Vehicle commercial insurance premium pricing method, system and device, storage medium and product

Abstract

The invention discloses a vehicle commercial insurance premium pricing method, system and device, a storage medium and a product, and relates to the technical field of automatic vehicle insurance, and the method comprises the steps: matching a basic rate corresponding to an automatic driving vehicle from an insurance contract library; obtaining SOTIF data of the autonomous vehicle; determining a main engine plant responsibility coefficient and a residual risk coefficient through a responsibility actuarial engine; calculating a total loss measure according to the SOTIF data; and on the basis of the basic rate, the main engine plant responsibility coefficient, the total loss measurement and the residual risk coefficient, calculating to obtain the commercial insurance expense of the autonomous vehicle. According to the method, the automatic driving commercial insurance premium actuarial model based on the SOTIF is constructed through the basic rate, the main engine plant responsibility coefficient, the total loss measurement and the residual risk coefficient, the accident responsibility can be accurately defined, the multi-dimensional loss can be quantified, the matching precision of the insurance premium and the real risk is remarkably improved, and accurate pricing is achieved.

Description

Technical Field

[0001] This application relates to the field of autonomous vehicle insurance technology, and in particular to vehicle commercial insurance premium pricing methods, systems, equipment, storage media and products. Background Technology

[0002] The existing auto insurance system has revealed three structural flaws in the commercialization of Level 4 Robotaxi (driverless taxis), making it difficult to adapt to the new logic of liability attribution: Ineffective Liability Delineation: Traditional auto insurance centers on "driver's primary responsibility," but in Level 4 autonomous driving, humans have no operational obligation, and liability for accidents essentially shifts to the OEM or system supplier. Existing insurance terms do not establish a clear compensation mechanism for damages caused by limitations in the system's intended functionality (such as collisions in unknown SOTIF scenarios), creating a liability vacuum.

[0003] Lack of standardized damage assessment: Current damage assessment still relies on the physical collision damage cost model based on NCAP (New Car Assessment Program), which only assesses vehicle repair costs and does not cover the ethical consequences of decisions unique to autonomous driving (such as secondary accidents caused by malicious avoidance). According to statistics from the ISO 21448 SOTIF case library, approximately 32% of L4-related accidents result in ethical disputes and claims, but there is a lack of corresponding damage quantification and compensation criteria.

[0004] Actuarial risk is out of sync: Traditional actuarial models rely heavily on historical human-caused accident data and cannot capture the dynamic risk changes brought about by continuous OTA updates of autonomous driving systems (such as new versions being exposed to more edge scenarios). Munich Re research points out that this can lead to premium pricing discrepancies exceeding 300%, seriously affecting product feasibility and market fairness.

[0005] In summary, the existing insurance system cannot support the safety governance and commercialization of L4 Robotaxi in the three major aspects of liability determination, loss assessment and risk pricing, resulting in the inability to accurately price insurance premiums for L4 Robotaxi. Summary of the Invention

[0006] The main purpose of this application is to provide a method, system, device, storage medium and product for pricing commercial vehicle insurance premiums, which aims to solve the technical problem that the existing insurance system cannot achieve accurate premium pricing for L4 autonomous vehicles.

[0007] To achieve the above objectives, this application proposes a vehicle commercial insurance premium pricing method, which includes: Match the base premium rate corresponding to the autonomous vehicle from the insurance contract database; Obtain expected functional safety SOTIF data for autonomous vehicles; Based on the SOTIF data, the OEM liability coefficient and residual risk coefficient are determined by a pre-built liability actuarial engine. Calculate the total loss metric caused by the autonomous vehicle based on the SOTIF data; The commercial insurance for the autonomous vehicle is calculated based on the base rate, the OEM liability coefficient, the total loss metric, and the residual risk coefficient.

[0008] In one embodiment, the step of matching the base premium rate corresponding to the autonomous vehicle from the insurance contract database includes: The initial base rate is determined in the insurance contract database based on the vehicle value of the autonomous vehicle, the risk coefficient corresponding to the operating area, the historical benchmark rate, and the expected insured amount. The vehicle value is determined based on the cost of sensors and autonomous driving hardware in the vehicle configuration, and the regional risk coefficient is determined based on the traffic complexity of the operating area.

[0009] In one embodiment, after the step of determining the initial base rate in the insurance contract database based on the vehicle value of the autonomous vehicle, the risk coefficient corresponding to the operating area, the historical benchmark rate, and the expected insured amount, the method further includes: Obtain the actual loss ratio, accident rate per thousand kilometers, and SOTIF scenario pass rate during fleet operation; The loss ratio variation coefficient is determined based on the deviation between the actual loss ratio and the target loss ratio, the trend of the accident rate per thousand kilometers, and the pass rate of the SOTIF scenario. The initial base rate is adjusted based on the loss ratio change coefficient to obtain the updated base rate.

[0010] In one embodiment, the step of determining the OEM liability coefficient and residual risk coefficient based on the SOTIF data using a pre-built actuarial engine includes: Based on the SOTIF data, determine whether the autonomous vehicle was within the preset operating domain (ODD) at the time of the accident; Based on the judgment results, the OEM responsibility weight, and the user / third-party responsibility weight, the OEM responsibility coefficient is determined through the pre-built responsibility actuarial engine. Based on the effectiveness coefficient, verification coverage coefficient, confirmation activity adequacy coefficient, and scenario exposure intensity of the design protective measures for the preset unsafe scenarios in the SOTIF data, the residual risk coefficient is calculated.

[0011] In one embodiment, the step of determining the OEM responsibility coefficient using the pre-built responsibility actuarial engine based on the judgment result, the OEM responsibility weight, and the user / third-party responsibility weight includes: If it is determined that the autonomous vehicle is within the ODD range, then the autonomous vehicle's Out of Design Domain Ratio (ODR), Safety Takeover Request Frequency (SOR), Remote Takeover Response Timeliness (RTR), and Vehicle Failure Rate (VFR) are obtained, and the OEM responsibility coefficient is calculated based on the ODR, SOR, RTR, and VFR. If it is determined that the autonomous vehicle is outside the scope of the ODD, the OEM liability coefficient is determined as the user / third-party liability weight based on whether a valid takeover prompt was issued before the accident and the user operation record.

[0012] In one embodiment, the step of calculating the total loss metric caused by the autonomous vehicle based on the SOTIF data includes: In the accident scenarios represented by the SOTIF data, the losses caused by the accident are evaluated in a multi-dimensional monetary form, resulting in property damage, personal injury damage, data and privacy damage, and brand reputation damage. Among them, the property loss is determined based on vehicle repair costs and third-party damages; the personal injury is calculated according to preset personal injury compensation rules and injury parameters; the data and privacy loss is determined based on the sensitive type and quantity of the leaked data combined with a preset compensation unit price; and the brand reputation loss is estimated by analyzing the impact of the accident and combining it with a preset corporate market value fluctuation model. The total loss measure is obtained by summing the property loss, personal injury loss, data and privacy loss, and brand reputation loss.

[0013] Furthermore, to achieve the above objectives, this application also proposes a vehicle commercial insurance premium pricing system, which includes... The first parameter determination module matches the basic premium rate corresponding to the autonomous vehicle from the insurance contract database; The data acquisition module is used to acquire the expected functional safety SOTIF data of autonomous vehicles. The second parameter determination module is used to determine the OEM liability coefficient and residual risk coefficient based on the SOTIF data and through a pre-built liability actuarial engine. The third parameter determination module is used to calculate the total loss metric caused by the autonomous vehicle based on the SOTIF data. The premium calculation module is used to calculate the commercial insurance cost of the autonomous vehicle based on the base rate, the OEM liability coefficient, the total loss metric, and the residual risk coefficient.

[0014] In addition, to achieve the above objectives, this application also proposes a vehicle commercial insurance premium pricing device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle commercial insurance premium pricing method as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and which, when executed by a processor, implements the steps of the vehicle commercial insurance premium pricing method described above.

[0016] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the vehicle commercial insurance premium pricing method described above.

[0017] This application proposes a method, system, device, storage medium, and product for pricing commercial vehicle insurance premiums. The method includes: matching a base rate corresponding to an autonomous vehicle from an insurance contract database; obtaining the Expected Functional Safety Index (SOTIF) data for the autonomous vehicle; determining the OEM liability coefficient and residual risk coefficient based on the SOTIF data using a pre-built actuarial engine; calculating the total loss measure caused by the autonomous vehicle based on the SOTIF data; and calculating the commercial insurance premium for the autonomous vehicle based on the base rate, the OEM liability coefficient, the total loss measure, and the residual risk coefficient. This method, by integrating the base rate, the OEM liability coefficient, the total loss measure, and the residual risk coefficient, constructs a SOTIF-based actuarial model for autonomous driving commercial insurance premiums. This model not only clearly defines accident liability and effectively quantifies the assessment standards for multi-dimensional losses, but also significantly improves the accuracy of matching premium pricing with actual risk. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0019] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating the vehicle commercial insurance premium pricing method of this application (Example 1); Figure 2This is a flowchart illustrating the second embodiment of the vehicle commercial insurance premium pricing method in this application. Figure 3 A simplified flowchart illustrating the vehicle commercial insurance premium pricing method provided in Embodiment 2 of this application; Figure 4 This is a schematic diagram of the module structure of the vehicle commercial insurance premium pricing system according to an embodiment of this application; Figure 5 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the vehicle commercial insurance premium pricing method in this application embodiment.

[0021] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0022] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0023] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0024] The main solution of this application embodiment is as follows: matching the basic premium rate corresponding to the autonomous vehicle from the insurance contract database; obtaining the expected functional safety SOTIF data of the autonomous vehicle; determining the OEM liability coefficient and residual risk coefficient based on the SOTIF data through a pre-built liability actuarial engine; calculating the total loss measure caused by the autonomous vehicle based on the SOTIF data; and calculating the commercial insurance for the autonomous vehicle based on the basic premium rate, OEM liability coefficient, total loss measure and residual risk coefficient.

[0025] In this embodiment, for ease of description, the following description will focus on the vehicle commercial insurance premium pricing system.

[0026] Traditional auto insurance, primarily based on the "driver's primary responsibility" principle, is ill-suited for Level 4 autonomous driving scenarios—where the OEM bears the majority of liability in an accident, rendering existing liability determination mechanisms ineffective. Furthermore, the Insurance Association continues to use NCAP's physical collision damage cost model for pricing, failing to incorporate the ethical consequences of autonomous driving decisions into loss assessment, resulting in a lack of standardized damage assessment criteria. In addition, existing actuarial models rely on historical human-caused accident data, making it impossible to assess the iterative risks of autonomous driving systems, leading to a severe disconnect between premium pricing and actual risk.

[0027] This application provides a solution that, by introducing a liability actuarial engine based on SOTIF (Expected Functional Safety) data, constructs a commercial premium pricing model that integrates OEM liability coefficients, residual risk coefficients, multi-dimensional total loss measurements, and dynamic base rates, thereby achieving accurate division of liability for L4 autonomous vehicle accidents, comprehensive quantification of losses, and effective alignment of premiums with actual risks.

[0028] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device or vehicle-mounted computing unit capable of performing the above functions. The following description uses a vehicle-mounted computing unit as an example to illustrate this embodiment and the subsequent embodiments.

[0029] Based on this, the embodiments of this application provide a method for pricing commercial vehicle insurance premiums, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the vehicle commercial insurance premium pricing method of this application.

[0030] In this embodiment, the vehicle commercial insurance premium pricing method includes steps S10 to S50: Step S10: Match the basic premium rate corresponding to the autonomous vehicle from the insurance contract database; It should be noted that the base premium rate (denoted as K) represents the benchmark premium coefficient required to cover the agreed sum insured under the standardized risk assumption (i.e., without considering specific accident liability and residual risk).

[0031] Understandably, because Level 4 autonomous vehicles differ significantly from traditional manned vehicles in hardware configuration and operational scenario characteristics, directly using the static rate tables of historical commercial vehicles or private cars would fail to reflect the high-value sensor costs of Robotaxis, exposure to complex urban operations, and new risk exposures, leading to a significant deviation of insurance from the true cost. Therefore, step S40, by constructing a dynamic basic rate matching mechanism oriented towards the characteristics of autonomous driving, avoids the problems of insufficient coverage or over-insurance caused by "one-size-fits-all" pricing, thereby achieving an initial rate setting that accurately aligns with the vehicle's technical attributes, operating environment, and coverage needs.

[0032] In one feasible embodiment, step S10 may include step S11: Step S11: Determine the initial base rate in the insurance contract database based on the vehicle value of the autonomous vehicle, the risk coefficient corresponding to the operating area, the historical benchmark rate, and the expected insured amount.

[0033] In this embodiment, the initial base rate (denoted as K_initial) is determined by a combination of factors, including vehicle value, risk coefficient of the operating area, historical benchmark rate, and expected insured amount, i.e., K_initial = f(vehicle value, regional risk coefficient, historical benchmark rate, expected insured amount).

[0034] The vehicle value refers to the purchase or replacement cost of an autonomous vehicle, especially including high-value specialized components such as LiDAR, high-performance domain controllers, and redundant braking systems. For example, a Robotaxi equipped with five or more mechanical LiDARs can have a vehicle value 3–5 times that of a regular passenger car, corresponding to a higher K_initial value. The operational area risk coefficient represents the risk level of a region based on geofencing. For example, the K value for vehicles operating in urban centers (such as Lujiazui in Shanghai) is higher than that for vehicles operating in simple suburban areas; The historical benchmark rates are based on traditional commercial vehicle insurance costs and the average claim costs of early Robotaxi test vehicles. The expected sum insured is the maximum compensation limit that the policyholder hopes to be covered. The higher the sum insured, the higher K_initial will be, in order to cover the risk of potentially large payouts.

[0035] After obtaining K_initial, it is necessary to dynamically adjust the base rate (K_new) based on the vehicle's annual operating performance and historical accident records. The specific annual adjustment mechanism and post-accident rate correction method will be described in detail in another embodiment.

[0036] Through the above steps, this embodiment ensures that the base rate not only reflects the asset value of the vehicle itself, but also incorporates spatial risk differences and historical experience data, laying a reasonable starting point for the subsequent introduction of SOTIF-driven dynamic risk factors (OEM liability coefficient α, total loss metric L_total, residual risk coefficient), and ultimately achieving the fair actuarial principle of "high risk, high pricing; low risk, low premium".

[0037] Step S20: Obtain the expected functional safety SOTIF data of the autonomous vehicle; It should be noted that SOTIF (Safety of the Intended Functionality) refers to the technical framework that, under the premise of no hardware failure or software malfunction, the perception, decision-making, and control modules have insufficient processing capabilities for known or unknown scenarios within the Design Operating Domain (ODD), causing the system behavior to deviate from expectations and triggering potential safety risks.

[0038] In this embodiment, the SOTIF data serves as the core input for risk quantification in the liability determination domain, encompassing key information such as environmental conditions at the time of the accident, vehicle status, system response behavior, and ODD compliance records. By analyzing this data, it can be determined whether the accident was caused by limitations in the system's intended functionality, thereby supporting the calculation of the OEM's liability coefficient, the assessment of residual risk coefficients, and the triggering and modeling of total loss measurement.

[0039] Specifically, SOTIF data comes from the operation logs of autonomous vehicles, raw sensor data, high-precision map matching results, and system event records. After preprocessing, it is input into the liability actuarial engine to drive the subsequent liability division, loss assessment, and premium calculation processes, ensuring that insurance pricing has technical traceability and risk consistency.

[0040] Step S30: Based on the SOTIF data, determine the OEM liability coefficient and residual risk coefficient using a pre-built liability actuarial engine; It should be noted that the OEM liability coefficient (denoted as α) is used to characterize the proportion of responsibility that the OEM should bear in the event of an accident involving an autonomous vehicle. Its value is mainly determined by whether the vehicle is within its Operational Design Domain (ODD) at the time of the accident.

[0041] Here, ODD refers to the set of conditions under which an autonomous driving system is designed to operate safely, including but not limited to specific road types, geographical areas, environmental conditions (such as lighting and weather), vehicle speed ranges, traffic density, and time intervals. Only within these defined ranges does the system promise to possess the expected functional safety performance.

[0042] It should also be noted that the residual risk coefficient (denoted as R_res) is a coefficient between 0 and 1, representing unknown safety risks that still exist in the system and cannot be completely eliminated even if the vehicle passes all known safety designs and tests.

[0043] Understandably, traditional auto insurance models lack the ability to dynamically identify the liability boundaries of autonomous driving systems and fail to quantify the inherent residual risks of the systems, leading to a disconnect between premium pricing and actual risk. Therefore, by executing step S30, the host liability coefficient α and residual risk coefficient R_res are synchronously output based on SOTIF data through the liability calculation engine, avoiding the problems of ambiguous liability attribution and risk underestimation. This achieves a refined, traceable, and technology-driven insurance liability allocation and risk pricing mechanism for L4 autonomous driving.

[0044] In one feasible embodiment, step S30 may include steps S31 to S33: Step S31: Based on the SOTIF data, determine whether the autonomous vehicle was within the preset operating domain (ODD) at the time of the accident. Since the safety of autonomous driving systems is only guaranteed within their declared design operating domain, and the apportionment of liability for accidents is highly dependent on whether the vehicle was within that legal operating boundary at the time of the incident, the lack of accurate identification of the ODD boundary will lead to the OEM being wrongly assigned or exempted from liability, thereby affecting the fairness and reasonableness of insurance pricing.

[0045] To address this, this embodiment introduces a compliance factor (ODD_Compliance) to objectively determine whether the autonomous vehicle was completely within the preset ODD range at the time of the accident. The compliance factor is a Boolean result: when SOTIF data indicates that the vehicle's environmental conditions (such as weather and lighting), geographical location (such as the area covered by a high-precision map), road type, vehicle speed, and traffic conditions at the time of the accident strictly meet all the constraints defined by the ODD, the compliance factor is set to 1, indicating that the vehicle was within the ODD; conversely, if any dimension exceeds the ODD boundary (e.g., sudden weather changes, entering an unmapped area), the compliance factor is set to 0, indicating that the vehicle has exceeded the ODD range.

[0046] Step S32: Based on the judgment result, the OEM responsibility weight, and the user / third party responsibility weight, the OEM responsibility coefficient is determined through the pre-built responsibility actuarial engine. It should be noted that the OEM responsibility factor α is calculated using the following formula: α = ODD_Compliance * β + (1 - ODD_Compliance) * γ Wherein, β represents the liability limit that the OEM should bear when the vehicle is involved in an accident within the ODD, and γ represents the limited liability weight that the OEM still needs to bear when the vehicle is involved in an accident outside the ODD.

[0047] Understandably, since Level 4 autonomous driving systems should have fully autonomous operation capabilities within the ODD (Operational Domain), if an accident occurs within this range, it indicates that the system has failed to effectively handle the scenarios it promises to handle, and the OEM (Original Equipment Manufacturer) should bear primary responsibility (α∈[0.5, 0.9]). However, if an accident occurs outside the ODD, it may involve user misconduct or force majeure, and the OEM's responsibility is significantly reduced (α∈[0.1, 0.5]). Therefore, by executing step S32, the structured responsibility weight model is used to automatically calculate α, avoiding the subjectivity and lag of manual responsibility determination, thereby realizing an automated and auditable responsibility allocation mechanism based on the SOTIF evidence chain.

[0048] In another feasible embodiment, step S32 may further include steps S321 to S322: Step S321: If it is determined that the autonomous vehicle is within the ODD range, then obtain the autonomous vehicle's Out of Design Domain Ratio (ODR), Safety Takeover Request Frequency (SOR), Remote Takeover Response Timeliness (RTR), and Vehicle Failure Rate (VFR), and calculate the OEM responsibility coefficient based on the ODR, SOR, RTR, and VFR. In this embodiment, if it is determined that the autonomous vehicle is within the ODD range (i.e., ODD_Compliance = 1), the vehicle's Out of Design Domain Ratio (ODR), Safety Takeover Request Frequency (SOR), Remote Takeover Response Timeliness (RTR), and Vehicle Failure Rate (VFR) are obtained. Based on these four indicators, the OEM responsibility weight β is calculated, and the OEM responsibility coefficient α is set to β.

[0049] The Out-of-ODD Ratio (ODR) refers to the percentage of time or mileage that an autonomous vehicle operates outside the ODD range within the statistical period. Its value ranges from 0 to 1, and a higher value indicates that the system deviates from the safe operating boundary more frequently. The Remote Takeover Responsiveness (SOR) refers to the normalized value of the number of times the system actively initiates manual takeover requests within a unit of operating time, reflecting the stability of the system in edge scenarios, and its value ranges from 0 to 1. The Remote Takeover Responsiveness (RTR) refers to the proportion of remote operators who complete the intervention in a timely manner after receiving a takeover request. It is used to measure emergency response capability and has a value of 0-1. The Vehicle Failure Rate (VFR) is a normalized value representing the frequency of occurrence of hardware or software malfunctions, characterizing system reliability, and has a value of 0-1.

[0050] In this embodiment, ODR, SOR, RTR, and VFR together constitute the basis for calculating the OEM responsibility weight β, and preferably adopt an equal-weight linear combination method, that is: β=0.25*ODR+0.25*SOR+0.25*RTR+0.25*VFR Step S322: If it is determined that the autonomous vehicle is outside the range of the ODD, the OEM liability coefficient is determined as the user / third-party liability weight based on whether a valid takeover prompt was issued before the accident and the user operation record.

[0051] In this embodiment, if it is determined that the autonomous vehicle is outside the ODD range (i.e., ODD_Compliance = 0), the OEM liability coefficient α is set as the user / third party liability weight γ based on whether the system issued a valid takeover prompt before the accident and the user operation record, where the value of γ ranges from 0.1 to 0.5.

[0052] For example, if the system has issued a dual visual and audible takeover warning in advance and the user does not respond, then γ can be set to a lower value (e.g., 0.1); if the system does not issue a timely warning, then γ can be appropriately increased (e.g., 0.3~0.5) to reflect the OEM's negligence in risk warning.

[0053] Through the above steps S221~S222, this embodiment can dynamically and quantitatively determine the OEM's responsibility coefficient α based on whether the vehicle is within the Design Operating Domain (ODD) when the accident occurs, thereby achieving a more refined and objective division of responsibility.

[0054] Step S33: Based on the effectiveness coefficient, verification coverage coefficient, confirmation activity adequacy coefficient, and scenario exposure intensity of the design protection measures for the preset unsafe scenario in the SOTIF data, the residual risk coefficient is calculated.

[0055] In this embodiment, the residual risk coefficient R_res is calculated by the following formula:

[0056] Among them, the The design effectiveness coefficient, with a value ranging from 0 to 1, represents the degree of effectiveness of the functional safety and expected functional safety designs adopted for known unsafe scenarios. The To verify the coverage coefficient, the value range is 0-1, reflecting the proportion of scenarios in the standard SOTIF scenario library that have completed simulation or real vehicle testing; The To confirm the adequacy coefficient of the activity, it is used to measure the depth and breadth of field validation of edge scenarios in real operating environments; The The scene exposure intensity is calculated using the following formula:

[0057] Among them, the The system failure probability in scenario i (based on SOTIF test results); The coefficients represent multi-scenario correlations (considering scenario chain reactions); the... Calculated using the following formula:

[0058] Among them, the Let i be the number of times scenario i occurs within the statistical period; the Total operating time (hours); This is a geographical region coefficient, including urban centers (value 1.5), suburbs (value 1.0), and highways (value 0.8); This is a time coefficient, including peak (value 1.8), normal (value 1.0), and nighttime (value 0.7); This is a weather coefficient, including normal (value 1.0) and severe (value 2.0).

[0059] Through the above steps, this embodiment organically integrates the system's inherent protection capabilities with external operational risk exposure, achieving a quantitative assessment of "unknown risks that remain even after all known safety procedures have been completed." This residual risk coefficient, as a key input for premium actuarial calculations, effectively reflects the dynamic risk level of the autonomous driving system in real-world complex environments, avoiding the risk underestimation caused by traditional models that ignore differences in scenario exposure and system verification gaps.

[0060] Step S40: Calculate the total loss metric caused by the autonomous vehicle based on the SOTIF data; It should be noted that the total loss metric (denoted as L_total) is the monetary sum of all possible losses caused by a single incident. Its measurement is a multi-dimensional evaluation process.

[0061] Understandably, traditional auto insurance loss assessment models focus solely on repair and personal injury costs resulting from physical collisions, neglecting the data leakage risks and brand value damage caused by public opinion inherent in autonomous driving. This leads to severely incomplete loss assessments. Furthermore, in Level 4 autonomous driving scenarios, the responsible party shifts from the driver to the system provider, necessitating a comprehensive loss accounting system tailored to the technology's characteristics. Therefore, step S40, through structured modeling and monetization of four types of losses within the SOTIF framework, avoids the problems of narrow loss assessment scope and unrecoverable intangible losses. This achieves a comprehensive, quantifiable, legally and market-compatible loss measurement mechanism for advanced autonomous driving, providing a realistic and complete risk base for subsequent premium actuarial calculations.

[0062] In one feasible embodiment, step S40 may include steps S41-S42: Step S41: In the accident scenario represented by the SOTIF data, a multi-dimensional monetary assessment of the losses caused by the accident is conducted to obtain property losses, personal injury losses, data and privacy losses, and brand reputation losses. In this embodiment, under the accident scenario represented by the SOTIF data, a multi-dimensional monetary assessment of the losses caused by the accident is performed, specifically including the following four components: Property damage (L_property): This includes repair costs for your own vehicles, repair costs for third-party vehicles, compensation for damage to road infrastructure (such as guardrails and traffic lights), and loss of cargo. This part of the loss is calculated based on the actual repair invoices and the assessment amount issued by a professional damage assessment agency. As the most traditional and easily measurable type of loss, the system can automatically access the real-time quotation databases of partner 4S stores, repair shops, and logistics insurance platforms, and combine this with the accident damage image recognition results to quickly generate an estimated repair cost.

[0063] Personal injury loss (L_personal): This includes medical expenses, rehabilitation expenses, lost wages, disability compensation, and death compensation. This part of the loss is precisely calculated based on preset personal injury compensation rules and the personal injury compensation standards of the place where the accident occurred. This embodiment has a built-in compensation calculation model. Users only need to input parameters such as injury level, age, and income level to get an estimated compensation amount that conforms to preset rules.

[0064] Data and Privacy Loss (L_data): This represents the compensation cost incurred due to the leakage of vehicle data (such as passenger images and location trajectories from in-vehicle cameras) caused by an accident. Pricing is typically based on the sensitivity and amount of data leaked, and the calculation formula is: L_data = Number of leaked data records * Compensation price per record. The compensation price per record can be pre-set according to pre-defined penalty guidelines and industry standards (for example, the compensation price for sensitive biometric information is much higher than that for ordinary location information).

[0065] Brand reputation loss (L_brand): refers to the intangible asset depreciation caused to a company's brand value by negative public opinion triggered by an accident. This embodiment adopts a quantitative method that integrates natural language processing (NLP) and financial econometric models: First, it collects the number of reports, the breadth of dissemination, and the sentiment (positive / neutral / negative) regarding the accident from mainstream news media, Weibo, Douyin, Zhihu, and other platforms; second, it calculates a comprehensive negative index using a trained public opinion sentiment analysis model; finally, it establishes a "public opinion intensity – market value impact" regression model by combining the historical market value fluctuation data of the listed company to which the OEM belongs, estimates the potential brand value loss caused by this accident, and converts it into a monetized loss that can be included in the insurance compensation scope.

[0066] Through the aforementioned thinking and evaluation mechanism, this embodiment, for the first time, integrates tangible and intangible losses, physical damage and digital risks, individual compensation and corporate reputation in autonomous driving accidents into a calculable, traceable and payable actuarial framework, significantly improving the completeness and foresight of loss measurement.

[0067] Step S42: Sum the property loss, personal injury loss, data and privacy loss, and brand reputation loss to obtain the total loss measure.

[0068] After obtaining the property loss (L_property), personal injury loss (L_personal), data and privacy loss (L_data), and brand reputation loss (L_brand) through the above step S41, the total loss metric L_total is calculated using the following formula: L_total=L_property + L_personal + L_data + L_brand Through the above steps, by expanding the loss dimensions to four levels—property, personal injury, data privacy, and brand reputation—and introducing a maintenance database, a statutory compensation model, a data sensitivity pricing mechanism, and a public opinion-market value correlation model, a comprehensive loss measurement system matching the characteristics of advanced autonomous driving technology has been constructed for the first time. This not only avoids the problem of intangible losses not being included in the scope of insurance liability, but also ensures that the total loss measurement can truly reflect the comprehensive social and economic impact of the accident. It provides a complete, objective, and legally and market-credible risk base for subsequent premium actuarial calculations based on SOTIF, significantly improving the coverage, pricing accuracy, and compensation rationality of autonomous driving commercial insurance.

[0069] Step S50: Based on the base rate, the OEM liability coefficient, the total loss metric, and the residual risk coefficient, calculate the commercial insurance cost for the autonomous vehicle.

[0070] Based on the basic premium rate K, OEM liability coefficient α, total loss metric L_total, and residual risk coefficient R_res obtained in steps S10 to S40 above, the commercial insurance cost P for autonomous vehicles is calculated using the following formula: P = K*α*L_total*R_res Wherein, K is the base rate; α is the OEM liability coefficient; L_total is the total loss measure caused by the vehicle; and R_res is the residual risk coefficient of an L4 vehicle when dealing with a certain type of unsafe scenario.

[0071] The above-described method involves matching the base premium rate corresponding to the autonomous vehicle from the insurance contract database; obtaining SOTIF data for the autonomous vehicle; determining the OEM liability coefficient and residual risk coefficient based on the SOTIF data using a liability actuarial engine; calculating the total loss metric based on the SOTIF data; and calculating the commercial insurance premium for the autonomous vehicle based on the base premium rate, OEM liability coefficient, total loss metric, and residual risk coefficient. This method, by integrating the base premium rate, OEM liability coefficient, total loss metric, and residual risk coefficient, constructs a SOTIF-based actuarial model for autonomous driving commercial insurance premiums. This model not only clearly defines accident liability and effectively quantifies the loss assessment standards for multi-dimensional losses, but also significantly improves the accuracy of matching premium pricing with actual risk.

[0072] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 After step S11, the vehicle commercial insurance premium pricing method further includes steps A11 to A13: Step A11: Obtain the actual loss rate, accident rate per thousand kilometers, and SOTIF scenario pass rate of the fleet to which the autonomous vehicle belongs during its operation. It should be noted that the actual loss ratio (LR) refers to the ratio of total claims payouts to total premium income of a fleet within a statistical period (usually an insurance year), i.e.: LR = Total claims payouts / Total premium income. This indicator directly reflects the risk coverage capability of the current base premium rate.

[0073] In addition, the accident rate per thousand kilometers refers to the number of OEM-related accidents that occur per thousand kilometers of driving during the fleet's operation, which is used to measure the vehicle's safety performance in real road environments; the SOTIF scenario pass rate refers to the proportion of successful responses of the autonomous driving system in the standard SOTIF test scenario library, which characterizes the system's ability to handle known edge scenarios.

[0074] Step A12: Based on the deviation between the actual loss ratio and the target loss ratio, the trend of the accident rate per thousand kilometers, and the pass rate of the SOTIF scenario, determine the loss ratio change coefficient; In this embodiment, a target loss ratio (e.g., 85%) is set as a benchmark threshold for premium adequacy. If the actual loss ratio (LR) > 85%, it indicates that the current premium level is insufficient to cover claims costs, and the base premium rate needs to be increased; conversely, if LR < 85%, it indicates that risk control is good, and there is room to reduce or maintain the premium rate.

[0075] Furthermore, the loss ratio change coefficient (denoted as Δ) is dynamically determined based on the following three aspects: When the accident rate per thousand kilometers increases compared to the previous period, Δ increases, reflecting a deterioration in operational risk; when the SOTIF scenario pass rate decreases (i.e., the system performs worse in standard testing), Δ increases, indicating a degradation in expected functional safety capabilities; conversely, if the accident rate per thousand kilometers decreases and the SOTIF pass rate increases, Δ decreases or even becomes negative, reflecting an improvement in risk.

[0076] Step A13: Adjust the initial base rate according to the loss ratio change coefficient to obtain the updated base rate.

[0077] Specifically, the updated base rate K_new is calculated using the following formula: K_new = K_previous * (1 + loss ratio change coefficient) K_previous is the base rate used in the previous week (K_initial is used during the first adjustment).

[0078] Through the methods described above, this embodiment achieves closed-loop dynamic optimization of the basic premium rate: it not only responds to historical claims results, but also integrates real operational safety indicators (accident rate per thousand kilometers) and system capability verification results (SOTIF pass rate), so that the premium level can continuously match the actual risk evolution trend of the autonomous driving fleet, avoid the defects of "static pricing and lagging adjustment" in traditional auto insurance, and significantly improve the sustainability and market adaptability of insurance products.

[0079] For example, to help understand the implementation process of the vehicle commercial insurance premium pricing method obtained in this embodiment combined with the above embodiment one, please refer to... Figure 3 , Figure 3 A simplified flowchart illustrating a vehicle commercial insurance premium pricing method is provided, specifically: like Figure 3 As shown, this embodiment first obtains the SOTIF data source from the autonomous vehicle, including: Scene exposure rate λ: used to assess the frequency of occurrence of a specific unsafe scene; Residual risk input (R_res): reflects unknown risks that still exist outside the validation coverage of the system; ODD compliance record: Determines whether the vehicle was within its designed operating range at the time of the accident.

[0080] The above data is input into the responsible actuarial engine, which processes it through the following three core modules: Three-tier responsibility model: Based on ODD compliance status, distinguish the responsibility boundaries between OEM domain users and third parties; Four-dimensional loss quantification: Monetize the loss of property, personal injury, data privacy and brand reputation, and generate the total loss metric L_total; Dynamic premium calculation: Combining the basic premium rate K, the OEM liability coefficient α, the total loss metric L_total, and the residual risk coefficient R_res, the final premium formula is output: P = K*α*L_total*R_res The base premium rate K is obtained by matching from the insurance contract database and can be dynamically adjusted annually based on fleet operating performance. The entire process is driven by SOTIF data, achieving a closed-loop technology that enables traceable liability, quantifiable losses, and actuarial premiums, and is applicable to commercial insurance pricing for advanced autonomous vehicles such as Level 4 Robotaxi.

[0081] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the vehicle commercial insurance premium pricing method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0082] This application also provides a vehicle commercial insurance premium pricing system; please refer to [reference needed]. Figure 4 The vehicle commercial insurance premium pricing system includes: The first parameter determination module 10 matches the basic premium rate corresponding to the autonomous vehicle from the insurance contract database; The data acquisition module 20 is used to acquire the expected functional safety SOTIF data of the autonomous vehicle. The second parameter determination module 30 is used to determine the OEM liability coefficient and residual risk coefficient based on the SOTIF data and through a pre-built liability actuarial engine. The third parameter determination module 40 is used to calculate the total loss metric caused by the autonomous vehicle based on the SOTIF data. The premium calculation module 50 is used to calculate the commercial insurance for the autonomous vehicle based on the base rate, the OEM liability coefficient, the total loss metric, and the residual risk coefficient.

[0083] The vehicle commercial insurance premium pricing system provided in this application, employing the vehicle commercial insurance premium pricing method described in the above embodiments, can solve the technical problem that the existing insurance system cannot achieve accurate premium pricing for L4 autonomous vehicles. Compared with the prior art, the beneficial effects of the vehicle commercial insurance premium pricing system provided in this application are the same as those of the vehicle commercial insurance premium pricing method provided in the above embodiments, and other technical features of the vehicle commercial insurance premium pricing system are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0084] This application provides a vehicle commercial insurance premium pricing device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to execute the vehicle commercial insurance premium pricing method in the above embodiment 1.

[0085] The following is for reference. Figure 5 The diagram illustrates a structural schematic suitable for implementing vehicle commercial insurance premium pricing devices according to embodiments of this application. The vehicle commercial insurance premium pricing devices in embodiments of this application may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5 The vehicle commercial insurance premium pricing device shown is merely an example and should not impose any limitations on the functionality and scope of application of the embodiments of this application.

[0086] like Figure 5 As shown, the vehicle commercial insurance premium pricing device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the vehicle commercial insurance premium pricing device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An input / output interface 1006 is also connected to the bus. Typically, the following systems can be connected to the input / output interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the vehicle commercial insurance premium pricing device to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows vehicle commercial insurance premium pricing devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0087] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0088] The vehicle commercial insurance premium pricing device provided in this application, employing the vehicle commercial insurance premium pricing method described in the above embodiments, can solve the technical problem that the existing insurance system cannot achieve accurate premium pricing for L4 autonomous vehicles. Compared with the prior art, the beneficial effects of the vehicle commercial insurance premium pricing device provided in this application are the same as those of the vehicle commercial insurance premium pricing method provided in the above embodiments, and other technical features in this vehicle commercial insurance premium pricing device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0089] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0090] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0091] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the vehicle commercial insurance premium pricing method in the above embodiments.

[0092] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0093] The aforementioned computer-readable storage medium may be included in the vehicle commercial insurance premium pricing device; or it may exist independently and not be installed in the vehicle commercial insurance premium pricing device.

[0094] The aforementioned computer-readable storage medium carries one or more programs that, when executed by a vehicle commercial insurance premium pricing device, cause the vehicle commercial insurance premium pricing device to: match the base rate corresponding to the autonomous vehicle from the insurance contract database; obtain the SOTIF data of the autonomous vehicle; determine the OEM liability coefficient and residual risk coefficient based on the SOTIF data through a liability actuarial engine; calculate the total loss measure based on the SOTIF data; and calculate the commercial insurance for the autonomous vehicle based on the base rate, OEM liability coefficient, total loss measure, and residual risk coefficient.

[0095] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0096] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0097] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0098] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described vehicle commercial insurance premium pricing method. This solves the technical problem that the existing insurance system cannot achieve accurate premium pricing for L4 autonomous vehicles. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the vehicle commercial insurance premium pricing method provided in the above embodiments, and will not be elaborated upon here.

[0099] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the vehicle commercial insurance premium pricing method described above.

[0100] The computer program product provided in this application can solve the technical problem that the existing insurance system cannot achieve accurate premium pricing for L4 autonomous vehicles. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the vehicle commercial insurance premium pricing method provided in the above embodiments, and will not be repeated here.

[0101] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A method for pricing commercial vehicle insurance premiums, characterized in that, The vehicle commercial insurance premium pricing method includes: Match the base premium rate corresponding to autonomous vehicles from the insurance contract database; Obtain the expected functional safety SOTIF data of the autonomous vehicle; Based on the SOTIF data, the OEM liability coefficient and residual risk coefficient are determined by a pre-built liability actuarial engine. Calculate the total loss metric caused by the autonomous vehicle based on the SOTIF data; The commercial insurance cost of the autonomous vehicle is calculated based on the base rate, the OEM liability coefficient, the total loss metric, and the residual risk coefficient.

2. The vehicle commercial insurance premium pricing method as described in claim 1, characterized in that, The step of matching the base premium rate corresponding to the autonomous vehicle from the insurance contract database includes: The initial base rate is determined in the insurance contract database based on the vehicle value of the autonomous vehicle, the risk coefficient corresponding to the operating area, the historical benchmark rate, and the expected insured amount. The vehicle value is determined based on the cost of sensors and autonomous driving hardware in the vehicle configuration, and the regional risk coefficient is determined based on the traffic complexity of the operating area.

3. The vehicle commercial insurance premium pricing method as described in claim 2, characterized in that, After the step of determining the initial base rate in the insurance contract database based on the vehicle value of the autonomous vehicle, the risk coefficient corresponding to the operating area, the historical benchmark rate, and the expected insured amount, the method further includes: The actual loss rate, accident rate per thousand kilometers, and SOTIF scenario pass rate of the fleet to which the autonomous vehicles belong during operation are obtained. The loss ratio variation coefficient is determined based on the deviation between the actual loss ratio and the target loss ratio, the trend of the accident rate per thousand kilometers, and the pass rate of the SOTIF scenario. The initial base rate is adjusted based on the loss ratio change coefficient to obtain the updated base rate.

4. The vehicle commercial insurance premium pricing method as described in claim 1, characterized in that, The steps of determining the OEM liability coefficient and residual risk coefficient based on the SOTIF data using a pre-built actuarial engine include: Based on the SOTIF data, determine whether the autonomous vehicle was within the preset operating domain (ODD) at the time of the accident; Based on the judgment results, the OEM responsibility weight, and the user / third-party responsibility weight, the OEM responsibility coefficient is determined through the pre-built responsibility actuarial engine. Based on the effectiveness coefficient, verification coverage coefficient, confirmation activity adequacy coefficient, and scenario exposure intensity of the design protective measures for the preset unsafe scenarios in the SOTIF data, the residual risk coefficient is calculated.

5. The vehicle commercial insurance premium pricing method as described in claim 4, characterized in that, The step of determining the OEM responsibility coefficient using the pre-built responsibility actuarial engine based on the judgment result, the OEM responsibility weight, and the user / third-party responsibility weight includes: If it is determined that the autonomous vehicle is within the ODD range, then the autonomous vehicle's Out of Design Domain Ratio (ODR), Safety Takeover Request Frequency (SOR), Remote Takeover Response Timeliness (RTR), and Vehicle Failure Rate (VFR) are obtained, and the OEM responsibility coefficient is calculated based on the ODR, SOR, RTR, and VFR. If it is determined that the autonomous vehicle is outside the scope of the ODD, the OEM liability coefficient will be determined as the user's or third party's liability weight based on whether a valid takeover prompt was issued before the accident and the user's operation records.

6. The vehicle commercial insurance premium pricing method as described in claim 1, characterized in that, The step of calculating the total loss metric caused by the autonomous vehicle based on the SOTIF data includes: In the accident scenario represented by the SOTIF data, the losses caused by the accident are assessed in a multi-dimensional monetary manner to obtain property damage, personal injury damage, data and privacy damage, and brand reputation damage. Among them, the property damage is determined based on vehicle repair costs and third-party damages; the personal injury damage is calculated according to preset personal injury compensation rules and injury parameters; the data and privacy damage is determined based on the sensitive type and quantity of the leaked data combined with a preset compensation unit price; and the brand reputation damage is estimated by analyzing the impact of the accident and combining it with a preset corporate market value fluctuation model. The total loss measure is obtained by summing the property loss, personal injury loss, data and privacy loss, and brand reputation loss.

7. A vehicle commercial insurance premium pricing system, characterized in that, The vehicle commercial insurance premium pricing system includes: The first parameter determination module matches the basic premium rate corresponding to autonomous vehicles from the insurance contract database; The data acquisition module is used to acquire the expected functional safety SOTIF data of the autonomous vehicle. The second parameter determination module is used to determine the OEM liability coefficient and residual risk coefficient based on the SOTIF data and through a pre-built liability actuarial engine. The third parameter determination module is used to calculate the total loss metric caused by the autonomous vehicle based on the SOTIF data. The premium calculation module is used to calculate the commercial insurance cost of the autonomous vehicle based on the base rate, the OEM liability coefficient, the total loss metric, and the residual risk coefficient.

8. A vehicle commercial insurance premium pricing device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the vehicle commercial insurance premium pricing method as described in any one of claims 1 to 6.

9. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the vehicle commercial insurance premium pricing method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the vehicle commercial insurance premium pricing method as described in any one of claims 1 to 6.

Images