Vehicle insurance service method and system based on real-time driving data

Abstract

The invention relates to the crossing field of insurance science and technology and Internet of Vehicles technology, and particularly provides a vehicle insurance service method and system based on real-time driving data, and the method comprises the steps: collecting the real-time driving data of a vehicle, and carrying out the preprocessing of the real-time driving data; constructing a driving behavior risk scoring model, and obtaining a driving behavior score by taking the preprocessed real-time driving data as the input of the driving behavior risk scoring model; and automatically adjusting the next automobile insurance premium according to the driving behavior score. By introducing a driving behavior risk scoring model and dynamic vehicle insurance rate linkage mechanism and a mathematical closed loop between the first real-time driving behavior score and the vehicle insurance rate, the insurance service is changed from a static rule to self-learning and automatic adjustment, the driving behavior-vehicle insurance premium pricing in a real sense can be realized, and the driving safety is improved. The safety awareness of a driver can be improved; and the accident rate is reduced.

Description

Technical Field

[0001] This invention relates to the intersection of insurance technology and vehicle networking technology, and more specifically, to a vehicle insurance service method and system based on real-time driving data. Background Technology

[0002] Current vehicle insurance business mainly relies on static data such as vehicle age, model, years of use, and historical claims records for premium pricing, lacking dynamic assessment of driving behavior and real-time operational risks.

[0003] This type of car insurance premium pricing method cannot effectively incentivize safe driving behavior and makes it difficult to identify high-risk drivers, which can easily lead to frequent problems such as driving in the wrong direction and moral hazard.

[0004] Therefore, it is necessary to develop a vehicle insurance service method and system based on real-time driving data to effectively incentivize drivers to drive safely. Summary of the Invention

[0005] Therefore, in order to address the problem that existing auto insurance premium pricing methods cannot effectively incentivize safe driving behavior, this invention provides a vehicle insurance service method and system based on real-time driving data, the specific technical solution of which is as follows:

[0006] A method for providing vehicle insurance services based on real-time driving data includes the following steps:

[0007] Collect real-time driving data of the vehicle and preprocess the real-time driving data;

[0008] A driving behavior risk scoring model is constructed, and the preprocessed real-time driving data is used as the input to the driving behavior risk scoring model to obtain a driving behavior score;

[0009] The next car insurance premium will be automatically adjusted based on the driving behavior score.

[0010] The vehicle insurance service method based on real-time driving data introduces a driving behavior risk scoring model and a dynamic vehicle insurance rate linkage mechanism. For the first time, a mathematical closed loop is established between real-time driving behavior scores and vehicle insurance rates, enabling insurance services to move from static rules to self-learning and automatic adjustment. This can achieve true "driving behavior-vehicle insurance premium pricing," which can improve drivers' safety awareness and reduce accident rates.

[0011] Preferably, the specific methods for obtaining driving behavior scores include:

[0012] Obtain the scoring weight values ​​corresponding to the different types of real-time driving data;

[0013] Calculate the weighted value or weighted average of the different types of real-time driving data, and use the weighted value or weighted average as the driving behavior score.

[0014] Preferably, the specific method for automatically adjusting the next period's auto insurance premium based on the driving behavior score includes:

[0015] Establish a dynamic premium adjustment mechanism;

[0016] The driving risk level is obtained based on the driving behavior score.

[0017] Based on the aforementioned driving risk level and dynamic premium adjustment mechanism, the next period's auto insurance premium will be automatically adjusted.

[0018] Preferably, the specific method for automatically adjusting the next period's auto insurance premium based on the driving behavior score includes:

[0019] Obtain the deviation value of the driving behavior score relative to the preset benchmark driving score;

[0020] Obtain the current premium and automatically adjust the next period's auto insurance premium based on the current premium and the deviation value.

[0021] Preferably, the vehicle insurance service method further includes the following steps:

[0022] When an accident occurs, key data is selected from the real-time driving data;

[0023] The key data will be uploaded to the cloud-based insurance service platform as the basis for claims processing, and the claims process will be automatically triggered.

[0024] A vehicle insurance service system based on real-time driving data, used to implement the aforementioned vehicle insurance service method based on real-time driving data, includes:

[0025] The data acquisition module is used to collect real-time driving data of the vehicle.

[0026] The cloud-based insurance service platform includes a driving behavior risk scoring model and a dynamic premium adjustment module, used to preprocess the real-time driving data;

[0027] The driving behavior risk scoring model is used to obtain a driving behavior score based on preprocessed real-time driving data, and the dynamic premium adjustment module is used to automatically adjust the next period's auto insurance premium based on the driving behavior score.

[0028] Preferably, the driving behavior risk scoring model includes:

[0029] The scoring weight acquisition unit is used to acquire the scoring weight values ​​corresponding to different types of real-time driving data;

[0030] The driving behavior scoring unit is used to calculate the weighted value or weighted average of the real-time driving data of different types, and to use the weighted value or weighted average as the driving behavior score.

[0031] Preferably, the dynamic premium adjustment module includes:

[0032] A risk level acquisition unit is used to acquire a driving risk level based on the driving behavior score.

[0033] The automatic premium adjustment unit is used to automatically adjust the next period's auto insurance premium based on the driving risk level and the dynamic premium adjustment mechanism.

[0034] Preferably, the dynamic premium adjustment module includes:

[0035] The scoring deviation acquisition unit is used to acquire the deviation value of the driving behavior score relative to the preset benchmark driving score;

[0036] The automatic premium adjustment unit is used to obtain the current premium and automatically adjust the next period's auto insurance premium based on the current premium and the deviation value.

[0037] Preferably, the cloud-based insurance service platform further includes:

[0038] The intelligent claims module is used to automatically trigger the claims process in the event of an accident, using key data uploaded to the cloud-based insurance service platform as the basis for claims. Attached Figure Description

[0039] The invention will be further understood from the following description taken in conjunction with the accompanying drawings. The components in the drawings are not necessarily drawn to scale, but rather the emphasis is on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0040] Figure 1 This is a schematic diagram of the overall process of a vehicle insurance service method based on real-time driving data in one embodiment of the present invention;

[0041] Figure 2 This is a flowchart illustrating a specific method for obtaining a driving behavior score in one embodiment of the present invention;

[0042] Figure 3 This is a flowchart illustrating a specific method for automatically adjusting the next period's auto insurance premium in one embodiment of the present invention;

[0043] Figure 4 This is a flowchart illustrating a specific method for automatically adjusting the next period's auto insurance premium in another embodiment of the present invention;

[0044] Figure 5This is a schematic diagram of the overall structure of a vehicle insurance service system based on real-time driving data according to another embodiment of the present invention;

[0045] Figure 6 This is a schematic diagram of the risk assessment and premium adjustment process in one embodiment of the present invention;

[0046] Figure 7 This is a schematic diagram of the claims processing flow in one embodiment of the present invention;

[0047] Figure 8 This is a schematic diagram of the user visual interface structure in one embodiment of the present invention. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to its embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the scope of protection of the invention.

[0049] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly attached to the other element or there may be an intervening element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or there may be an intervening element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible implementation.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0051] In this invention, "first" and "second" do not represent a specific quantity or order, but are merely used to distinguish names.

[0052] Current vehicle insurance pricing primarily relies on static data such as vehicle age, model, years of use, and historical claims records, lacking dynamic assessments of driving behavior and real-time operational risks. This pricing method fails to effectively incentivize safe driving behavior and struggles to identify high-risk drivers, easily leading to frequent issues like wrong-way driving and moral hazard. Furthermore, in the event of an accident, existing vehicle insurance claims processes largely depend on manual evidence collection and review, resulting in low efficiency, numerous disputes, and failing to meet the demands for efficient and transparent insurance services.

[0053] To address the problem that existing technologies cannot effectively incentivize safe driving behavior, such as Figure 1 As shown, an embodiment of the present invention provides a vehicle insurance service method based on real-time driving data, which includes the following steps:

[0054] S1. Collect real-time driving data of the vehicle and preprocess the real-time driving data. Specifically, the real-time driving data includes, but is not limited to, vehicle speed, acceleration, number of emergency braking events, fatigue driving behavior, driving area, and GPS trajectory. The preprocessing includes, but is not limited to, cleaning, classifying, and analyzing the data.

[0055] S2, Construct a driving behavior risk scoring model, using the preprocessed real-time driving data as input to the driving behavior risk scoring model to obtain a driving behavior score.

[0056] To improve the insurance system's responsiveness to driving behavior, a driving behavior risk scoring model can be constructed based on machine learning algorithms. The preprocessed real-time driving data can then be processed according to the driving behavior risk scoring model to obtain a driving behavior score.

[0057] As a preferred technical solution, in step S2, such as Figure 2 As shown, the specific methods for obtaining driving behavior scores include:

[0058] S21, obtain the scoring weight values ​​corresponding to the different types of real-time driving data.

[0059] S22, calculate the weighted value or weighted average of the different types of real-time driving data, and use the weighted value or weighted average as the driving behavior score. For example, R = ∑(w i ·X i ), where X i w represents the real-time driving data of the i-th type. i This represents the weighting coefficient of the i-th type of real-time driving data.

[0060] Specifically, driving behavior scores are obtained using the formula R = w1·B + w2·A + w3·F + w4·T + w5·G. Here, R represents the driving behavior score, B represents the frequency of sudden braking, A represents the rate of change of average acceleration, F represents the percentage of time spent driving while fatigued, T represents the percentage of time spent driving at night, G represents the percentage of time spent driving in dangerous areas, and w1, w2, w3, w4, and w5 represent weighting coefficients, which can be obtained through machine learning training.

[0061] To ensure that driving behavior scores more closely reflect real-world risk scenarios, the weighting coefficients w1, w2, w3, w4, and w5 can be dynamically adjusted in real time based on time of day (e.g., morning and evening rush hours, late at night) and area (e.g., school zones, highways). These coefficients are updated through training with real-time traffic risk data, with the weighting automatically increasing for peak / dangerous areas. In other words, sudden braking during peak hours and dangerous driving in school zones receive higher weightings, precisely penalizing high-risk behaviors.

[0062] S3, automatically adjust the next period's car insurance premium based on the driving behavior score.

[0063] As a preferred technical solution, such as Figure 3 As shown, the specific methods for automatically adjusting the next period's car insurance premium based on the driving behavior score include:

[0064] S31, Obtain the deviation value of the driving behavior score relative to the preset benchmark driving score.

[0065] S32, obtain the current premium and automatically adjust the next period's auto insurance premium based on the current premium and the deviation value.

[0066] Through formula Automatically adjust the next period's car insurance premium. Among them, P n+1 Indicates the next car insurance premium, P n R represents the current car insurance premium. base This represents the preset neutral baseline score (e.g., 60 points), ΔR = (RR) base ) / 100 represents the deviation of the driving behavior score R from the benchmark score, and α represents the adjustment coefficient (e.g., 0.2, which means that the deviation value fluctuates by 2% for every 10 points).

[0067] For example, if a driver's driving score for the current period is 75 points (15 points higher than the benchmark), then the car insurance premium for the next period will be... That is, the premium will decrease by 3%; if the score is 45 points, then... This means the premium will increase by 3%.

[0068] In the aforementioned vehicle insurance service method, a driver credit scoring mechanism can be constructed to facilitate insurance review and renewal recommendations, and data sources such as weather, road conditions, and load can be integrated into the driving behavior risk scoring model to enhance the assessment accuracy.

[0069] It can also be combined with the scene penalty coefficient β risk Optimize next period's auto insurance premiums to make premium adjustments more targeted for extreme risk behaviors, such as rainy or snowy weather, holidays, and other special periods. Triggers will be subject to additional scenario-based penalty coefficients, strengthening premium responses in high-risk environments. For "safety incentive scenarios" (such as accident-free commuting late at night), a β setting can be implemented. risk <1 (e.g., β) risk=0.95), rewarding compliant driving. The optimized formula is expressed as:

[0070] For example, if the proportion of driving time in rainy or snowy weather for the target user during the premium period is greater than the corresponding preset threshold, then β risk =1.2; If the target user's driving time during holidays accounts for a greater than the corresponding preset threshold during the premium period, then β risk =1.1. Thus, by distinguishing between dangerous behaviors under extreme conditions such as "normal driving" and "driving in harsh environments / high-risk scenarios," the premium adjustment is more stringent, which can incentivize users to proactively avoid risky scenarios.

[0071] The vehicle insurance service method based on real-time driving data introduces a driving behavior risk scoring model and a dynamic vehicle insurance rate linkage mechanism. For the first time, a mathematical closed loop is established between real-time driving behavior scores and vehicle insurance rates, enabling insurance services to move from static rules to self-learning and automatic adjustment. This can achieve true "driving behavior-vehicle insurance premium pricing," which can improve drivers' safety awareness and reduce accident rates.

[0072] As a preferred technical solution, such as Figure 4 As shown, the specific methods for automatically adjusting the next period's car insurance premium based on the driving behavior score include:

[0073] S33, establish a dynamic premium adjustment mechanism.

[0074] S34, Obtain the driving risk level based on the driving behavior score. Specifically, map the driving behavior score to three driving risk levels: low risk, medium risk, or high risk.

[0075] S35, based on the aforementioned driving risk level and dynamic premium adjustment mechanism, automatically adjust the next period's auto insurance premium. The system automatically adjusts the next period's auto insurance premium according to the driving risk level, forming a closed-loop mechanism of "high risk → high premium, low risk → low premium".

[0076] As a preferred technical solution, the vehicle insurance service method further includes the following steps:

[0077] S4. When an accident occurs, key data is selected from the real-time driving data. The key data can be selected based on experience, such as vehicle speed, acceleration, driving area, and GPS trajectory from the real-time driving data.

[0078] S5. Upload the key data to the cloud insurance service platform as the basis for claims and automatically trigger the claims process.

[0079] All key data is visualized and securely stored through a cloud-based insurance service platform, displaying driving scores, premium changes, and claims progress to drivers and insurance companies.

[0080] As a preferred technical solution, to encourage users to maintain good habits and reflect the long-term value of "continuous safe driving" and the cumulative rewards for long-term behavior, the auto insurance service method further includes: first, pre-setting a continuous safe driving cycle (e.g., monthly, quarterly) and constructing a safety cycle decay coefficient γ based on the continuous safe driving cycle. Specifically, for each additional safe driving cycle, the safety cycle decay coefficient decreases proportionally (e.g., by 5% per quarter), and the premium discount accumulates if safety is maintained. If the safe driving cycle is interrupted (e.g., due to dangerous driving), the safety cycle decay coefficient is reset to 1 and accumulates again.

[0081] In this embodiment, In this way, the next round of car insurance premiums will not only differentiate between dangerous behaviors under extreme conditions such as "normal driving" and "driving in harsh environments / high-risk scenarios," with stricter premium adjustments, but will also shift from "single-time scoring" to "long-term behavior management," resulting in more significant premium discounts for users who consistently drive safely, further strengthening positive incentives.

[0082] As a preferred technical solution, the vehicle insurance service method further includes the following steps: first, acquiring vehicle network data; then, based on the vehicle network data, identifying the number of times (D1) a target user causes a following vehicle to brake suddenly / change lanes due to their own driving behavior (such as sudden braking or cutting in line) within the premium period (unit: year); next, based on the vehicle network data, obtaining the total number of times (D2) multiple users cause a following vehicle to brake suddenly / change lanes due to their own driving behavior (such as sudden braking or cutting in line) within the premium period; and finally, calculating the risk spillover value based on the number of times (D1) and the total number of times (D2). For example, the risk spillover value D = number of times (D1) / total number of times (D2).

[0083] The real-time driving data includes risk spillover values. Ultimately, the driving behavior score R = w1·B + w2·A + w3·F + w4·T + w5·G + w6·D. Here, w6 represents the spillover risk weighting coefficient, which can be set based on experience. In this way, the newly added risk spillover values ​​incorporate user behaviors that affect the safety of others into the driving behavior score, upgrading the vehicle insurance service method from "personal risk" to "traffic ecosystem risk." This can punish individual behaviors that "create chain reactions of danger," reducing the overall accident risk rate of the traffic ecosystem.

[0084] As a preferred technical solution, the real-time driving data also includes vehicle health data and environmental risk data. Vehicle health data is acquired through vehicle-to-everything (V2X) data. This involves obtaining the target user's real-time vehicle fault risk value (such as brake system wear, abnormal tire pressure, etc.) and the average real-time vehicle fault risk value of multiple users, or a preset basic vehicle fault risk value, to calculate the cumulative vehicle risk value within the premium period. For example, to simplify the calculation, the real-time vehicle fault risk value can be compared with the average real-time vehicle fault risk value to calculate the cumulative time during which the real-time vehicle fault risk value exceeds the average real-time vehicle fault risk value, and the cumulative vehicle risk value within the premium period can be calculated based on this cumulative time. Alternatively, the real-time vehicle fault risk value can be compared with a preset basic vehicle fault risk value to calculate the cumulative time during which the real-time vehicle fault risk value exceeds the preset basic vehicle fault risk value, and the cumulative vehicle risk value within the premium period can be calculated based on this cumulative time.

[0085] Environmental risk data is obtained through a traffic big data platform. The environmental risk value is calculated by acquiring environmental risk indices (such as road icing coefficients and construction density) and preset baseline environmental risk index values. For example, to simplify the calculation, the environmental risk value within the premium period can be calculated by calculating the cumulative time during which the environmental risk index exceeds the baseline environmental risk index value.

[0086] The driving behavior score R = w1·B + w2·A + w3·F + w4·T + w5·G + w6·D + w7·H + w8·E. w7 and w8 represent the weighting coefficients for the vehicle risk accumulation value and the environmental risk value, respectively. By incorporating vehicle health data and environmental risk data into the driving behavior score, the score becomes more comprehensive, preventing users from being unfairly blamed for vehicle / road problems and penalizing neglect of vehicle maintenance. The vehicle insurance service method extends from "human behavior" to the collaborative risks of "human-vehicle-road" interactions, distinguishing between "human-caused accidents" and "vehicle / road accidents," ensuring fair premium pricing, and incentivizing users to maintain their vehicles and avoid dangerous road sections.

[0087] The aforementioned driving behavior scoring function model R = w1·B + w2·A + w3·F + w4·T + w5·G + w6·D + w7·H + w8·E only uses single behavioral factors for weighting, ignoring the risks of combined behaviors such as "sudden braking + night driving" and "rapid acceleration + fatigue." Therefore, a behavioral interaction term is introduced into the driving behavior scoring function model to capture scenarios where "single behaviors are safe, but the risk increases dramatically when combined" (e.g., the accident rate for sudden braking at night is much higher than for sudden braking during the day), making the risk scoring more closely reflect the logic of real accidents.

[0088] The optimized driving behavior scoring function model R = ∑(w i ·X i )+∑(w j ·X k·X l ). X k ·X l This represents behavioral interaction items, such as B×T for "emergency braking + nighttime" and A×F for "rapid acceleration + fatigue". j X represents the weight coefficient of the j-th behavioral interaction. k X l Let X1 represent the k-th and l-th driving behaviors, respectively. For example, X1 = B (frequency of emergency braking), X2 = A (average rate of change of acceleration), X3 = F (percentage of time spent driving while fatigued), X4 = T (percentage of time spent driving at night), and X5 = G (percentage of time spent driving in dangerous areas). For the behavior interaction item X... k ·X l The types of combinations can be set according to the actual situation, and will not be elaborated here.

[0089] like Figure 5 As shown, an embodiment of the present invention also provides a vehicle insurance service system based on real-time driving data, used to implement the vehicle insurance service method based on real-time driving data, which includes a data acquisition module and a cloud insurance service platform.

[0090] The data acquisition module is used to collect real-time driving data of the vehicle; the cloud-based insurance service platform includes a driving behavior risk scoring model and a dynamic premium adjustment module, which are used to preprocess the real-time driving data.

[0091] The driving behavior risk scoring model is used to obtain a driving behavior score based on preprocessed real-time driving data, and the dynamic premium adjustment module is used to automatically adjust the next period's auto insurance premium based on the driving behavior score.

[0092] The cloud-based insurance service platform also includes an intelligent claims module, which automatically triggers the claims process in the event of an accident, using key data uploaded to the platform as the basis for claims. The system also includes a user-friendly interface and an encrypted evidence storage module, which displays driving scores, premium changes, and claims progress to drivers and insurance companies. The encrypted evidence storage module uses blockchain technology to encrypt and store accident data.

[0093] Figure 7 This demonstrates the fully automated process from receiving a claim request to final claim processing. First, the user or system initiates a claim application (e.g., via an app or automatically triggered by an accident). Then, the system retrieves data from key periods before and after the accident (speed, braking, acceleration, images, etc.) and uses algorithms to identify abnormal behaviors such as collisions and sudden speed changes to verify the authenticity of the accident. If the data matches an abnormal event, the automated review process can be initiated directly, leading to either payout or manual review.

[0094] like Figure 5As shown, it illustrates the core structure and logical flow of the entire vehicle insurance service system. The vehicle terminal is installed on the vehicle, such as a heavy truck, and includes data acquisition modules (such as ECU, GPS, cameras, etc.) to collect vehicle driving data in real time and upload it to the cloud.

[0095] The cloud-based insurance service platform serves as the core processing unit. The driving behavior risk scoring model analyzes driving behavior based on machine learning (ML) models. The user's visual interface displays information such as driving scores, premium trends, and claims status through an app or web platform, providing insurance advice and feedback, thus forming a closed-loop service.

[0096] Figure 8 This section showcases the functionalities of the user interface for insurance customers on mobile and web platforms. The user interface provides a unified entry point, including modules for driving data, abnormal events, and insurance status. The driving data module displays behavioral data such as driving scores, number of emergency braking incidents, number of times driving while fatigued, and average speed, presented through visual line charts or radar graphs. The abnormal events module automatically records and displays abnormal driving or accident behaviors identified by the system, such as collision warnings and violations. The insurance status module displays the current policy status, remaining coverage period, and monthly premium trends, providing renewal and risk advice services.

[0097] As a preferred technical solution, the driving behavior risk scoring model includes a scoring weight acquisition unit and a driving behavior scoring unit.

[0098] The scoring weight acquisition unit is used to acquire the scoring weight values ​​corresponding to different types of real-time driving data; the driving behavior scoring unit is used to calculate the weighted value or weighted average value of different types of real-time driving data, and use the weighted value or weighted average value as the driving behavior score.

[0099] The dynamic premium adjustment module includes a risk level acquisition unit and an automatic premium adjustment unit.

[0100] The risk level acquisition unit is used to acquire the driving risk level based on the driving behavior score; the automatic premium adjustment unit is used to automatically adjust the next period's auto insurance premium based on the driving risk level and the dynamic premium adjustment mechanism.

[0101] Here, as Figure 6 As shown, the system first obtains multi-dimensional driving data from the vehicle terminal, including speed, braking frequency, and fatigue driving. Then, it generates a driving behavior score based on the driving behavior risk scoring model and maps the driving behavior score to three driving risk levels: low risk, medium risk, or high risk. Finally, it automatically adjusts the next period's car insurance premium according to the driving risk level, forming a closed-loop mechanism of "high risk → high premium, low risk → low premium".

[0102] Alternatively, the deviation value of the driving behavior score from a preset benchmark driving score can be obtained first, then the current premium can be obtained, and the next period's auto insurance premium can be automatically adjusted based on the current premium and the deviation value. Specifically, the dynamic premium adjustment module includes a score deviation acquisition unit and an automatic premium adjustment unit.

[0103] The scoring deviation acquisition unit is used to acquire the deviation value of the driving behavior score relative to the preset benchmark driving score; the premium automatic adjustment unit is used to acquire the current premium and automatically adjust the next period's auto insurance premium based on the current premium and the deviation value.

[0104] More specifically, it can be achieved through the formula Automatically adjust the next period's car insurance premium. Among them, P n+1 Indicates the next car insurance premium, P n R represents the current car insurance premium. base This represents the preset neutral baseline score (e.g., 60 points), ΔR = (RR) base ) / 100 represents the deviation of the driving behavior score R from the benchmark score, and α represents the adjustment coefficient (e.g., 0.2, which means that the deviation value fluctuates by 2% for every 10 points).

[0105] Drivers can first be clustered according to driving risk, dividing them into low / medium / high-risk groups, with different adjustment coefficients α corresponding to different risk groups. The higher the adjustment coefficient α of the high-risk group, the higher the neutral baseline score, and vice versa for the low-risk group, thus achieving differentiated premium pricing. For example, for the high-risk group, the adjustment coefficient is set to 0.3 and the neutral baseline score is set to 65, making it easier for high-risk drivers to trigger premium increases; for the low-risk group, the adjustment coefficient is set to 0.1 and the neutral baseline score is set to 55, making it easier for high-quality drivers to trigger discounts.

[0106] In summary, the vehicle insurance service system based on real-time driving data can achieve the following: 1. Clearly linking risky behavior with premiums, enabling vehicle insurance premiums to be priced based on driving behavior scores; 2. Improving drivers' safety awareness and reducing accident rates; 3. Automating the claims process, ensuring reliable and efficient data; 4. Reducing the operating costs of insurance companies and improving risk control capabilities; 5. Enhancing customer experience and forming a closed-loop service system.

[0107] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A vehicle insurance service method based on real-time driving data, characterized by, The vehicle insurance service method comprises the following steps: Collecting real-time driving data of a vehicle and preprocessing the real-time driving data; Building a driving behavior risk score model, taking the preprocessed real-time driving data as input of the driving behavior risk score model, and obtaining a driving behavior score; Automatically adjusting a next-term vehicle insurance premium according to the driving behavior score.

2. The vehicle insurance service method based on real-time driving data according to claim 1, characterized in that, The specific method for obtaining the driving behavior score comprises: Obtaining score weight values corresponding to different types of the real-time driving data; Calculating weighted values or weighted average values of different types of the real-time driving data, and taking the weighted values or weighted average values as the driving behavior score.

3. The vehicle insurance service method based on real-time driving data according to claim 2, wherein, The specific method for automatically adjusting the next-term vehicle insurance premium according to the driving behavior score comprises: Building a dynamic premium adjustment mechanism; Obtaining a driving risk level according to the driving behavior score; Based on the driving risk level and the dynamic premium adjustment mechanism, automatically adjusting the next-term vehicle insurance premium.

4. The vehicle insurance service method based on real-time driving data according to claim 2, wherein, The specific method for automatically adjusting the next-term vehicle insurance premium according to the driving behavior score comprises: Obtaining a deviation value of the driving behavior score relative to a preset benchmark driving score; Obtaining a current-term premium, and automatically adjusting the next-term vehicle insurance premium according to the current-term premium and the deviation value.

5. The vehicle insurance service method based on real-time driving data according to claim 1, wherein, The vehicle insurance service method further comprises the following steps: When an accident occurs, selecting key data from the real-time driving data; Uploading the key data to a cloud insurance service platform as a basis for claim settlement, and automatically triggering a claim settlement process.

6. A vehicle insurance service system based on real-time driving data for implementing the vehicle insurance service method based on real-time driving data according to any one of claims 1 to 5, characterized by The vehicle insurance service system comprises: A data collection module for collecting real-time driving data of a vehicle; A cloud insurance service platform comprising a driving behavior risk score model and a dynamic premium adjustment module, for preprocessing the real-time driving data; The driving behavior risk score model is used to obtain a driving behavior score according to the preprocessed real-time driving data, and the dynamic premium adjustment module is used to automatically adjust a next-term vehicle insurance premium according to the driving behavior score.

7. The vehicle insurance service system based on real-time driving data according to claim 6, wherein, The driving behavior risk score model comprises: A score weight obtaining unit for obtaining score weight values corresponding to different types of the real-time driving data; A driving behavior score unit for calculating weighted values or weighted average values of different types of the real-time driving data, and taking the weighted values or weighted average values as the driving behavior score.

8. The vehicle insurance service system based on real-time driving data according to claim 7, wherein, The dynamic premium adjustment module comprises: A risk level obtaining unit for obtaining a driving risk level according to the driving behavior score; A premium automatic adjustment unit for automatically adjusting a next-term vehicle insurance premium based on the driving risk level and a dynamic premium adjustment mechanism.

9. The vehicle insurance service system based on real-time driving data according to claim 7, wherein, The dynamic premium adjustment module comprises: A score deviation obtaining unit for obtaining a deviation value of the driving behavior score relative to a preset benchmark driving score; A premium automatic adjustment unit for obtaining a current-term premium, and automatically adjusting the next-term vehicle insurance premium according to the current-term premium and the deviation value.

10. The vehicle insurance service system based on real-time driving data according to claim 6, wherein, The cloud insurance service platform further comprises: An intelligent claim settlement module for, when an accident occurs, taking key data uploaded to the cloud insurance service platform as a basis for claim settlement, and automatically triggering a claim settlement process.

Images