate a benchmark premium of the smart driving vehicle based on the smart driving scene occurrence probability, the scene accident loss of the smart driving vehicle, an insurance premium rate, and an expected mileage of the smart driving vehicle.

[0020] In a third aspect, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the premium evaluation method for a smart driving vehicle according to any one of the above embodiments when executing the computer program.

[0021] In a fourth aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the steps of the premium evaluation method of the intelligent driving vehicle in any one of the above embodiments are implemented.

[0022] The premium evaluation method of the intelligent driving vehicle provided in the embodiments of the present application acquires sensor multi-level data, the sensor multi-level data including sensor technical parameters, sensor detection parameters, and sensor safety and quality parameters; generates a first perception parameter based on the sensor multi-level data, the first perception parameter being used to describe a joint distribution of detection capabilities of a perception system, the first perception parameter being constructed from a single-item distribution of detection capabilities corresponding to each vehicle detection position covered by multiple sensors, the single-item distribution of detection capabilities corresponding to each vehicle detection position being determined from the sensor multi-level data; generates a second perception parameter based on a sensor service life and a sensor warranty period, the second perception parameter being used to describe a failure probability of the sensor after use; configures a simulation scenario based on the first perception parameter and the second perception parameter, obtains a target simulation scenario, and simulates driving decisions of the intelligent driving vehicle in the target simulation scenario to obtain risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenarios; determines a scenario accident loss of the intelligent driving vehicle based on the risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenarios; determines a scenario occurrence probability of the intelligent driving vehicle based on a scenario driving mileage of the intelligent driving vehicle and a total driving mileage of the vehicle, and evaluates a benchmark premium of the intelligent driving vehicle based on the scenario occurrence probability of the intelligent driving vehicle, the scenario accident loss of the intelligent driving vehicle, an insurance premium rate, and an expected driving mileage of the intelligent driving vehicle. In this way, the intelligent driving simulation is performed by constructing a simulation scenario, and the driving data and historical claim data of the vehicle are not relied on, but only the vehicle configuration data is relied on, so that the fast and accurate premium evaluation of the vehicle is effectively realized.

[0023] The above description is only a summary of the technical solutions of the embodiments of the present application. In order to more clearly understand the technical means of the embodiments of the present application, the embodiments of the present application can be implemented according to the content of the specification, and in order to make the above and other purposes, features and advantages of the embodiments of the present application more obvious and easy to understand, the specific embodiments of the present application are described below. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments will be briefly described below. It should be known that the drawings described below only relate to some embodiments of the present application, but not limit the present application, wherein:

[0025] Figure 1 is a flowchart of a premium evaluation method of an intelligent driving vehicle provided by the present application.

[0026] Figure 2 is a detection range coverage map of a perception system provided by the present application.

[0027] Figure 3 is a structural schematic diagram of an intelligent driving vehicle premium evaluation device provided by the present disclosure.

[0028] Figure 4 is a structural schematic diagram of a computer device provided by the present disclosure.

[0029] It should be noted that the elements in the drawings are schematic and not drawn to scale. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions of the embodiments of the present disclosure will be described clearly and completely below in conjunction with the drawings. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by a person skilled in the art without any inventive effort also belong to the scope of protection of the present disclosure.

[0031] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this present subject matter belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the specification and relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein. As used herein, the statement that two or more parts are "connected" or "coupled" together refer to an indirect or direct connection or coupling.

[0032] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. A person of ordinary skill in the art will readily recognize from the disclosure herein, given the total volume of this application that one or more passages that are described as an embodiment is / are also an embodiment of another embodiment.

[0033] The term "and / or", merely used as a description of associated objects, means that there can be three kinds of relations, for example, A and / or B, which can represent: there is A, there are A and B, and there is B. In addition, the character " / " in this paper generally represents that the front and rear associated objects are a "or" relationship. Terms such as "first" and "second" are only used to distinguish one component (or part of a component) from another component (or another part of a component).

[0034] In the description of the present application, the meaning of "a plurality of" is two or more (including two), and similarly, "a plurality of groups" means two or more groups (including two groups).

[0035] The embodiment constructs the risk of the intelligent driving vehicle by evaluating the hardware configuration of the intelligent driving vehicle sensing system and the reliability of the intelligent driving system, and realizes the benchmark premium calculation model of the intelligent driving vehicle by combining the risk with the vehicle loss.

[0036] In order to enable personnel in the art to better understand the scheme of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings.

[0037] Figure 1 is a flowchart of a premium evaluation method of an intelligent driving vehicle provided by the embodiment of the present application, as shown in Figure 1 The specific process of the premium evaluation method of the intelligent driving vehicle includes:

[0038] S110, acquiring multi-level data of a sensor.

[0039] The perception system of the intelligent driving vehicle is composed of one or more sensors, and various sensors are distributed and configured at various positions of the vehicle to realize the perception of the intelligent driving vehicle to the surrounding situation. The multi-level data of the sensor includes sensor technical parameters, sensor detection parameters, and sensor safety and quality parameters.

[0040] The sensor technical parameters include two parts, namely, basic technical parameters and type-related technical parameters. The sensor types of the perception system include but are not limited to a camera, a laser radar, a millimeter wave radar, an ultrasonic radar, and a positioning module. The basic technical parameters are shown in Table 1.

[0041] Table 1 Basic technical parameter table

[0042]

[0043]

[0044] The camera parameter table is shown in Table 2.

[0045] Table 2 Camera parameter table

[0046]

[0047] The laser radar parameter table is shown in Table 3.

[0048] Table 3 Laser radar parameter table

[0049]

[0050]

[0051] The parameters of the millimeter-wave radar are shown in Table 4.

[0052] Table 4. Parameters of Millimeter-Wave Radar

[0053] Serial number Parameter name Explanation Example 1 Manufacturer Sensor manufacturer MWR 2 Model Sensor model code MR-808 3 Operating frequency Frequency of millimeter wave signal 24 GHz 4 Detection technology Detection method of millimeter wave signal FMCW

[0054] The parameters of the ultrasonic radar are shown in Table 5.

[0055] Table 5. Parameters of Ultrasonic Radar

[0056] Serial number Parameter name Explanation Example 1 Manufacturer Sensor manufacturer SSR 2 Model Sensor model code SR-808 3 Type Analog or digital Digital 4 Independence Whether it is an independent detection method Independent

[0057] The parameters of the positioning equipment are shown in Table 6.

[0058] Table 6 Positioning Equipment Parameter Table

[0059]

[0060]

[0061] The sensor detection parameters constitute the static coverage area of ​​the sensing system. The sensor installation locations are recorded using a combination of textual descriptions and markings, and the static coverage area of ​​the sensing system is calculated based on the aforementioned sensor detection capability parameters. Sensor installation locations can be recorded using the following descriptions: front left corner, front right corner, rear left corner, rear right corner, directly in front, directly behind, left rearview mirror, right rearview mirror, windshield, rear windshield, left door, right door, interior, roof, etc.

[0062] The coverage area of ​​the sensing system is calculated based on the location, detection distance, horizontal fovea (FOV), and vertical FOV of each sensor, taking into account the spatial coverage of each sensor, to determine the static detection range of the entire system. The graphical representation of the calculation results is shown below. Figure 2 As shown, the area where point a is located is the detection coverage of the rear-view camera; the areas where points b, c, d, i, and j are located are the detection coverage of the millimeter-wave radar; the area where point e is located is the minimum detection range required by regulations; the areas where points f and h are located are the detection coverage of the front-view camera; and the area where point g is located is the detection coverage of the lidar. The intelligent driving system compares the calculated results with the requirements of intelligent driving regulations, and the coverage rate Z can be obtained using formula (1).

[0063]

[0064] In formula (1), Z s Z represents the spatial coverage area for each sensor; the operator ∩ denotes the spatial intersection of the coverage areas of each sensor, with the result calculated in terms of spatial volume; r The area covered by the regulations is calculated by volume.

[0065] Sensor safety and quality parameters are used to describe the safety and quality reliability of the sensor. The parameters shown in Table 7 can be used to evaluate the sensor safety and quality.

[0066] The sensor safety and quality parameter table is shown in Table 7.

[0067] Table 7 Sensor safety and quality parameter table

[0068]

[0069]

[0070] S120, generating a first perception parameter based on the multi-level sensor data.

[0071] The first perception parameter is used to describe the joint distribution of the detection capability of the perception system, and the first perception parameter is constructed from the single-item distribution of the detection capability corresponding to each vehicle detection position covered by the multi-sensor. The single-item distribution of the detection capability corresponding to each vehicle detection position is determined by the multi-level sensor data.

[0072] In some embodiments, generating a first perception parameter based on the multi-level sensor data includes:

[0073] Quantifying and assigning the multi-level sensor data based on the class to which the data belongs to obtain quantized assignment data corresponding to the multi-level sensor data, and obtaining sensor capability quantized data based on the quantized assignment data corresponding to the multi-level sensor data and the parameter weight ratio corresponding to the multi-level sensor data.

[0074] The quantifying and assigning the multi-level sensor data based on the class to which the data belongs to obtain quantized assignment data corresponding to the multi-level sensor data includes: classifying the multi-level sensor data to obtain discrete class data and continuous class data; for the discrete class data, assigning and processing the discrete class data based on the corresponding detection capability representation data to obtain discrete assignment data; for the continuous class data, linearly assigning and processing the continuous class data based on the corresponding intelligent driving compliance representation data to obtain continuous assignment data; and determining the quantized assignment data corresponding to the multi-level sensor data based on the discrete assignment data and the continuous assignment data.

[0075] For example, for sensor module k, the normalized sensor hardware capability quantization (i.e., quantized assignment data) is obtained by E k =∑ω i C i / ∑ω i C i is the i-th sensor performance parameter; ω iThe importance weight of the i-th sensor parameter can be configured differently for different types of sensors.

[0076] For C i Quantization and assignment are required. For discrete data, an assignment method is used, assigning scores based on the impact of each parameter on detection capability; higher capabilities are assigned higher scores, and lower capabilities are assigned lower scores. For example, for LiDAR types, MEMS is assigned a score of 3, solid-state a score of 2, and mechanical a score of 1. Linear compression is then applied across intervals, meaning MEMS will be assigned a score of 2, solid-state a score of 1.5, and mechanical a score of 1. For continuous parameters, a linear assignment method is used. Each parameter is assigned a base score of 1 based on intelligent driving compliance requirements. Histogram analysis is performed on common sensor performance parameters, with the top 5% of performance parameters receiving the highest score of 2. Other scores are then linearly fitted to derive their corresponding scores.

[0077] Different types of sensors have different detection capabilities for different types of targets. For a specific sensor S... k For a target T located at position (d,θ) i Its detection capability can be expressed as the confidence level P in detecting the target. ki It can be represented by the following formula (2).

[0078] P ki (d,θ)=R ki (d)×A ki (θ) (2)

[0079] Therefore, the sensor's detection range and FOV can be used to evaluate its coverage. This embodiment evaluates the coverage capability of the sensing system based on the following assumptions: 1) The sensor's detection accuracy is basically stable within the specified detection range, but decreases with increasing distance; its accuracy can be considered as an exponential distribution. 2) The sensor's detection accuracy decreases with deviation from the FOV centerline; its accuracy can be considered as a normal distribution with the centerline as the highest point. 3) For overlapping areas of sensors, their accuracy can be calculated by superimposing their target detection accuracy. The larger the sensor's detection range, the stronger its detection capability.

[0080] Calculating the detection capability of a perception system based on the above assumptions presents a challenge in obtaining the target detection accuracy of the sensors. Given that assessing the risks of intelligent driving systems prioritizes the coverage and reliability of the perception system's detection range, and generally, the more powerful the sensor, the stronger its target detection capability.

[0081] The detection rate distribution data corresponding to the radial distribution of the vehicle sensor is acquired, and the detection rate distribution data corresponding to the angular distribution of the vehicle sensor is acquired, and based on the detection rate distribution data corresponding to the radial distribution of the vehicle sensor and the detection rate distribution data corresponding to the angular distribution of the vehicle sensor, the detection capability evaluation data of the vehicle sensor is determined.

[0082] wherein, for a sensor S k with capability E k , the detection capability P k is proportional to E k , the detection accuracy of which is independent of the distribution of the radial R and the angle A, and the accuracy radial distribution R(d) obeys an exponential distribution, the detection rate distribution data corresponding to the radial distribution of the vehicle sensor is shown in the following formula (3).

[0083]

[0084] In formula (3), R max is the maximum recognition rate; d th is the critical distance of stable recognition of the sensor, which can be the required recognition distance; d max is the nominal effective recognition distance of the sensor; k1 and k2 are empirical parameters of the distribution, and k1 < k2.

[0085] The angular distribution obeys a normal distribution with the bisector of the FOV angle as the center, and the detection rate distribution data corresponding to the angular distribution of the vehicle sensor is shown in the following formula (4).

[0086]

[0087] In formula (4), A max is the maximum recognition rate; θ is the included angle between the detected target and the bisector of the FOV angle of the sensor.

[0088] Therefore, for a sensor S k , for a target T i located at a position (d, θ), the detection capability evaluation is shown in the following formula (5).

[0089]

[0090] Based on the detection capability evaluation data of the vehicle sensor and the sensor capability quantification data, the detection capability single distribution corresponding to each vehicle detection position is determined; based on the detection capability single distribution corresponding to each vehicle detection position, the detection capability joint distribution of the perception system is constructed to obtain the first perception parameter.

[0091] wherein, for a position (d, θ), if there are m sensors covering the position, the perception system detection capability of the position can be represented as a joint distribution shown in the following formula (6).

[0092]

[0093] Due to detection capability P k Proportional to E k Therefore, data E can be quantified through sensor capabilities. k Adjust P appropriately i (d, θ) yields the individual distribution of detection capability at each vehicle detection location. Based on this individual distribution, a joint distribution of the detection capability of the entire perception system is constructed, which is then represented as a detection capability distribution map.

[0094] S130. Generate second sensing parameters based on the sensor's service life and warranty period.

[0095] The second sensing parameter is used to describe the failure probability of the sensor after use.

[0096] In some embodiments, a second sensing parameter is generated based on the sensor's lifespan and warranty period, including:

[0097] Obtain the preset sensor failure probability.

[0098] Among these factors, the safety and quality parameters of a sensor determine its reliability during use. Common safety and quality parameters include design life, warranty period, functional safety level, and quality system certification. Generally speaking, the reliability of a sensor is proportional to its design life and warranty period; furthermore, a higher functional safety level and a more complete quality system result in higher reliability.

[0099] For sensors in intelligent driving systems, the core indicator, the probability of random hardware failure (PMHF) (i.e., the preset sensor failure probability), is generally difficult to obtain, but the ASIL level is relatively easy to obtain. The ASIL level includes the minimum requirements for PMHF, as shown in Table 8.

[0100] Table 8 ASIL Level PMHF Requirements

[0101] ASIL level PMHF ASIL D ≤ 10 -9 failures / hour ASIL C ≤ 10 -8 failures / hour ASIL B ≤ 10 -7 failures / hour ASIL A ≤ 10 -6 failures / hour

[0102] This embodiment uses the lowest PMHF requirement of ASIL level, denoted as Q, as the benchmark value for reliability assessment. Generally speaking, the reliability of a sensor is relatively poor in the early stages of use, i.e., the failure rate is high, it becomes more stable in the middle stages, but the reliability gradually decreases over time in the later stages, i.e., the failure rate increases.

[0103] The sensor usage weight is determined based on the sensor's lifespan.

[0104] In some embodiments, determining the sensor use weight based on the sensor use life includes: determining a weight coefficient corresponding to the first use stage, a weight coefficient corresponding to the second use stage, and a weight coefficient corresponding to the third use stage based on the sensor use life respectively; and performing normalization processing on the weight coefficient corresponding to the first use stage, the weight coefficient corresponding to the second use stage, and the weight coefficient corresponding to the third use stage to obtain the sensor use weight.

[0105] For a sensor with a design life of T (i.e., a sensor use life) and a warranty life of Y (i.e., a sensor warranty life), generally Y >> T.

[0106] The weight coefficient w'1(t) corresponding to the first use stage is determined based on the sensor use life T, as shown in the following formula (7).

[0107]

[0108] In formula (7), a1 is the minimum weight value of the first use stage (i.e., the early stage); b1 is the percentage point position of the time point of the first use stage (i.e., the early stage); and k1 is the rising / falling rate, which is related to the sensor device and can be configured based on an empirical value.

[0109] The weight coefficient w'2(t) corresponding to the second use stage is determined based on the sensor use life T, as shown in the following formula (8).

[0110]

[0111] In formula (8), a2 is the minimum weight value of the second use stage (i.e., the middle stage); b2 is the percentage point position of the time point of the second use stage (i.e., the middle stage); T is the sensor use life; and k2 is the rising / falling rate, which is related to the sensor device and can be configured based on an empirical value.

[0112] The weight coefficient w'3(t) corresponding to the third use stage is determined based on the sensor use life T, as shown in the following formula (9).

[0113]

[0114] In formula (9), a3 is the minimum weight value of the third use stage (i.e., the late stage); b3 is the percentage point position of the time point of the third use stage (i.e., the late stage); and k3 is the rising / falling rate, which is related to the sensor device and can be configured based on an empirical value.

[0115] The weight coefficient w'1(t) corresponding to the first use stage, the weight coefficient w'2(t) corresponding to the second use stage, and the weight coefficient w'3(t) corresponding to the third use stage are normalized to obtain the sensor use weight w(t), as shown in the following formula (10). i ​

[0116]

[0117] The sensor warranty weight is determined based on a sensor warranty period.

[0118] wherein, for the warranty period effect, it is considered that it is stable at the beginning, but as time goes on, its reliability will decrease. Therefore, the warranty expiration weight w y (y) (i.e. the sensor warranty weight) can be regarded as an initial stability, which gradually decreases over time. As shown in the following formula (11).

[0119]

[0120] Formula (11), k y is a warranty reliability decrease coefficient, a y is a minimum value of reliability.

[0121] The second perception parameter is determined based on a preset sensor failure probability, a sensor use weight, and a sensor warranty weight.

[0122] wherein, the relationship between the failure probability F after the use of the sensor and the equipment use time t conforms to a mixed Weibull distribution, as shown in the following formula (12).

[0123]

[0124] In formula (12), β1<1 (early stage), β2=1 (middle stage), and β3>1 (late stage). The specific values can be obtained according to experience; η i is a scale parameter, which is related to the cumulative use time t. Generally, η<<t at the beginning, η≈t at the middle, and η<<kt at the late stage, wherein k is close to 1, such as 0.8, indicating that at 0.8t, the quality enters the late stage.

[0125] S140, a target simulation scene is obtained based on the first perception parameter and the second perception parameter, and driving decision simulation is performed on the intelligent driving vehicle in the target simulation scene, to obtain risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenes.

[0126] The simulation scene is configured based on the first perception parameter and the second perception parameter, and the target of the perception system configuration is to build the perception capability of the vehicle so that the simulation system can determine the perception range of the vehicle, such as configuring the first perception parameter into the simulation system in the form of a detection capability distribution parameter; and the second perception parameter is configured as a reliability parameter of the perception system. And configure the simulation scene parameters, such as environmental information: temperature, humidity, light intensity, rainfall and snowfall intensity; road information: road type (such as expressway, national / provincial road, urban traffic), number of lanes, signs and markings, etc.; vehicle type information: vehicle model, vehicle size; traffic scene information: other traffic participant types, driving mode, number, etc.

[0127] The risk assessment monitoring module collects vehicle driving condition information in the simulation environment in the simulation scene, judges whether a violation behavior, a general risk behavior and an accident occur. The risk assessment monitoring module obtains the speed, acceleration, driving mileage, enabled intelligent driving function, driving behavior and distance, angle and other information of the vehicle in the simulation process through the preset interface definition of the simulation system, and outputs three different risk types of violation, general risk behavior and accident. At the same time, the information of the surrounding environment in the simulation system is collected. The driving operation that is judged to have violated the road traffic law is regarded as a violation behavior; the violation behavior will be recorded as a low-risk behavior in subsequent risk assessment, and a lower accident conversion probability is given; the behavior that is judged to have violated the requirements of automatic driving specification, such as too close following, automatic stopping too close, etc. is regarded as a general risk behavior; the risk behavior is recorded as a medium-risk behavior in subsequent risk assessment, and a general accident conversion probability is given; the actual accident that occurs in the simulation process, such as vehicle rear-end collision, collision with fixed objects, etc. will be directly recorded as an accident, and the loss part and loss degree are recorded.

[0128] After the simulation scene configuration and the risk assessment monitoring model are completed, the simulation software can start the simulation process after loading the intelligent driving software system of the target vehicle, to simulate the driving process of the target vehicle under various conditions. In the simulation process, the risk assessment monitoring module will monitor the decision execution process of the vehicle, record the risk behavior data of the vehicle in the driving process, including violation behavior and accident, occurrence scene, and loss part and degree of the vehicle in the accident. At the same time, the mileage, environmental information, road information and other information of the vehicle in the simulation process are recorded. After the simulation is completed, the risk behavior is evaluated, the risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenes are determined according to the occurrence scene and number of risks, risk behavior type, loss position and degree, and stored in the risk loss record table 9.

[0129] Table 9 Risk Loss Record Table

[0130]

[0131] wherein, M is the cumulative mileage of the simulation process; K is the risk type, which is the risk behavior recorded by the risk assessment and monitoring module, including violation, general risk and accident; P is the loss part in the loss model, and one or more loss parts can exist in one risk behavior; D is the loss degree of the corresponding part, which is expressed by a percentage value, and the intact damage is 0%, and the complete damage is 100%; and C is the occurrence number of the risk behavior.

[0132] For the violation and general risk behavior, no actual loss is caused, but there is potential loss possibility. A given conversion probability and a fixed loss value are given to convert it into an accident loss. That is, if the system detects that 100 times of illegal lane changing occur, if the given conversion probability is 1% and the loss is 2000 yuan, then in the risk loss record table, when the loss is counted, a loss of 2000 yuan in the lane changing scene is recorded.

[0133] S150, based on the risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenes, determining the scene accident loss of the intelligent driving vehicle.

[0134] wherein, in view of the different vehicle loss parts and loss degrees caused by the accident, the vehicle is modeled according to its position area in this embodiment, and the vehicle value is divided into each area; on the basis of the foregoing risk loss record table, the loss of each accident is calculated.

[0135] This embodiment divides the vehicle into 10 areas, including front, left front, right front, rear, left rear, right rear, left, right, upper and other areas. And the total value of the vehicle is allocated to different value intervals according to the value and repair cost of the vehicle parts. In view of the fact that the front part of the vehicle is generally configured with more components, the front part is further divided into front front part, front middle part and front rear part to accurately evaluate the loss. In view of the fact that the difference in vehicle configuration leads to the difference in accessories and repair cost, only regional division is made when calculating the vehicle loss to support loss description and loss valuation. The specific allocation ratio parameters can be manually configured.

[0136] In some embodiments, the risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenes includes: a plurality of vehicle loss areas, simulation loss degrees of the vehicle loss areas corresponding to different driving scenes, and simulation risk numbers of the vehicle loss areas corresponding to different driving scenes.

[0137] Based on the risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenes, determining the scene accident loss of the intelligent driving vehicle, including:

[0138] Based on the preset repair cost coefficient of each vehicle loss area, the overall estimated value of the vehicle and the simulated loss degree of each vehicle loss area corresponding to different driving scenarios, the simulated loss value of each vehicle loss area corresponding to different driving scenarios is determined; based on the simulated loss value of each vehicle loss area corresponding to different driving scenarios, the simulated risk number of the vehicle loss area corresponding to different driving scenarios and the simulated driving mileage corresponding to different driving scenarios, the scene accident loss of the intelligent driving vehicle is determined.

[0139] Among them, due to the difference between the vehicle configurations, there is a big difference between the same area spare parts value and repair cost of different vehicle models. Therefore, different parameters can be used for manual configuration for different vehicle models.

[0140] The simulated loss value of the vehicle loss area corresponding to different driving scenarios Loss p The following formula (13) can be used to determine.

[0141] Loss p = Value·R p ·D p (13)

[0142] In formula (13), Value is the overall estimated value of the vehicle; R p is the preset repair cost coefficient, expressed as a percentage, which can be manually configured according to the vehicle configuration and repair area. Due to the fact that the vehicle's spare parts ratio usually exceeds 100%, the coefficients of all areas can exceed 100%; D p is the simulated loss degree of the vehicle loss area corresponding to different driving scenarios.

[0143] The scene accident loss L s of the intelligent driving vehicle can be determined using the following formula (14).

[0144]

[0145] In formula (14), S is the scene set; P i is the loss site, i.e. the vehicle loss area; L i is the simulated loss value of the vehicle loss area corresponding to different driving scenarios; C i is the number of risk behaviors, i.e. the simulated risk number; M i is the driving mileage of scene i in the vehicle simulation process when the risk behavior occurs.

[0146] S160, based on the intelligent driving scene mileage and the total vehicle mileage, determine the intelligent driving scene occurrence probability, and based on the intelligent driving scene occurrence probability, the scene accident loss of the intelligent driving vehicle, the insurance premium rate and the expected driving mileage of the intelligent driving vehicle, evaluate the benchmark premium of the intelligent driving vehicle.

[0147] wherein the ratio of the intelligent driving scene driving mileage (e.g., annual intelligent driving scene driving mileage) and the total vehicle driving mileage (e.g., annual total driving mileage) can be determined as the intelligent driving scene occurrence probability. The benchmark premium H of the intelligent driving vehicle can be determined using the following formula (15).

[0148]

[0149] In formula (15), X1 is the intelligent driving scene occurrence probability; X2 is the expected driving mileage; and X3 is the insurance rate, which is the ratio of the premium and the insurance amount.

[0150] In this embodiment, multi-level sensor data is obtained, including sensor technical parameters, sensor detection parameters, and sensor safety and quality parameters. A first perception parameter is generated based on the multi-level sensor data, which is used to describe the joint distribution of the detection capability of the perception system. The first perception parameter is constructed from the single-item distribution of the detection capability corresponding to each vehicle detection position covered by the multi-sensor. The single-item distribution of the detection capability corresponding to each vehicle detection position is determined from the multi-level sensor data. A second perception parameter is generated based on the sensor service life and the sensor warranty period, which is used to describe the failure probability of the sensor after use. The first perception parameter and the second perception parameter are used to configure a simulation scenario, obtain a target simulation scenario, and simulate driving decisions of the intelligent driving vehicle in the target simulation scenario to obtain risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenarios. The scene accident loss of the intelligent driving vehicle is determined based on the risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenarios. The intelligent driving scene occurrence probability is determined based on the intelligent driving scene driving mileage and the total vehicle driving mileage. The benchmark premium of the intelligent driving vehicle is evaluated based on the intelligent driving scene occurrence probability, the scene accident loss of the intelligent driving vehicle, the insurance rate, and the expected driving mileage of the intelligent driving vehicle. In this way, the intelligent driving simulation is performed by constructing a simulation scenario, which does not rely on the driving data and historical claim data of the vehicle, but only relies on the vehicle configuration data, thereby effectively realizing the rapid and accurate premium evaluation of the vehicle.

[0151] In some embodiments, the method further comprises:

[0152] Intelligent driving usage data of the intelligent driving vehicle corresponding to the historical driving scenarios is obtained, and the intelligent driving driving level corresponding to the intelligent driving vehicle is determined based on the intelligent driving usage data of the intelligent driving vehicle corresponding to the historical driving scenarios. The benchmark premium of the intelligent driving vehicle is adjusted based on the intelligent driving driving level corresponding to the intelligent driving vehicle.

[0153] The intelligent driving vehicle corresponds to the intelligent driving usage data in the historical driving scene, such as the number of times or the time length of starting intelligent driving of the intelligent driving vehicle in the historical driving process. If the number of times or the time length of starting intelligent driving exceeds a preset threshold, the benchmark premium of the intelligent driving vehicle is increased; if the number of times or the time length of starting intelligent driving does not exceed the preset threshold, the benchmark premium of the intelligent driving vehicle is reduced. Thus, the benchmark premium of the intelligent driving vehicle can be adjusted adaptively based on the intelligent driving usage.

[0154] The embodiment evaluates the performance and reliability of the intelligent driving vehicle perception system based on the configuration parameters of the intelligent driving vehicle perception system, and then loads the perception system parameters and the decision execution system capability through the simulation system, simulates and analyzes the accident probability and loss in the simulation system through multi-scene simulation, so as to calculate the benchmark premium of the vehicle, thereby facilitating the insurance company and the vehicle manufacturer to realize the premium pricing of the intelligent driving liability insurance.

[0155] Figure 3 A structure schematic diagram of an intelligent driving vehicle premium evaluation device provided by the embodiment is provided. The intelligent driving vehicle premium evaluation device can include:

[0156] The acquisition module 310 is configured to acquire sensor multi-level data, and the sensor multi-level data includes sensor technical parameters, sensor detection parameters, and sensor safety and quality parameters.

[0157] The first generation module 320 is configured to generate a first perception parameter based on the sensor multi-level data, and the first perception parameter is used to describe the joint distribution of the detection capability of the perception system. The first perception parameter is constructed from the detection capability single-item distribution corresponding to each vehicle detection position covered by the multi-sensor. The detection capability single-item distribution corresponding to each vehicle detection position is determined from the sensor multi-level data.

[0158] The second generation module 330 is configured to generate a second perception parameter based on the sensor usage period and the sensor warranty period, and the second perception parameter is used to describe the failure probability of the sensor after use.

[0159] The first determination module 340 is configured to configure a simulation scene based on the first perception parameter and the second perception parameter, obtain a target simulation scene, and simulate driving decisions of the intelligent driving vehicle in the target simulation scene, to obtain risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenes.

[0160] The second determination module 350 is configured to determine the scene accident loss of the intelligent driving vehicle based on the risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenes.

[0161] The evaluation module 360 is configured to determine a smart driving scene occurrence probability based on the smart driving scene mileage and the total mileage of the vehicle, and evaluate the benchmark premium of the intelligent driving vehicle based on the smart driving scene occurrence probability, the scene accident loss of the intelligent driving vehicle, the insurance premium rate, and the expected mileage of the intelligent driving vehicle.

[0162] In this embodiment, the first generation module 320, optionally, includes a first determination unit, a second determination unit, a third determination unit, and a construction unit.

[0163] The first determination unit is configured to quantitatively assign the sensor multi-level data based on the data belonging class of the sensor multi-level data to obtain quantitatively assigned data corresponding to the sensor multi-level data, and obtain sensor capability quantization data based on the quantitatively assigned data corresponding to the sensor multi-level data and the parameter weight ratio corresponding to the sensor multi-level data.

[0164] The second determination unit is configured to obtain detection rate distribution data corresponding to radial distribution of the vehicle sensor, and obtain detection rate distribution data corresponding to angle distribution of the vehicle sensor, and determine detection capability evaluation data of the vehicle sensor based on the detection rate distribution data corresponding to radial distribution of the vehicle sensor and the detection rate distribution data corresponding to angle distribution of the vehicle sensor.

[0165] The third determination unit is configured to determine the detection capability single distribution corresponding to each vehicle detection position based on the detection capability evaluation data of the vehicle sensor and the sensor capability quantization data.

[0166] The construction unit is configured to construct the detection capability joint distribution of the perception system based on the detection capability single distribution corresponding to each vehicle detection position to obtain the first perception parameter.

[0167] In this embodiment, the first determination unit, optionally, is specifically configured to:

[0168] Classify the sensor multi-level data based on the belonging class to obtain discrete class data and continuous class data; for the discrete class data, perform assignment processing on the discrete class data based on the corresponding detection capability representation data to obtain discrete assignment data; for the continuous class data, perform linear assignment processing on the continuous class data based on the corresponding smart driving compliance representation data to obtain continuous assignment data; and determine the quantitatively assigned data corresponding to the sensor multi-level data based on the discrete assignment data and the continuous assignment data.

[0169] In this embodiment, the second generation module 330, optionally, includes an acquisition unit, a fourth determination unit, and a fifth determination unit.

[0170] The acquisition unit is configured to acquire a preset sensor failure probability.

[0171] The fourth determining unit is configured to determine a sensor use weight based on the sensor use period, and determine a sensor warranty weight based on the sensor warranty period.

[0172] The fifth determining unit is configured to determine the second perception parameter based on a preset sensor failure probability, the sensor use weight, and the sensor warranty weight.

[0173] In this embodiment, the fourth determining unit is specifically configured to:

[0174] The sensor use weight is determined based on the weight coefficient corresponding to the first use stage, the weight coefficient corresponding to the second use stage, and the weight coefficient corresponding to the third use stage.

[0175] In this embodiment, the risk loss simulation data corresponding to different driving scenes of the intelligent driving vehicle includes: a plurality of vehicle loss regions, a simulation loss degree of each vehicle loss region corresponding to different driving scenes, and a simulation risk number of each vehicle loss region corresponding to different driving scenes.

[0176] The second determining module 350 is specifically configured to:

[0177] The simulation loss value of each vehicle loss region corresponding to different driving scenes is determined based on a preset repair cost coefficient of each vehicle loss region, an overall estimated value of the vehicle, and a simulation loss degree of each vehicle loss region corresponding to different driving scenes.

[0178] In this embodiment, the adjustment module is further included.

[0179] The acquisition module 310 is further configured to acquire the intelligent driving data corresponding to the historical driving scenes of the intelligent driving vehicle, and determine the intelligent driving driving level corresponding to the intelligent driving vehicle based on the intelligent driving data corresponding to the historical driving scenes of the intelligent driving vehicle.

[0180] The adjustment module is configured to optimize and adjust the benchmark premium of the intelligent driving vehicle based on the intelligent driving driving level corresponding to the intelligent driving vehicle.

[0181] The premium evaluation device for the intelligent driving vehicle provided by the present disclosure can execute the above-mentioned method embodiments, and the specific implementation principles and technical effects can be referred to the above-mentioned method embodiments, which will not be described here again.

[0182] The embodiment of the present application further provides a computer device. Specifically, refer to Figure 4 Figure 4 The basic structure block diagram of the computer device is shown in the figure.

[0183] The computer device comprises a memory 410 and a processor 420 which are connected to each other through a system bus. It should be noted that only the computer device with the memory 410 and the processor 420 is shown in the figure, but it should be understood that all the components shown are not required to be implemented, and more or fewer components can be alternatively implemented. It can be understood by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculation and / or information processing according to pre-set or stored instructions, and the hardware thereof includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0184] The computer device can be a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The computer device can interact with a user through a keyboard, a mouse, a remote controller, a touchpad, a voice control device and the like.

[0185] ​The memory 410 includes at least one type of readable storage medium, including non-volatile memory or volatile memory, for example, flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. The RAM can include static RAM or dynamic RAM. In some embodiments, the memory 410 can be an internal storage unit of the computer device, for example, a hard disk or a memory of the computer device. In other embodiments, the memory 410 can also be an external storage device of the computer device, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, or a flash card, etc. equipped on the computer device. Of course, the memory 410 can include both the internal storage unit and the external storage device of the computer device. In the present embodiment, the memory 410 is generally used to store an operating system and various application software installed on the computer device, for example, program codes of the above method, etc. In addition, the memory 410 can also be used to temporarily store various data that has been output or will be output.

[0186] The processor 420 is generally used to perform the overall operation of the computer device. In the present embodiment, the memory 410 is used to store program codes or instructions, the program codes including computer operation instructions, and the processor 420 is used to execute the program codes or instructions stored in the memory 410 or process data, for example, run the program codes of the above method.

[0187] In this document, the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, among others. The bus system can be a system of address, data, and control buses, for example. For the sake of presentation, the detailed wiring for bus transactions has been omitted, except for the interconnection of buses themselves. For example, a bus interface unit is typically used to implement the wiring for addressing transactions that make up the genetic bus protocol in order to communicate with the direct-connected, or “on-die” components of the system.

[0188] Another embodiment of the present application further provides a computer readable medium, which can be a computer readable signal medium or a computer readable storage medium. A processor in a computer reads the computer readable program code stored in the computer readable medium, so that the processor can perform the function actions specified in each step or combination of steps in the above method; and generates a device implementing the function actions specified in each block or combination of blocks in the block diagram.

[0189] The computer readable medium includes, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any suitable combination of the foregoing, for storing program codes or instructions, which include computer operation instructions, and a processor for executing the program codes or instructions of the above method stored in the memory.

[0190] The definition of the memory and the processor can refer to the description of the foregoing computer device embodiment, which will not be repeated here.

[0191] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed each other can be indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0192] The function units or modules in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software function unit.

[0193] If the integrated unit is implemented in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0194] In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of both hardware and software, and any combination thereof. In the device claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The mere fact that certain measures are recited in mutually different claims does not indicate that a combination of these measures cannot be used to advantage. The use of relative terms such as "first", "second" and "third", etc. does not connote any prioritization, but such terms are used to distinguish a certain feature from another feature with the same name. The steps of the above-described methods shall not be understood as necessarily limited to the order in which they are presented.

[0195] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; even though the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for assessing insurance premiums for intelligent driving vehicles, characterized in that, include: Acquire multi-level sensor data, which includes: sensor technical parameters, sensor detection parameters, and sensor safety and quality parameters; A first perception parameter is generated based on the multi-level data from the sensors. The first perception parameter is used to describe the joint distribution of the detection capability of the perception system. The first perception parameter is constructed from the individual distribution of the detection capability corresponding to each vehicle detection location covered by the multi-sensor system. The individual distribution of the detection capability corresponding to each vehicle detection location is determined by the multi-level data from the sensors. A second sensing parameter is generated based on the sensor's service life and warranty period. The second sensing parameter is used to describe the failure probability of the sensor after use. Based on the first perception parameter and the second perception parameter, a simulation scenario is configured to obtain a target simulation scenario. Driving decision simulation is performed on the intelligent driving vehicle in the target simulation scenario to obtain risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenarios. Based on the risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenarios, the scenario accident loss of the intelligent driving vehicle is determined. The probability of an intelligent driving scenario is determined based on the driving mileage in the intelligent driving scenario and the total driving mileage of the vehicle. Based on the probability of the intelligent driving scenario, the scenario accident loss of the intelligent driving vehicle, the insurance rate, and the expected driving mileage of the intelligent driving vehicle, the benchmark insurance premium of the intelligent driving vehicle is evaluated.

2. The method according to claim 1, characterized in that, The generation of the first sensing parameters based on the multi-level data from the sensor includes: Based on the data category of the multi-level sensor data, the multi-level sensor data is quantized and assigned values ​​to obtain the quantized assigned data corresponding to the multi-level sensor data. Based on the quantized assigned data corresponding to the multi-level sensor data and the parameter weight ratio corresponding to the multi-level sensor data, sensor capability quantization data is obtained. Acquire the detection rate distribution data of the vehicle sensor corresponding to the radial distribution, and acquire the detection rate distribution data of the vehicle sensor corresponding to the angular distribution, and determine the detection capability evaluation data of the vehicle sensor based on the detection rate distribution data of the vehicle sensor corresponding to the radial distribution and the detection rate distribution data of the vehicle sensor corresponding to the angular distribution. Based on the detection capability evaluation data of the vehicle sensors and the sensor capability quantification data, the individual distribution of detection capability corresponding to each vehicle detection location is determined. The joint distribution of the detection capabilities of the perception system is constructed based on the individual distribution of the detection capabilities corresponding to each vehicle detection location, so as to obtain the first perception parameter.

3. The method according to claim 2, characterized in that, The step of quantizing and assigning values ​​to the multi-level sensor data based on its data class to obtain quantized data corresponding to the multi-level sensor data includes: The multi-level data from the sensor is divided into discrete and continuous data categories. For the discrete data, the discrete data is assigned a value based on the corresponding detection capability representation data to obtain discrete assigned data. For the continuous data, linear scoring is performed on the continuous data based on the corresponding intelligent driving compliance representation data to obtain continuous assigned data; Based on the discrete assignment data and the continuous assignment data, the quantization assignment data corresponding to the multi-level data of the sensor is determined.

4. The method according to claim 1, characterized in that, The generation of the second sensing parameters based on the sensor's service life and warranty period includes: Obtain the preset sensor failure probability; The sensor usage weight is determined based on the sensor's service life, and the sensor warranty weight is determined based on the sensor's warranty period. The second sensing parameter is determined based on the preset sensor failure probability, the sensor usage weight, and the sensor quality assurance weight.

5. The method according to claim 4, characterized in that, The process of determining the sensor usage weight based on the sensor's service life includes: Based on the sensor's service life, the weighting coefficients corresponding to the first use stage, the second use stage, and the third use stage are determined respectively. The weight coefficients corresponding to the first usage stage, the second usage stage, and the third usage stage are normalized to obtain the sensor usage weight.

6. The method according to claim 1, characterized in that, The simulated risk loss data of the intelligent driving vehicle corresponding to different driving scenarios includes: multiple vehicle loss areas, the simulated loss degree of the vehicle loss area corresponding to different driving scenarios, and the simulated risk number of the vehicle loss area corresponding to different driving scenarios. Based on the risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenarios, the scenario accident loss of the intelligent driving vehicle is determined, including: Based on the preset repair cost coefficient of each vehicle damage area, the overall estimated value of the vehicle, and the simulated loss degree of each vehicle damage area corresponding to different driving scenarios, the simulated loss value of each vehicle damage area corresponding to different driving scenarios is determined. The scenario accident loss of the intelligent driving vehicle is determined based on the simulated loss value of each vehicle loss area corresponding to different driving scenarios, the simulated risk number of each vehicle loss area corresponding to different driving scenarios, and the simulated driving mileage corresponding to different driving scenarios.

7. The method according to claim 1, characterized in that, Also includes: The intelligent driving vehicle's intelligent driving usage data in historical driving scenarios is obtained, and the intelligent driving driving level corresponding to the intelligent driving vehicle is determined based on the intelligent driving vehicle's intelligent driving usage data in historical driving scenarios. The base insurance premium for the intelligent driving vehicle is optimized and adjusted based on the intelligent driving driving level corresponding to the intelligent driving vehicle.

8. A premium assessment device for intelligent driving vehicles, characterized in that, include: The acquisition module is used to acquire multi-level sensor data, which includes: sensor technical parameters, sensor detection parameters, and sensor safety and quality parameters. The first generation module is used to generate a first perception parameter based on the multi-level data of the sensors. The first perception parameter is used to describe the joint distribution of the detection capability of the perception system. The first perception parameter is constructed by the individual distribution of the detection capability corresponding to each vehicle detection position covered by the multi-sensor. The individual distribution of the detection capability corresponding to each vehicle detection position is determined by the multi-level data of the sensors. The second generation module is used to generate a second sensing parameter based on the sensor's service life and the sensor's warranty period. The second sensing parameter is used to describe the failure probability of the sensor after use. The first determining module is used to configure a simulation scenario based on the first perception parameter and the second perception parameter to obtain a target simulation scenario, and to perform driving decision simulation on the intelligent driving vehicle in the target simulation scenario to obtain risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenarios. The second determining module is used to determine the scenario accident loss of the intelligent driving vehicle based on the risk loss simulation data of the intelligent driving vehicle corresponding to different driving scenarios. The evaluation module is used to determine the probability of occurrence of intelligent driving scenarios based on the driving mileage in intelligent driving scenarios and the total driving mileage of the vehicle, and to evaluate the benchmark premium of the intelligent driving vehicle based on the probability of occurrence of intelligent driving scenarios, the scenario accident loss of the intelligent driving vehicle, the insurance rate, and the expected driving mileage of the intelligent driving vehicle.

9. A computer device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the premium assessment method for intelligent driving vehicles as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the premium assessment method for intelligent driving vehicles as described in any one of claims 1 to 7.

Images