Intelligent car insurance quotation system based on multi-modal data processing

Abstract

The invention relates to an intelligent car insurance quotation system based on multi-modal data processing. The intelligent car insurance quotation system comprises a multi-source data acquisition module, a risk domain construction module and a dynamic quotation module, the multi-source data acquisition module analyzes the driving behavior characteristics, the vehicle condition characteristics and the driving environment characteristics of the target vehicle based on the acquired image data, the structured text data and the sensor time sequence data; the risk domain construction module constructs a driving behavior risk curve of the target vehicle based on the driving behavior characteristics, constructs a vehicle condition risk curve of the target vehicle based on the vehicle condition characteristics, and then constructs a driving environment risk curve of the target vehicle based on the driving environment characteristics. And finally, constructing a dynamic quotation domain of the target vehicle based on the driving behavior risk curve, the vehicle condition risk curve and the driving environment risk curve. And the dynamic quotation module performs quotation analysis on the dynamic quotation domain to obtain the vehicle insurance quotation of the target vehicle.

Description

Technical Field

[0001] The present invention relates to the technical fields of big data and motor vehicle insurance quotation, and particularly relates to an intelligent motor vehicle insurance quotation system based on multi-modal data processing. Background Art

[0002] With the rapid development of the insurance and financial fields, especially in the current era of rapid development of the Internet economy, the traditional vehicle insurance application system can no longer meet the expansion of actual insurance business. At present, the practices of traditional motor vehicle insurance are that business agents expand business, telephone sales, and vehicle owners buy insurance at car dealerships. All three aspects are inseparable from the quotation of motor vehicle insurance, and they have the following disadvantages:

[0003] Traditional motor vehicle insurance quotation relies on manual experience and a single data source (such as vehicle model, historical claim records), and has the following problems: single data dimension: it is difficult to capture the actual state of the vehicle (accident damage) or the risk of driving behavior; subjective deviation: low efficiency of manual evaluation and vulnerable to subjective factors; lag in dynamic update: unable to fuse the latest vehicle state or driving data in real time. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides an intelligent motor vehicle insurance quotation system based on multi-modal data processing. The intelligent motor vehicle insurance quotation system includes: a multi-source data acquisition module, a risk domain construction module, and a dynamic quotation module, and there is a communication connection between each module; the risk domain construction module includes a first unit, a second unit, a third unit, and a construction unit, and there is a communication connection between each unit;

[0005] The multi-source data acquisition module acquires image data, structured text data, and sensor time series data of a target vehicle, and analyzes the driving behavior characteristics, vehicle condition characteristics, and driving environment characteristics of the target vehicle based on the image data, structured text data, and sensor time series data;

[0006] The first unit of the risk domain construction module constructs a driving behavior risk curve of the target vehicle based on the driving behavior characteristics;

[0007] The second unit of the risk domain construction module constructs a vehicle condition risk curve of the target vehicle based on the vehicle condition characteristics;

[0008] The third unit of the risk domain construction module constructs a driving environment risk curve of the target vehicle based on the driving environment characteristics;

[0009] The construction unit of the risk domain construction module constructs a dynamic quotation domain of the target vehicle based on the driving behavior risk curve, the vehicle condition risk curve, and the driving environment risk curve;

[0010] The dynamic quotation module performs quotation analysis on the dynamic quotation domain to obtain the motor vehicle insurance quotation of the target vehicle.

[0011] According to a preferred embodiment, the image data includes: vehicle damage images, high-definition vehicle body detail images, and driving environment images collected in real time by on-vehicle cameras; the structured text data includes vehicle repair records, insurance policy histories, and fault diagnosis reports; the sensor time-series data includes vehicle status parameters, GPS positioning trajectories, and environmental sensor data collected at high frequency through the on-vehicle OBD interface.

[0012] According to a preferred embodiment, the driving behavior characteristics, vehicle condition characteristics, and driving environment characteristics of the target vehicle obtained based on the image data, structured text data, and sensor time-series data include:

[0013] Perform data cleaning, dimension unification, and missing value filling on the image data, structured text data, and sensor time-series data to obtain standard image data, standard text data, and standard time-series data;

[0014] Perform visual feature parsing, text semantic mining, and behavior pattern extraction on the standard image data, standard text data, and standard time-series data respectively to obtain image features, text features, and time-series features;

[0015] Perform a spatio-temporal alignment layer and an attention fusion mechanism on the image features, text features, and time-series features to obtain a spatio-temporally synchronized fusion feature tensor;

[0016] Use the spatio-temporally synchronized fusion feature tensor to perform vehicle status diagnosis, driving risk prediction, and environmental perception verification on the target vehicle to obtain the driving behavior characteristics, vehicle condition characteristics, and driving environment characteristics of the target vehicle.

[0017] According to a preferred embodiment, constructing a driving behavior risk curve for the target vehicle based on the driving behavior characteristics includes:

[0018] Obtain a number of target driving behavior feature points based on the driving behavior characteristics of the target vehicle; obtain standard driving behavior characteristics from the database, and obtain corresponding standard driving behavior feature points based on the standard driving behavior characteristics;

[0019] Obtain the number of insurance claims and the amount of insurance claims of the target vehicle based on the historical insurance claim records of the target vehicle, and calculate the compensation correction distance using a preset compensation correction function and the number of insurance claims and the amount of insurance claims of the target vehicle;

[0020] Construct a first risk buffer domain with each standard driving behavior feature point as the center and the compensation correction distance as the radius, and find a circle tangent to the first risk buffer domain with each target driving behavior feature point as the center, and then use the corresponding tangent point as the risk critical point corresponding to each target driving behavior feature point;

[0021] Connect the risk critical points corresponding to all target driving behavior feature points to obtain a driving behavior risk curve.

[0022] According to a preferred embodiment, constructing a vehicle condition risk curve for a target vehicle based on the vehicle condition features includes:

[0023] Obtain a number of target vehicle condition feature points based on the vehicle condition features of the target vehicle; obtain standard vehicle condition features from a database, and obtain corresponding standard vehicle condition feature points based on the standard vehicle condition features;

[0024] Obtain the number of claims and claim amounts of the target vehicle based on the historical claim records of the target vehicle, and calculate a compensation correction distance using a preset compensation correction function and the number of claims and claim amounts of the target vehicle;

[0025] Construct a second risk buffer domain with each standard vehicle condition feature point as the center and the compensation correction distance as the radius, and find a circle tangent to the second risk buffer domain with each target vehicle condition feature point as the center, and then use the corresponding tangent point as the risk critical point corresponding to each target vehicle condition feature point;

[0026] Connect the risk critical points corresponding to all target vehicle condition feature points to obtain a vehicle condition risk curve.

[0027] According to a preferred embodiment, constructing a driving environment risk curve for a target vehicle based on the driving environment features includes:

[0028] Obtain a number of target driving environment feature points based on the driving environment features of the target vehicle; obtain standard driving environment features from a database, and obtain corresponding standard driving environment feature points based on the standard driving environment features;

[0029] Obtain the number of claims and claim amounts of the target vehicle based on the historical claim records of the target vehicle, and calculate a compensation correction distance using a preset compensation correction function and the number of claims and claim amounts of the target vehicle;

[0030] Construct a third risk buffer domain with each standard driving environment feature point as the center and the compensation correction distance as the radius, and find a circle tangent to the third risk buffer domain with each target driving environment feature point as the center, and then use the corresponding tangent point as the risk critical point corresponding to each target driving environment feature point;

[0031] Connect the risk critical points corresponding to all target driving environment feature points to obtain a driving environment risk curve.

[0032] According to a preferred embodiment, constructing a dynamic quotation domain for the target vehicle based on the driving behavior risk curve, the vehicle condition risk curve, and the driving environment risk curve includes:

[0033] Performing step-by-step boundary convergence on the driving behavior risk curve to obtain a driving behavior risk boundary line;

[0034] Performing step-by-step boundary convergence on the vehicle condition risk curve to obtain a vehicle condition risk boundary line;

[0035] Performing step-by-step boundary convergence on the driving environment risk curve to obtain a driving environment risk boundary line;

[0036] Performing dynamic fitting on the driving behavior risk boundary line, the vehicle condition risk boundary line, and the driving environment risk boundary line to obtain a dynamic quotation domain.

[0037] According to a preferred embodiment, performing step-by-step boundary convergence on the driving behavior risk curve to obtain a driving behavior risk boundary line includes:

[0038] Obtaining all risk critical points of the driving behavior risk curve and extracting the eigenvalue of each risk critical point; calculating the average eigenvalue of all risk critical points and obtaining a first convergence reference point based on the average eigenvalue;

[0039] Obtaining all extreme points of the driving behavior risk curve and taking all extreme points as the first convergence points to obtain a number of first convergence points;

[0040] Taking the direction from each first convergence point to the first convergence reference point as the boundary iteration direction of each first convergence point;

[0041] Moving the first convergence point along the boundary iteration direction of each first convergence point by a preset step length and determining whether the first convergence point is within the area of the first risk buffer domain. If the first convergence point is within the area of the first risk buffer domain, continue to move the first convergence point by the preset step length until the first convergence point is not within the area of the first risk buffer domain, and take the first convergence point at this time as the driving behavior risk boundary point;

[0042] Connecting the driving behavior risk boundary points of all first convergence points to obtain a driving behavior risk boundary line.

[0043] According to a preferred embodiment, performing step-by-step boundary convergence on the vehicle condition risk curve to obtain a vehicle condition risk boundary line includes:

[0044] Obtaining all risk critical points of the vehicle condition risk curve and extracting the eigenvalue of each risk critical point; calculating the average eigenvalue of all risk critical points and obtaining a second convergence reference point based on the average eigenvalue;

[0045] Obtain all extreme points of the vehicle condition risk curve, and use all extreme points as the second convergence points to obtain a number of second convergence points;

[0046] Take the direction from each second convergence point to the second convergence reference point as the boundary iteration direction of each second convergence point;

[0047] Move the second convergence point along the boundary iteration direction of each second convergence point according to a preset step size, and determine whether the second convergence point is within the area of the second risk buffer area. If the second convergence point is within the area of the second risk buffer area, continue to move the second convergence point according to the preset step size until the second convergence point is not within the area of the second risk buffer area, and use the second convergence point at this time as the vehicle condition risk boundary point;

[0048] Connect the vehicle condition risk boundary points of all second convergence points to obtain the vehicle condition risk boundary line.

[0049] According to a preferred embodiment, performing step-by-step boundary convergence on the driving environment risk curve to obtain the driving environment risk boundary line includes:

[0050] Obtain all risk critical points of the driving environment risk curve, and extract the characteristic values of each risk critical point; calculate the average characteristic value of all risk critical points, and obtain the third convergence reference point based on the average characteristic value;

[0051] Obtain all extreme points of the driving environment risk curve, and use all extreme points as the third convergence points to obtain a number of third convergence points;

[0052] Take the direction from each third convergence point to the third convergence reference point as the boundary iteration direction of each third convergence point;

[0053] Move the third convergence point along the boundary iteration direction of each third convergence point according to a preset step size, and determine whether the third convergence point is within the area of the third risk buffer area. If the third convergence point is within the area of the third risk buffer area, continue to move the third convergence point according to the preset step size until the third convergence point is not within the area of the third risk buffer area, and use the third convergence point at this time as the driving environment risk boundary point;

[0054] Connect the driving environment risk boundary points of all third convergence points to obtain the driving environment risk boundary line.

[0055] According to a preferred embodiment, the intelligent vehicle insurance quotation system further includes a user terminal; the user terminal sends a quotation request to the multi-source data acquisition module; the multi-source data acquisition module determines the target vehicle in response to the received quotation request, and acquires the image data, structured text data and sensor time series data of the target vehicle.

[0056] According to a preferred embodiment, the dynamic quotation module performs quotation analysis on the dynamic quotation field to obtain the vehicle insurance quotation of the target vehicle, and sends the vehicle insurance quotation of the target vehicle to the corresponding user terminal.

[0057] According to a preferred embodiment, the used terminal is a device used by a user and having communication functions and data transmission functions, including: smart phones, tablet computers, laptop computers, and smart watches.

[0058] The present invention has the following beneficial effects: By deeply integrating multi-dimensional data such as driving behavior, vehicle status, and driving environment, this application breaks through the limitation of traditional vehicle insurance relying on a single static indicator, and constructs a dynamic risk assessment model. Based on real-time interaction analysis of the collaborative effects of driving habit risk tendencies, vehicle component health, and environmental road condition complexity, accurate premium calculation and instant adjustment are realized, significantly improving the risk identification coverage and response efficiency. At the same time, by cross-verifying the matching of vehicle usage intensity and mechanical wear, the abnormal behavior monitoring ability is strengthened, and the fraud risk is effectively prevented. This technology promotes the transformation of vehicle insurance pricing from an empirical and extensive mode to a personalized and dynamic quantification mode, provides a protection plan adapted to the actual risks of each vehicle, and forms a complete chain of active risk management closed-loop of "assessment - warning - optimization". BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 The block diagram of a smart vehicle insurance quotation system based on multi-modal data processing provided for an exemplary embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0060] Here, the exemplary embodiments will be described in detail, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0061] The terms used in the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms of "a", "the", and "said" used in the present invention and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0062] It should be understood that although the terms first, second, third, etc. may be used in the present invention to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from each other. For example, without departing from the scope of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "when" or "while" or "in response to a determination".

[0063] See Figure 1 , in one embodiment, an intelligent auto insurance quotation system based on multimodal data processing includes: a multi-source data acquisition module, a risk domain construction module, and a dynamic quotation module, and there is a communication connection between the modules; the risk domain construction module includes a first unit, a second unit, a third unit, and a construction unit, and there is a communication connection between the units.

[0064] The multi-source data acquisition module acquires image data, structured text data, and sensor time-series data of the target vehicle, and analyzes the driving behavior characteristics, vehicle condition characteristics, and driving environment characteristics of the target vehicle based on the image data, structured text data, and sensor time-series data;

[0065] The image data includes: vehicle damage images, high-definition vehicle body detail images, and driving environment images collected in real time by an in-vehicle camera; the structured text data includes vehicle repair records, insurance policy histories, and fault diagnosis reports; the sensor time-series data includes vehicle state parameters, GPS positioning trajectories, and environmental sensor data collected at high frequency through an in-vehicle OBD interface.

[0066] The source of the image data is an in-vehicle camera (resolution ≥ 1920×1080), user-uploaded accident photos (format is JPEG or PNG, size ≤ 10MB);

[0067] The source of the text data is the insurance company database (JSON / CSV format) and the OCR-recognized repair records;

[0068] The sensor time-series data is collected through the OBD interface at a frequency of 10Hz, covering hard acceleration (acceleration > 2.5m / s 2 ), hard braking (deceleration > 3.0m / s 2 ) events

[0069] The structured text data includes vehicle repair records (including repair items, dates, and costs), insurance policy histories (insurance dates, claim amounts), and fault diagnosis reports (fault codes and descriptions), which are stored in JSON / CSV format and conform to the ISO18542 standardized machine-readable data structure.

[0070] The sensor time-series data includes vehicle status parameters (such as engine speed, vehicle speed, hard acceleration / hard braking events) collected at high frequency (10Hz) through the vehicle OBD interface, GPS positioning trajectories (accuracy ≤ 1 meter), and environmental sensor data (such as tire pressure, temperature), and is stored in a standardized time series format for driving behavior modeling and risk analysis.

[0071] In a preferred embodiment, the driving behavior characteristics, vehicle condition characteristics, and driving environment characteristics of the target vehicle obtained based on the image data, structured text data, and sensor time-series data include:

[0072] Perform data cleaning, dimension unification, and missing value filling on the image data, structured text data, and sensor time-series data to obtain standard image data, standard text data, and standard time-series data;

[0073] Perform visual feature parsing, text semantic mining, and behavior pattern extraction on the standard image data, standard text data, and standard time-series data respectively to obtain image features, text features, and time-series features;

[0074] Perform a spatio-temporal alignment layer and an attention fusion mechanism on the image features, text features, and time-series features to obtain a spatio-temporally synchronized fusion feature tensor;

[0075] Use the spatio-temporally synchronized fusion feature tensor to perform vehicle status diagnosis, driving risk prediction, and environmental perception verification on the target vehicle to obtain the driving behavior characteristics, vehicle condition characteristics, and driving environment characteristics of the target vehicle.

[0076] Optionally, the driving behavior characteristics are used to characterize the driving habits of the driver of the target vehicle, and the driving habits include whether there are frequent hard brakes, speeding, random lane changes, following too closely, as well as dangerous driving behaviors such as night driving and fatigue driving.

[0077] Optionally, the vehicle condition characteristics are used to characterize the vehicle condition of the target vehicle, and the vehicle condition covers appearance scratches, engine oil leakage or abnormal noise, gearbox jerks, brake sensitivity, tire wear, chassis rust or deformation, and whether electronic devices (such as ABS, airbags) are normal, comprehensively reflecting the vehicle health and potential risks.

[0078] Optionally, the driving environment characteristics are used to characterize the environment where the target vehicle often travels, including the weather (rain / snow / fog) in the frequently traveled area, road type (highway / mountain road / unpaved road), congestion frequency, proportion of night driving, and whether it passes through school areas, construction areas, or sharp turn and steep slope sections, affecting vehicle wear and accident probability.

[0079] The first unit of the risk domain construction module constructs a driving behavior risk curve for the target vehicle based on the driving behavior characteristics.

[0080] In a preferred embodiment, constructing a driving behavior risk curve for the target vehicle based on the driving behavior characteristics includes:

[0081] Obtaining a number of target driving behavior feature points based on the driving behavior characteristics of the target vehicle; obtaining standard driving behavior characteristics from a database, and obtaining corresponding standard driving behavior feature points based on the standard driving behavior characteristics;

[0082] Obtaining the number of insurance claims and the amount of insurance claims of the target vehicle based on the historical insurance claim records of the target vehicle, and calculating a compensation correction distance using a preset compensation correction function and the number of insurance claims and the amount of insurance claims of the target vehicle;

[0083] Constructing a first risk buffer region with each standard driving behavior feature point as the center and the compensation correction distance as the radius, and finding a circle tangent to the first risk buffer region with each target driving behavior feature point as the center, and then using the corresponding tangent point as the risk critical point corresponding to each target driving behavior feature point;

[0084] Connecting the risk critical points corresponding to all target driving behavior feature points to obtain a driving behavior risk curve.

[0085] Optionally, the standard driving behavior characteristics are the related characteristics of the standard driving behavior, and the standard driving behavior refers to the standard driving habits of strictly observing traffic regulations, maintaining a reasonable vehicle distance, accelerating and decelerating smoothly, avoiding speeding or dangerous lane changes, and being able to actively adjust the vehicle speed and operations according to weather and road conditions.

[0086] The second unit of the risk region construction module constructs a vehicle condition risk curve for the target vehicle based on the vehicle condition characteristics.

[0087] In a preferred embodiment, constructing a vehicle condition risk curve for the target vehicle based on the vehicle condition characteristics includes:

[0088] Obtaining a number of target vehicle condition feature points based on the vehicle condition characteristics of the target vehicle; obtaining standard vehicle condition characteristics from a database, and obtaining corresponding standard vehicle condition feature points based on the standard vehicle condition characteristics;

[0089] Obtaining the number of insurance claims and the amount of insurance claims of the target vehicle based on the historical insurance claim records of the target vehicle, and calculating a compensation correction distance using a preset compensation correction function and the number of insurance claims and the amount of insurance claims of the target vehicle;

[0090] Constructing a second risk buffer region with each standard vehicle condition feature point as the center and the compensation correction distance as the radius, and finding a circle tangent to the second risk buffer region with each target vehicle condition feature point as the center, and then using the corresponding tangent point as the risk critical point corresponding to each target vehicle condition feature point;

[0091] Connect the risk critical points corresponding to all the target vehicle condition feature points to obtain a vehicle condition risk curve.

[0092] The standard vehicle condition features are the features of the standard vehicle condition. The standard vehicle condition refers to the intact state where the vehicle appearance has no damage, and all mechanical components (such as the engine, braking system, and tires) have no wear or aging, and all functions (lights, electronic devices) meet the factory safety standards.

[0093] The third unit of the risk domain construction module constructs a driving environment risk curve for the target vehicle based on the driving environment features.

[0094] In a preferred embodiment, constructing a driving environment risk curve for the target vehicle based on the driving environment features includes:

[0095] Obtain a number of target driving environment feature points based on the driving environment features of the target vehicle; obtain the standard driving environment features from the database, and obtain the corresponding number of standard driving environment feature points based on the standard driving environment features;

[0096] Obtain the number of claims and claim amounts of the target vehicle based on the historical claim records of the target vehicle, and calculate the compensation correction distance by using a preset compensation correction function and the number of claims and claim amounts of the target vehicle;

[0097] Construct a third risk buffer domain with each standard driving environment feature point as the center and the compensation correction distance as the radius, and find a circle tangent to the third risk buffer domain with each target driving environment feature point as the center, and then use the corresponding tangent point as the risk critical point corresponding to each target driving environment feature point;

[0098] Connect the risk critical points corresponding to all the target driving environment feature points to obtain a driving environment risk curve.

[0099] Optionally, the standard driving environment features are the relevant features of the standard driving environment. The standard driving environment refers to a low-risk driving environment where the road is flat and unobstructed, the climate conditions are good (no extreme rain, snow, or fog), and high-risk sections such as construction areas, sharp curves, and steep slopes are avoided, and the traffic flow is moderate, meeting the basic conditions for safe vehicle driving.

[0100] Optionally, the compensation correction distance is used to correct the user's claim records and claim amounts when evaluating the driving behavior risk, vehicle state risk, and driving environment risk of the target vehicle. For example, although the driving behavior and driving environment of the driver of the target vehicle do not meet the standards, but there has been no claim for many years, so the premium cannot be increased only based on the non-compliance of the driving behavior and driving environment.

[0101] The construction unit of the risk domain construction module constructs the dynamic quotation domain of the target vehicle based on the driving behavior risk curve, the vehicle condition risk curve, and the driving environment risk curve.

[0102] Optionally, constructing the dynamic quotation domain of the target vehicle based on the driving behavior risk curve, the vehicle condition risk curve, and the driving environment risk curve; includes:

[0103] Performing step-by-step boundary convergence on the driving behavior risk curve to obtain the driving behavior risk boundary line;

[0104] Performing step-by-step boundary convergence on the vehicle condition risk curve to obtain the vehicle condition risk boundary line;

[0105] Performing step-by-step boundary convergence on the driving environment risk curve to obtain the driving environment risk boundary line;

[0106] Performing dynamic fitting on the driving behavior risk boundary line, the vehicle condition risk boundary line, and the driving environment risk boundary line to obtain the dynamic quotation domain.

[0107] In a preferred embodiment, performing step-by-step boundary convergence on the driving behavior risk curve to obtain the driving behavior risk boundary line includes:

[0108] Obtaining all risk critical points of the driving behavior risk curve, and extracting the characteristic values of each risk critical point; calculating the average characteristic value of all risk critical points, and obtaining the first convergence reference point based on the average characteristic value;

[0109] Obtaining all extreme points of the driving behavior risk curve, and taking all extreme points as the first convergence points to obtain several first convergence points;

[0110] Taking the direction from each first convergence point to the first convergence reference point as the boundary iteration direction of each first convergence point;

[0111] Moving the first convergence point along the boundary iteration direction of each first convergence point by a preset step length, and determining whether the first convergence point is within the area of the first risk buffer domain. If the first convergence point is within the area of the first risk buffer domain, continue to move the first convergence point by the preset step length until the first convergence point is not within the area of the first risk buffer domain, and take the first convergence point at this time as the driving behavior risk boundary point;

[0112] Connecting the driving behavior risk boundary points of all first convergence points to obtain the driving behavior risk boundary line.

[0113] In a preferred embodiment, performing step-by-step boundary convergence on the vehicle condition risk curve to obtain the vehicle condition risk boundary line includes:

[0114] Obtain all risk critical points of the vehicle condition risk curve, and extract the characteristic values of each risk critical point; calculate the average characteristic value of all risk critical points, and obtain the second convergence reference point based on the average characteristic value;

[0115] Obtain all extreme points of the vehicle condition risk curve, and use all extreme points as the second convergence points to obtain several second convergence points;

[0116] Take the direction of each second convergence point pointing to the second convergence reference point as the boundary iteration direction of each second convergence point;

[0117] Move the second convergence point along the boundary iteration direction of each second convergence point at a preset step length, and determine whether the second convergence point is within the area of the second risk buffer domain. If the second convergence point is within the area of the second risk buffer domain, continue to move the second convergence point at the preset step length until the second convergence point is not within the area of the second risk buffer domain, and use the second convergence point at this time as the vehicle condition risk boundary point;

[0118] Connect the vehicle condition risk boundary points of all second convergence points to obtain the vehicle condition risk boundary line.

[0119] In a preferred embodiment, performing stepwise boundary convergence on the driving environment risk curve to obtain the driving environment risk boundary line includes:

[0120] Obtain all risk critical points of the driving environment risk curve, and extract the characteristic values of each risk critical point; calculate the average characteristic value of all risk critical points, and obtain the third convergence reference point based on the average characteristic value;

[0121] Obtain all extreme points of the driving environment risk curve, and use all extreme points as the third convergence points to obtain several third convergence points;

[0122] Take the direction of each third convergence point pointing to the third convergence reference point as the boundary iteration direction of each third convergence point;

[0123] Move the third convergence point along the boundary iteration direction of each third convergence point at a preset step length, and determine whether the third convergence point is within the area of the third risk buffer domain. If the third convergence point is within the area of the third risk buffer domain, continue to move the third convergence point at the preset step length until the third convergence point is not within the area of the third risk buffer domain, and use the third convergence point at this time as the driving environment risk boundary point;

[0124] Connect the driving environment risk boundary points of all third convergence points to obtain the driving environment risk boundary line.

[0125] Optionally, the extreme point is the maximum or minimum value within a certain area of the curve.

[0126] Optionally, each feature point has a uniquely corresponding feature value, and the corresponding feature point can be uniquely located through the feature value.

[0127] The dynamic quotation module performs quotation analysis on the dynamic quotation field to obtain the vehicle insurance quotation of the target vehicle.

[0128] Optionally, the vehicle insurance quotation of the target vehicle includes the cost of vehicle insurance that the target vehicle needs to pay in the current year.

[0129] Preferably, the dynamic quotation field is used to characterize the driving behavior risk distribution, vehicle condition risk distribution and driving environment risk distribution of the target vehicle.

[0130] Preferably, the intelligent vehicle insurance quotation system further includes a user terminal; the user terminal sends a quotation request to the multi-source data collection module; the multi-source data collection module determines the target vehicle in response to the received quotation request, and collects the image data, structured text data and sensor time series data of the target vehicle.

[0131] Preferably, the dynamic quotation module performs quotation analysis on the dynamic quotation field to obtain the vehicle insurance quotation of the target vehicle, and sends the vehicle insurance quotation of the target vehicle to the corresponding user terminal.

[0132] Preferably, the user terminal is a device used by the user with communication function and data transmission function, including: smart phone, tablet computer, notebook computer and smart watch.

[0133] This application deeply integrates multi-dimensional data such as driving behavior, vehicle status and driving environment, breaks through the limitation of traditional vehicle insurance relying on a single static index, and constructs a dynamic risk assessment model. Based on real-time interactive analysis of the synergistic effects of driving habit risk tendency, vehicle component health and environmental road condition complexity, it realizes accurate premium calculation and instant adjustment, significantly improves the risk identification coverage and response efficiency. At the same time, by cross-verifying the matching of vehicle usage intensity and mechanical loss, it strengthens the abnormal behavior monitoring ability and effectively prevents fraud risks. This technology promotes the transformation of vehicle insurance pricing from an empirical and extensive mode to a personalized dynamic quantification, provides a protection plan adapted to the actual risks of each vehicle, and forms a complete chain of active risk management closed-loop of "assessment - early warning - optimization".

[0134] The computer program instructions for performing the operations of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages such as Smalltalk, C++, etc., and procedural programming languages such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, by using the state information of the computer-readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions to implement various aspects of the present invention.

[0135] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the scope of protection of the present invention.

Claims

1. An intelligent auto insurance quotation system based on multimodal data processing, characterized in that: The intelligent auto insurance quotation system includes: a multi-source data acquisition module, a risk domain construction module, and a dynamic quotation module, and each module has a communication connection; the risk domain construction module includes a first unit, a second unit, a third unit and a construction unit, and each unit has a communication connection; The multi-source data acquisition module acquires image data, structured text data and sensor time series data of the target vehicle, and analyzes driving behavior characteristics, vehicle condition characteristics and driving environment characteristics of the target vehicle based on the image data, structured text data and sensor time series data; The first unit of the risk domain construction module constructs a driving behavior risk curve of the target vehicle based on the driving behavior characteristics; The second unit of the risk domain construction module constructs a vehicle condition risk curve of the target vehicle based on the vehicle condition characteristics; The third unit of the risk domain construction module constructs a driving environment risk curve of the target vehicle based on the driving environment characteristics; The construction unit of the risk domain construction module constructs a dynamic quotation domain of the target vehicle based on the driving behavior risk curve, the vehicle condition risk curve and the driving environment risk curve; The dynamic quotation module performs quotation analysis on the dynamic quotation domain to obtain a car insurance quotation for the target vehicle.

2. The intelligent auto insurance quotation system according to claim 1, characterized in that: The image data includes: vehicle damage images, high-definition details of the vehicle body, and driving environment images collected in real time by the on-board camera; the structured text data includes vehicle maintenance records, insurance policy history, and fault diagnosis reports; the sensor time series data includes vehicle status parameters, GPS positioning trajectories, and environmental sensor data collected at high frequency through the on-board OBD interface.

3. The intelligent auto insurance quotation system according to claim 1, characterized in that: The driving behavior characteristics, vehicle condition characteristics and driving environment characteristics of the target vehicle obtained based on the analysis of the image data, structured text data and sensor time series data include: Perform data cleaning, dimension unification and missing value filling on image data, structured text data and sensor time series data to obtain standard image data, standard text data and standard time series data; Perform visual feature analysis, text semantic mining and behavior pattern extraction on standard image data, standard text data and standard time series data to obtain image features, text features and time series features; Perform spatiotemporal alignment and attention fusion mechanisms on image features, text features, and time series features to obtain a spatiotemporal synchronized fused feature tensor. The target vehicle is diagnosed with a vehicle state, predicted with driving risks, and verified by environmental perception using the spatiotemporally synchronized fusion feature tensor to obtain the target vehicle's driving behavior characteristics, vehicle condition characteristics, and driving environment characteristics.

4. The intelligent auto insurance quotation system according to claim 1, characterized in that: Constructing a driving behavior risk curve of a target vehicle based on the driving behavior characteristics includes: Acquire a number of target driving behavior feature points based on the driving behavior feature of the target vehicle; acquire a standard driving behavior feature from a database, and acquire a number of corresponding standard driving behavior feature points based on the standard driving behavior feature; The number of accidents and the amount of the accident of the target vehicle are obtained based on the historical accident records of the target vehicle, and the compensation correction distance is calculated using the preset compensation correction function and the number of accidents and the amount of the accident of the target vehicle; A first risk buffer domain is constructed with each standard driving behavior feature point as the center and the compensation correction distance as the radius, and a circle tangent to the first risk buffer domain is found with each target driving behavior feature point as the center, and then the corresponding tangent point is used as the risk critical point corresponding to each target driving behavior feature point; Connect the risk critical points corresponding to all target driving behavior feature points to obtain the driving behavior risk curve.

5. The intelligent auto insurance quotation system according to claim 4, characterized in that: Constructing a dynamic quotation domain of a target vehicle based on the driving behavior risk curve, the vehicle condition risk curve and the driving environment risk curve; including: Perform step-by-step boundary convergence on the driving behavior risk curve to obtain the driving behavior risk boundary line; Perform step-by-step boundary convergence on the vehicle condition risk curve to obtain the vehicle condition risk boundary line; Perform step-by-step boundary convergence on the driving environment risk curve to obtain the driving environment risk boundary line; The driving behavior risk boundary line, vehicle condition risk boundary line and driving environment risk boundary line are dynamically fitted to obtain a dynamic quotation domain.

6. The intelligent auto insurance quotation system according to claim 5, characterized in that: The driving behavior risk boundary line obtained by step-by-step boundary convergence of the driving behavior risk curve includes: Obtaining all risk critical points of the driving behavior risk curve and extracting the characteristic value of each risk critical point; calculating the average characteristic value of all risk critical points, and obtaining the first convergence reference point based on the average characteristic value; Obtain all extreme value points of the driving behavior risk curve, and use all extreme value points as first convergence points to obtain a number of first convergence points; The direction from each first convergence point to the first convergence reference point is used as the boundary iteration direction of each first convergence point; Moving the first convergence point according to a preset step length in a boundary iteration direction of each first convergence point, and determining whether the first convergence point is within the region of the first risk buffer domain; if the first convergence point is within the region of the first risk buffer domain, continuing to move the first convergence point according to the preset step length until the first convergence point is no longer within the region of the first risk buffer domain, and using the first convergence point at this time as a driving behavior risk boundary point; Connect all driving behavior risk boundary points of the first convergence point to obtain the driving behavior risk boundary line.

7. The intelligent auto insurance quotation system according to claim 1, characterized in that: The intelligent auto insurance quotation system also includes a user terminal; the user terminal sends a quotation request to the multi-source data acquisition module; the multi-source data acquisition module determines the target vehicle in response to the received quotation request, and collects image data, structured text data and sensor timing data of the target vehicle.

8. The intelligent auto insurance quotation system according to claim 7, characterized in that: The dynamic quotation module performs quotation analysis on the dynamic quotation domain to obtain the auto insurance quotation of the target vehicle, and sends the auto insurance quotation of the target vehicle to the corresponding user terminal.

9. The intelligent auto insurance quotation system according to claim 8, characterized in that: The terminal device with communication function and data transmission function used by users includes: smart phones, tablet computers, laptop computers and smart watches.

Images