Vehicle insurance pricing information determination method and device, equipment and medium

Abstract

The invention belongs to the field of big data, and relates to a vehicle insurance pricing information determination method, which comprises the steps of: when an insurance pricing request of a target vehicle is detected, firstly obtaining public security data of a resident position of the target vehicle, and evaluating a public security environment score by using an environment scoring model; and then climate data of the resident position is collected, and climate risks are predicted through a logistic regression model to obtain climate risk indexes. And obtaining vehicle data of a target vehicle, and calculating a vehicle risk index by using the vehicle risk scoring model. And finally, comprehensively determining vehicle insurance pricing information of the target vehicle by adopting an insurance premium pricing model in combination with the public security environment score, the climate risk index and the vehicle risk index. The invention further provides a device, equipment and a medium. In addition, the invention also relates to a block chain technology, and the car insurance pricing information can be stored in a block chain. The vehicle insurance pricing method and device can be applied to the business fields of financial insurance and the like, and accurate vehicle insurance pricing can be carried out on different types of customers.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to a method, apparatus, device, and medium for determining automobile insurance pricing information. Background Art

[0002] In the financial insurance sector, auto insurance, as a crucial component of property and casualty insurance, has long held a significant market share. Scratch insurance (full name: vehicle body scratch loss insurance), a popular auto insurance product, generates substantial annual revenue for property and casualty insurance companies. However, significant flaws in the traditional scratch insurance pricing model have severely hampered the further development of the property and casualty insurance business.

[0003] Traditional scratch insurance pricing relies primarily on the experience and judgment of sales representatives. This experience-driven approach lacks scientific and systematic principles, making it difficult to accurately price insurance for different customer types. In practice, due to the subjectivity and limitations of sales representatives' experience, various factors influencing scratch insurance risk cannot be fully and accurately considered, resulting in low prices for customers. For property and casualty insurance companies, low prices can lead to greater claims pressure, which in turn affects their revenue and profits.

[0004] To sum up, in the face of differences in needs among different user groups, there is an urgent need for a more personalized auto insurance pricing method that meets user needs, so as to achieve accurate auto insurance pricing for customers with different risk conditions. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to propose a method, device, equipment and medium for determining auto insurance pricing information to solve the problem that traditional auto insurance pricing relies too much on the experience and judgment of business personnel and cannot accurately price auto insurance for different types of customers.

[0006] In the first aspect, a method for determining auto insurance pricing information is provided, which adopts the following technical solutions:

[0007] When an insurance pricing request of a target vehicle is detected, the public security data of the target vehicle's permanent location is obtained; based on the public security data, a preset environmental scoring model is used to perform a public security score to obtain a public security environment score for the permanent location; the climate data of the permanent location is obtained, and based on the climate data, a preset logistic regression model is used to perform a climate risk prediction to obtain a climate risk index for the target vehicle; the vehicle data of the target vehicle is obtained, and based on the vehicle data, a preset vehicle risk scoring model is used to perform a vehicle risk score to obtain a vehicle risk index for the target vehicle; based on the public security environment score, the climate risk index, and the vehicle risk index, a preset premium pricing model is used to perform insurance pricing to obtain vehicle insurance pricing information for the target vehicle.

[0008] In a second aspect, a device for determining auto insurance pricing information is provided, which employs the following technical solutions:

[0009] an acquisition module, configured to acquire the security data of the permanent location of the target vehicle when an insurance pricing request of the target vehicle is detected;

[0010] The environmental scoring module is used to perform public security scoring based on public security data using a preset environmental scoring model to obtain a public security environment score for the resident location;

[0011] The prediction module is used to obtain climate data of the permanent location, and based on the climate data, use a preset logistic regression model to predict climate risk and obtain the climate risk index of the target vehicle;

[0012] The risk scoring module is used to obtain vehicle data of the target vehicle, and perform a vehicle risk score based on the vehicle data using a preset vehicle risk scoring model to obtain a vehicle risk index of the target vehicle;

[0013] The pricing module is used to perform insurance pricing based on the public security environment score, climate risk index and vehicle risk index using a preset premium pricing model to obtain the vehicle insurance pricing information of the target vehicle.

[0014] In a third aspect, a computer device is provided, including a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the steps of the method for determining the vehicle insurance pricing information as described above are implemented.

[0015] In a fourth aspect, a computer-readable storage medium is provided, which stores computer-readable instructions. The computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the method for determining the vehicle insurance pricing information as described above.

[0016] In the solution implemented by the aforementioned method, apparatus, device, and medium for determining auto insurance pricing information, upon detecting an insurance pricing request from a target vehicle, the system first obtains public security data for the vehicle's permanent location and generates a public security score based on a pre-set environmental scoring model. This accurately quantifies the impact of varying public security environments on the vehicle's scratch risk, reversing the ambiguity inherent in traditional methods that rely solely on empirical assessments of public security factors. It then obtains climate data for the permanent location and uses a pre-set logistic regression model to predict climate risk. This allows for a scientific assessment of the scratch risk posed by different climatic conditions, addressing the shortcomings of traditional pricing methods that often fail to consider climatic factors. Simultaneously, the system obtains vehicle data for the target vehicle and generates a risk score using a pre-set vehicle risk scoring model, comprehensively considering the risks posed by the vehicle's inherent characteristics. Finally, the pre-set premium pricing model integrates the public security environment score, climate risk index, and vehicle risk index to determine insurance pricing. This enables accurate and rational auto insurance pricing for customers with varying risk profiles. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the solutions in this application, a brief introduction will be given below to the drawings required for use in the description of the embodiments of this application. Obviously, the drawings described below are some embodiments of this application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 is an exemplary system architecture diagram to which the present application may be applied;

[0019] Figure 2 This is a flowchart of a method for determining auto insurance pricing information provided by this application;

[0020] Figure 3 This is a schematic diagram of the structure of a device for determining automobile insurance pricing information provided by this application;

[0021] Figure 4 This is a structural diagram of a computer device provided by this application. DETAILED DESCRIPTION

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meanings as commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of the application are for the purpose of describing specific embodiments only and are not intended to limit this application. The terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0023] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute an independent or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0024] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0025] like Figure 1 As shown, system architecture 100 may include a terminal device 101, a network 102, and a server 103. Terminal device 101 may be a laptop computer 1011, a tablet computer 1012, or a mobile phone 1013. Network 102 is a medium for providing a communication link between terminal device 101 and server 103. Network 102 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0026] The user can use the terminal device 101 to interact with the server 103 via the network 102 to receive or send messages, etc. Various communication client applications can be installed on the terminal device 101, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0027] The terminal device 101 can be various electronic devices with a display screen and supporting web browsing. In addition to the laptop computer 1011, tablet computer 1012 or mobile phone 1013, the terminal device 101 can also be an e-book reader, an MP3 player (Moving Picture Experts Group Audio Layer III, Moving Picture Experts Group Audio Layer III), an MP4 (Moving Picture Experts Group Audio Layer IV, Moving Picture Experts Group Audio Layer IV) player, a laptop computer and a desktop computer, etc.

[0028] The server 103 may be a server that provides various services, such as a background server that provides support for web pages displayed on the terminal device 101 .

[0029] It should be noted that the method for determining the auto insurance pricing information provided in the embodiment of the present application is generally executed by a server, and accordingly, the device for determining the auto insurance pricing information is generally set in the server.

[0030] It should be understood that Figure 1 The number of terminal devices, networks and servers in the embodiment is merely illustrative. Any number of terminal devices, networks and servers may be provided as required.

[0031] Continue to refer Figure 2 , shows a flow chart of an embodiment of a method for determining auto insurance pricing information according to the present application. The method for determining auto insurance pricing information comprises the following steps:

[0032] In step S201 , when an insurance pricing request of a target vehicle is detected, public security data of the target vehicle's permanent location is obtained.

[0033] The target vehicle refers to the specific vehicle selected for insurance pricing analysis during the current auto insurance pricing process. This information is derived from the vehicle information associated with the insurance pricing request received by the auto insurance business system. For example, when a car owner submits a scratch insurance pricing request to an insurance company, that vehicle becomes the target vehicle for subsequent pricing analysis.

[0034] An insurance pricing request is a request from a customer to the insurance business system, requesting information on insurance pricing for a specific vehicle. This request can be submitted to the insurance system through online platforms or offline channels. It triggers the insurance pricing process, prompting the system to collect relevant data and calculate pricing. For example, a car owner clicking the "Get Scratch Insurance Quote" button on a mobile app generates an insurance pricing request, which initiates the pricing process.

[0035] The permanent location refers to the geographic area where the target vehicle is primarily parked or frequently moves during daily use. This information is derived from vehicle usage records, information provided by the owner, or relevant positioning data. It represents the vehicle's long-term geographic environment and is used to assess the impact of factors such as public security and climate at that location on vehicle risk.

[0036] Public security data refers to information about the public security situation at the target vehicle's permanent location. It characterizes the safety and security risk level of the location. This data is used to calculate a public security score using an environmental scoring model, thereby assessing the impact of that location on vehicle scratch risk. For example, data such as theft rates and patrol frequency in a particular area are examples of public security data, which can reflect the public security situation in that area.

[0037] Step S202: Based on the public security data, a preset environment scoring model is used to perform public security scoring to obtain a public security environment score for the permanent location.

[0038] The environmental scoring model is a mathematical formula used to calculate a location-specific public security score based on public security data. It stems from the analysis and research of the relationship between extensive public security data and vehicle scratch risk. It describes a method for converting public security data into a quantitative score. This model is used to convert public security data into an intuitive public security environment score, allowing the impact of public security factors to be factored into auto insurance pricing.

[0039] The public security environment score, also known as the public security score, is a comprehensive quantitative assessment of the public security situation at the target vehicle's location. It is derived from the output of the environmental scoring model and represents the public security risk level of the location. For example, when pricing auto insurance, a higher public security environment score can indicate a lower risk of a vehicle being scratched in that location.

[0040] Step S203 , obtaining climate data of the permanent location, and based on the climate data, using a preset logistic regression model to perform climate risk prediction to obtain a climate risk index of the target vehicle.

[0041] Climate data is information about the climatic conditions at the target vehicle's permanent location, such as temperature, humidity, precipitation, and wind speed. It characterizes the climate characteristics and changing patterns at that location. This data is used to predict climate risk using a logistic regression model and assess the impact of climate factors on vehicle scratch risk.

[0042] The logistic regression model, derived from statistical analysis and modeling of the relationship between climate factors and vehicle scratch risk, represents a method for converting climate data into quantitative indicators of climate risk. This model is used to predict the likelihood of vehicle scratch risk under different climate conditions.

[0043] The Climate Risk Index is a quantitative representation of climate risk prediction, reflecting the risk of scratches on a target vehicle due to climate factors. It is derived from the output of a logistic regression model and represents the degree of climate risk, with higher values indicating greater risk.

[0044] Step S204 , obtaining vehicle data of the target vehicle, and performing a vehicle risk score based on the vehicle data using a preset vehicle risk scoring model to obtain a vehicle risk index of the target vehicle.

[0045] Among them, vehicle data refers to a collection of various types of information related to the target vehicle's own characteristics, usage status, etc. It characterizes the characteristics and behavior patterns of the target vehicle in different dimensions, covering vehicle routes, vehicle brands, vehicle uses (such as family cars, operating vehicles, transport vehicles, property insurance reception vehicles), vehicle types (new energy, fuel) and other aspects. Among them, the vehicle risk scoring model is a formula built based on a mathematical algorithm, which is used to quantitatively evaluate the degree of scratch risk faced by the target vehicle based on vehicle data. It can be obtained by exploring the intrinsic correlation between the various characteristics of the vehicle and the scratch risk. It represents a method for converting vehicle data into risk quantification indicators, which can comprehensively consider the impact of multiple factors such as vehicle routes, brands, uses, and types on scratch risks.

[0046] Among them, the vehicle risk index is an indicator calculated based on the vehicle data of the target vehicle through a preset vehicle risk scoring model to quantify the degree of scratch risk faced by the target vehicle itself. It comes from specific data such as the target vehicle's driving route, vehicle brand, vehicle purpose (such as family car, operating vehicle, transport vehicle, property insurance reception vehicle), and vehicle type (new energy, fuel). It characterizes the size of the scratch risk inherent in the target vehicle due to its own characteristics and usage. For example, an operating vehicle that often travels in areas with complex road conditions and high traffic volume may obtain a higher vehicle risk index after calculation through the vehicle risk scoring model due to its high-risk driving route and high frequency of use, which means that the vehicle faces a greater risk of scratches.

[0047] Step S205 , based on the public security environment score, the climate risk index, and the vehicle risk index, a preset premium pricing model is used to perform insurance pricing to obtain vehicle insurance pricing information for the target vehicle.

[0048] The premium pricing model is a pre-set mathematical formula used to calculate the target vehicle's auto insurance premium based on multiple risk indicators, including the public security environment score, climate risk index, and vehicle risk index. It represents a calculation method that converts multiple risk factors into specific premium amounts.

[0049] Insurance pricing is the process of determining the insurance premium for a target vehicle based on various risk factors and a pre-set pricing model. It stems from a comprehensive analysis and assessment of risk information related to the target vehicle, including factors such as the public security environment, climate conditions, and the vehicle's characteristics.

[0050] Auto insurance pricing information is the specific data and related information about the target vehicle's auto insurance price, derived from the insurance pricing process. It's derived from the calculated output of the premium pricing model and includes detailed information such as the required premium, policy term, and coverage for the target vehicle.

[0051] When the embodiment of the present application detects the insurance pricing request of the target vehicle, it first obtains the public security data of its permanent location and performs a public security score based on a preset environmental scoring model. This can accurately quantify the impact of different public security environments on the risk of vehicle scratches, changing the ambiguity of traditional public security factors that rely solely on experience. Then, the climate data of the permanent location is obtained, and the climate risk prediction is performed using a preset logistic regression model. This can scientifically evaluate the scratch risks brought to the vehicle by different climate conditions, making up for the shortcomings of insufficient consideration of climate factors in traditional pricing. At the same time, the vehicle data of the target vehicle is obtained, and the vehicle risk score is performed using a preset vehicle risk scoring model to comprehensively consider the risks brought by the vehicle's own characteristics. Finally, the public security environment score, climate risk index and vehicle risk index are integrated, and insurance pricing is performed through a preset premium pricing model, achieving accurate auto insurance pricing for customers with different risk conditions, making pricing more scientific and reasonable.

[0052] In some optional implementations of this embodiment, step S202, based on the public security data, uses a preset environment scoring model to perform a public security scoring to obtain a public security environment score for the resident location, specifically including the following steps:

[0053] Using geographic information system technology, the geographic coordinates of the target vehicle's permanent location are extracted; based on the geographic coordinates and public security data, a public security spatial distribution map of the permanent location is created; feature extraction is performed on the public security data to obtain violation indicators, traffic safety indicators, and environmental brightness; based on the spatial distribution map, the public security weights of the violation indicators, traffic safety indicators, and environmental brightness are determined respectively; based on the violation indicators, traffic safety indicators, environmental brightness, and public security weights, a preset environmental scoring model is used to perform weighted summation to obtain the public security environment score of the permanent location.

[0054] The public security spatial distribution map is a visualization created based on the geographic coordinates of the target vehicle's permanent location and public security data. It depicts the spatial distribution of public security conditions around the target vehicle's permanent location, visually displaying differences in public security levels across regions through different colors, symbols, and patterns. It assists in determining the weights of public security-related indicators and provides a spatial dimension for public security environment scoring.

[0055] The Violation Index, extracted from public security data, is a quantitative indicator used to measure the frequency of illegal activities around the target vehicle's regular location. It characterizes the frequency and type of illegal activities in the area, reflecting the quality of public security. It serves as a key factor in the public security environment score, helping to assess the risk impact of a location on vehicles. For example, if an area experiences numerous violations such as fights and thefts within a month, the Violation Index extracted through data analysis will be high, indicating poor public security in the area.

[0056] The traffic safety index, extracted from public security data, is a quantitative indicator used to assess traffic safety conditions around the target vehicle's permanent location. It characterizes the incidence of traffic accidents and compliance with traffic rules in the area, reflecting the safety of the traffic environment. It is used to comprehensively consider the impact of traffic factors on vehicle risk in the public security environment score. For example, if a road section frequently experiences traffic congestion, red light running, and other violations, leading to frequent traffic accidents, the corresponding traffic safety index value will be low, indicating an unsafe traffic environment.

[0057] Among them, ambient brightness is extracted from public security data and is used as a quantitative indicator to describe the nighttime lighting conditions around the target vehicle's permanent location. It is derived from an analysis of information such as lighting facilities and nighttime light intensity in public security data. It represents the brightness level of the area at night. The higher the ambient brightness, the better the nighttime visibility, which can reduce the possibility of vehicle risks to a certain extent. It is used to consider the impact of lighting factors on vehicle safety in the public security environment scoring. For example, if a residential area has a sufficient number of high-brightness streetlights and a bright nighttime environment, the ambient brightness index value will be high, indicating that it is relatively safe for vehicles to park in this area at night.

[0058] The public security weighting is based on the public security spatial distribution map and determines the importance of each indicator, including the illegal behavior indicator, traffic safety indicator, and ambient brightness, in the public security environment score. This weighting is derived from an analysis and assessment of the correlation between each indicator and the public security situation. It is used to appropriately distribute the influence of each indicator when calculating the public security environment score using a weighted summation. For example, if illegal behavior in a particular area has the most significant impact on public security, the illegal behavior indicator will have a higher public security weight, playing a greater role in the score calculation.

[0059] Among them, weighted summation is a mathematical calculation method. It is based on violation indicators, traffic safety indicators, environmental brightness and corresponding public security weights, and is calculated according to certain rules to obtain the public security environment score of the permanent location.

[0060] In one example, when an insurance pricing request is detected for a target vehicle, public security data for the vehicle's permanent location is first obtained. Simultaneously, geographic information system technology is used to extract the geographic coordinates of the target vehicle's permanent location. Based on the acquired geographic coordinates and public security data, a public security spatial distribution map for the permanent location is created. This public security spatial distribution map visually displays the public security conditions in different areas, providing a foundation for subsequent feature extraction and weighting. In-depth analysis of the public security data extracts three key features: violation indicators (e.g., crime rate C), traffic safety indicators (e.g., traffic accident frequency T), and ambient brightness (e.g., nighttime lighting conditions L). These features comprehensively reflect the public security risk at the target vehicle's permanent location. Based on the public security spatial distribution map, combined with historical data and expert judgment, the public security weights α for the violation indicator, β for the traffic safety indicator, and γ for the ambient brightness are determined. These weights reflect the contribution of different public security factors to the public security environment score. According to the preset environmental scoring model S=αC+βT+γL, the illegal behavior index, traffic safety index, environmental brightness and the corresponding public security weight are weighted and summed to obtain the public security environment score of the permanent location.

[0061] The embodiment of the present application can extract the geographic coordinates of the permanent location of the target vehicle by using geographic information system technology, and create a public security spatial distribution map in combination with public security data, thereby realizing an intuitive visual analysis of the public security environment at the permanent location of the vehicle. Furthermore, feature extraction is performed on the public security data to obtain illegal behavior indicators, traffic safety indicators and environmental brightness, which can comprehensively and meticulously characterize the public security risk situation at the location. The public security weights of each indicator are determined based on the public security spatial distribution map, ensuring the rationality and scientific nature of the weight distribution, and fully considering the spatial distribution differences of different public security factors and their influence on the public security environment score. Finally, a preset environmental scoring model is used for weighted summation to obtain the public security environment score of the permanent location. The score comprehensively reflects the public security risk level of the permanent location of the target vehicle, and provides an important reference basis for auto insurance pricing. This public security environment scoring method based on geographic information system and public security data overcomes the limitations and subjectivity of traditional pricing methods and improves the accuracy and rationality of auto insurance pricing.

[0062] In some optional implementations of this embodiment, the step of "using geographic information system technology to extract the geographic coordinates of the permanent location of the target vehicle; and creating a public security spatial distribution map of the permanent location based on the geographic coordinates and public security data" specifically includes the following steps:

[0063] The target vehicle's historical location information is obtained from the target vehicle's onboard positioning system; based on the location information, the geographic information system technology is used to determine the target vehicle's permanent location and the geographic coordinates of the permanent location; based on the public security data and geographic coordinates, a preset mapping software is used to draw a map to obtain a public security spatial distribution map of the permanent location.

[0064] In one example, when a target vehicle's insurance pricing request is detected, the system first retrieves its historical location information from its onboard positioning system. This information records the vehicle's travel trajectory and locations over a period of time and serves as the foundation for determining its permanent location. Geographic Information System (GIS) technology is then used to analyze and process this historical location information. By calculating the vehicle's dwell time and frequency at various locations, the target vehicle's permanent location is determined. GIS technology is also used to extract the geographic coordinates of this permanent location, providing accurate spatial positioning for the subsequent creation of a public security spatial distribution map. After obtaining the geographic coordinates of the target vehicle's permanent location, the map is created using pre-configured mapping software, combined with public security data for that location. Public security data includes crime rates, traffic accident frequency, nighttime lighting conditions, and other data that can reflect the public security situation in the area. Using the mapping software, this public security data is combined with the geographic coordinates to generate a visual public security spatial distribution map.

[0065] The embodiment of the present application can obtain the historical location information of the target vehicle from the on-board positioning system of the target vehicle, and use geographic information system technology to determine the permanent location and geographic coordinates of the target vehicle based on this information, thereby achieving an accurate portrayal of the vehicle's usage environment and risk status. Furthermore, in combination with public security data and geographic coordinates, a public security spatial distribution map of the permanent location is drawn using a preset map drawing software. This distribution map can intuitively display the public security situation in the area surrounding the target vehicle. Through the public security spatial distribution map, insurance companies can have a more comprehensive understanding of the risk status of the target vehicle, providing strong support for subsequent accurate insurance pricing based on the public security environment score, climate risk index, and vehicle risk index, helping to improve the accuracy and rationality of auto insurance pricing and reduce the insurance company's compensation risk.

[0066] In some optional implementations of this embodiment, step S203, based on the climate data, uses a preset logistic regression model to perform climate risk prediction to obtain a climate risk index for the target vehicle, specifically including the following steps:

[0067] The preset principal component analysis is used to extract key climate factors from the climate data. Based on the key climate factors, the preset logistic regression model is used to predict climate risk and obtain the climate risk index of the target vehicle.

[0068] Among them, principal component analysis is used to extract a few key climate factors from multidimensional climate data. These factors can characterize the main characteristics of climate data, while reducing the dimension of the data and simplifying the subsequent analysis process.

[0069] Key climate factors are the main climate characteristics that can significantly impact the climate risk of a target vehicle, extracted from raw climate data through methods such as principal component analysis. These factors are a comprehensive reflection of the raw climate data, characterizing the climate conditions in the area where the vehicle is used and used to predict the vehicle's risk level under different climate conditions.

[0070] In one example, climate data can be collected for the area where the target vehicle is used, including key indicators such as temperature, humidity, precipitation, and wind speed. This data can come from historical records of meteorological departments or real-time monitoring systems. Principal component analysis is used to reduce the dimensionality of the collected climate data. By calculating the covariance matrix of the climate data, key climate factors that characterize the main characteristics of the original data are extracted. For example, principal component analysis can produce factors such as "high temperature and high humidity factors" and "strong wind and precipitation factors," which comprehensively reflect the climate conditions in the area where the vehicle is used. Based on the extracted key climate factors, a logistic regression model is constructed to predict climate risk. The logistic regression model uses training sample data to learn the relationship between climate factors and vehicle climate risk, thereby predicting the climate risk index of the target vehicle. The goal of model training is to minimize the cross-entropy loss to ensure the accuracy of the prediction results.

[0071] The embodiment of the present application can extract key climate factors from climate data by using a preset principal component analysis, and combine it with a logistic regression model to perform climate risk prediction, thereby achieving an accurate quantitative assessment of the climate risk of the target vehicle. Principal component analysis, as an effective means of data dimensionality reduction, can integrate multi-dimensional information in climate data and extract key climate factors such as "high temperature and high humidity factors" and "frequent occurrence of extreme weather factors". These factors not only characterize the main characteristics of climate data, but also reduce the complexity of subsequent analysis. Subsequently, these key climate factors are modeled and analyzed using a logistic regression model, which can accurately predict the risk level of the target vehicle under different climatic conditions and obtain a climate risk index. This technical process overcomes the subjectivity and one-sidedness of climate risk assessment in traditional pricing methods, making auto insurance pricing more scientific and objective. Through the introduction of the climate risk index, the risk status of the target vehicle can be more comprehensively understood, which provides strong support for the formulation of personalized auto insurance pricing strategies and helps to improve the accuracy and rationality of auto insurance pricing.

[0072] In some optional implementations of this embodiment, step S204, performing a vehicle risk score based on the vehicle data using a preset vehicle risk scoring model to obtain a vehicle risk index for the target vehicle, specifically includes the following steps:

[0073] Feature extraction is performed on vehicle data to obtain the vehicle type code, energy level, average mileage and vehicle value information of the target vehicle; based on the vehicle type code, energy level, average mileage and vehicle value information, a preset vehicle risk scoring model is used to predict vehicle risk and obtain the vehicle risk index of the target vehicle.

[0074] In one example, detailed data on a target vehicle can be collected, including information such as vehicle type, brand, purpose, energy rating, mileage history, and vehicle value. Feature extraction is performed on the collected vehicle data to obtain key features such as vehicle type code (t), energy rating (ev), average mileage (pa), and vehicle value (r). The vehicle type code categorizes the vehicle by its purpose (e.g., family car, commercial vehicle, or transport vehicle). Vehicles with different purposes face different risks. The energy rating reflects the vehicle's energy type (e.g., new energy, fuel-powered). Vehicles with different energy types differ in operating costs, maintenance costs, and risks. Average mileage is calculated from historical driving data and reflects vehicle usage frequency and driving habits. Vehicle value is assessed based on factors such as purchase price and depreciation. A vehicle risk scoring model is constructed based on the extracted vehicle features. This model uses statistical methods such as linear regression or logistic regression, combined with historical claims data, to learn the relationship between vehicle features and risk. Based on the key features of the target vehicle, the vehicle risk scoring model calculates a vehicle risk index. The index takes into account factors such as vehicle type, energy level, mileage and value, and can comprehensively reflect the risk status of the vehicle.

[0075] The embodiment of the present application can extract features from the target vehicle data to obtain vehicle type codes, energy levels, average mileage, and vehicle value information, and perform risk prediction in combination with a preset vehicle risk scoring model, thereby achieving an accurate quantitative assessment of the target vehicle's risk. The vehicle type code reflects the nature of vehicle use and potential risk differences, the energy level reflects the vehicle's power source and corresponding risk characteristics, the average mileage reveals the vehicle's frequency of use and degree of wear and tear, and the vehicle value is directly related to the size of the potential loss. The comprehensive consideration of these features enables the vehicle risk scoring model to more comprehensively capture multi-dimensional information on vehicle risks. Through the application of this model, insurance companies can accurately predict the vehicle risk index of the target vehicle and provide a scientific basis for auto insurance pricing. This technical process overcomes the subjectivity and one-sidedness of vehicle risk assessment in traditional pricing methods, improves the accuracy and rationality of auto insurance pricing, and helps insurance companies achieve personalized pricing.

[0076] In some optional implementations of this embodiment, the step of "predicting vehicle risk using a preset vehicle risk scoring model based on the vehicle type code, energy level, average mileage, and vehicle value information to obtain a vehicle risk index for the target vehicle" specifically includes the following steps:

[0077] The factor weights corresponding to the vehicle type code, energy level, average mileage and vehicle value information are obtained respectively; based on the vehicle type code, energy level, average mileage, vehicle value information and factor weights, a vehicle risk scoring model is used for weighted summation to obtain the vehicle risk index of the target vehicle.

[0078] In one example, the factor weights corresponding to key features such as vehicle type code t, energy level ev, average mileage pa, and vehicle value r can be obtained respectively. That is, the factor weight β1 corresponding to vehicle type code t, the factor weight β2 corresponding to energy level ev, the factor weight β3 corresponding to average mileage pa, and the factor weight β4 corresponding to vehicle value r are obtained. Furthermore, the intercept term β0 and the random error term ∈ of the preset model can be obtained, which represent random fluctuations that cannot be explained by the model. Based on the data given in this example, the vehicle risk scoring model RT = β0 + β1t + β2ev + β3pa + β4r + ∈ is used to perform a weighted summation of the vehicle type code, energy level, average mileage, vehicle value information, the weights of each factor, the intercept term β0, and the random error term ∈ to calculate the vehicle risk index of the target vehicle.

[0079] The embodiment of the present application can achieve an accurate quantitative assessment of the target vehicle risk by respectively obtaining the factor weights corresponding to the vehicle type code, energy level, average mileage and vehicle value information, and using the vehicle risk scoring model to perform weighted summation based on these weights. In this process, the introduction of factor weights enables the vehicle risk scoring model to perform differentiated processing according to the degree of influence of different characteristics on vehicle risk, thereby more accurately reflecting the actual risk status of the vehicle. For example, the vehicle type code may have different risk weights due to different uses (such as home and commercial), and the energy level may be assigned different weight values due to the difference between new energy vehicles and traditional fuel vehicles. Average mileage and vehicle value information also play an important role in the calculation of the vehicle risk index through their corresponding weights. This weighted summation method not only takes into account the diversity of vehicle characteristics, but also achieves a refined assessment of vehicle risk through weight adjustment.

[0080] In some optional implementations of this embodiment, step S205, based on the public security environment score, the climate risk index, and the vehicle risk index, uses a preset premium pricing model to perform insurance pricing to obtain vehicle insurance pricing information for the target vehicle, specifically including the following steps:

[0081] Based on the public security environment score, climate risk index and vehicle risk index, the basic premium information of the target vehicle is determined; the feature weights corresponding to the public security environment score, climate risk index and vehicle risk index are obtained respectively; based on the basic premium information, public security environment score, climate risk index, vehicle risk index and feature weights, a preset premium pricing model is used to perform weighted summation to obtain the target vehicle's auto insurance pricing information.

[0082] In one example, when an insurance pricing request is detected for a target vehicle, public security data, climate data, and vehicle data for the vehicle's permanent location are first obtained. Based on the public security data, a public security score is generated using a preset environmental scoring model to obtain a public security environment score RS. Based on the climate data, a preset logistic regression model is used to predict climate risk to obtain a climate risk index R. Based on the vehicle data, a vehicle risk score is generated using a preset vehicle risk scoring model to obtain a vehicle risk index RT. Combining the public security environment score RS, the climate risk index R, and the vehicle risk index RT, a preset algorithm is used to determine the target vehicle's basic premium information P. risk. For example, for vehicles with poor security environment, high climate risk and large vehicle risk index, their basic premium will increase accordingly. Obtain the feature weights γ1, γ2, and γ3 corresponding to the security environment score RS, climate risk index R, and vehicle risk index RT respectively. These weights can be determined through historical data analysis, expert evaluation or machine learning algorithms to reflect the degree of influence of each factor on auto insurance pricing. Based on the basic premium information Prisk, security environment score RS, climate risk index R, vehicle risk index RT and feature weights γ1, γ2, and γ3, the preset premium pricing model P=P risk +γ1*RS+γ2*R+γ3*RT, perform weighted summation, and calculate the insurance pricing information P of the target vehicle.

[0083] The embodiment of the present application can determine the basic premium information of the target vehicle through the public security environment score, climate risk index and vehicle risk index, and further combine the feature weights corresponding to each factor, and use the preset premium pricing model for weighted summation, thereby achieving accurate and personalized auto insurance pricing. The public security environment score reflects the safety status of the vehicle's permanent location, the climate risk index reflects the impact of climate factors on the probability of vehicle accidents, and the vehicle risk index comprehensively considers the risk characteristics of the vehicle itself. Information from these three dimensions together constitutes the basis for auto insurance pricing, ensuring the comprehensiveness and accuracy of pricing. The introduction of feature weights allows the degree of influence of each factor in pricing to be quantified, further improving the level of refinement in pricing. Through the weighted summation method, premium pricing can be flexibly adjusted according to the risk status of different vehicles, which not only meets the personalized needs of customers, but also effectively reduces the compensation pressure of property and casualty insurance companies, laying a solid foundation for the sustainable development of auto insurance business.

[0084] It should be emphasized that in order to further ensure the above-mentioned public security data, climate data, vehicle data, and auto insurance pricing information, the above-mentioned public security data, climate data, vehicle data, and auto insurance pricing information can also be stored in a node of a blockchain.

[0085] The blockchain referred to in this application is a new application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks generated using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of this information (to prevent counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer.

[0086] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing related hardware via computer-readable instructions. The computer-readable instructions can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes in the above-described method embodiments. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0087] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0088] Further references Figure 3 , as a response to the above Figure 2 The present application provides an embodiment of a device for determining vehicle insurance pricing information. Figure 2 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0089] like Figure 3 As shown, the apparatus 400 for determining automobile insurance pricing information in this embodiment includes: an acquisition module 401, an environment scoring module 402, a prediction module 403, a risk scoring module 404, and a pricing module 405. Among them:

[0090] An acquisition module 401 is configured to acquire the security data of the permanent location of the target vehicle when an insurance pricing request of the target vehicle is detected;

[0091] An environment scoring module 402 is configured to perform a public security score based on public security data using a preset environment scoring model to obtain a public security environment score for the resident location;

[0092] The prediction module 403 is used to obtain climate data of the permanent location, and based on the climate data, use a preset logistic regression model to perform climate risk prediction to obtain a climate risk index of the target vehicle;

[0093] The risk scoring module 404 is used to obtain vehicle data of the target vehicle, and perform a vehicle risk score based on the vehicle data using a preset vehicle risk scoring model to obtain a vehicle risk index of the target vehicle;

[0094] The pricing module 405 is used to perform insurance pricing based on the public security environment score, the climate risk index, and the vehicle risk index using a preset premium pricing model to obtain vehicle insurance pricing information for the target vehicle.

[0095] When the embodiment of the present application detects the insurance pricing request of the target vehicle, it first obtains the public security data of its permanent location and performs a public security score based on a preset environmental scoring model. This can accurately quantify the impact of different public security environments on the risk of vehicle scratches, changing the ambiguity of traditional public security factors that rely solely on experience. Then, the climate data of the permanent location is obtained, and the climate risk prediction is performed using a preset logistic regression model. This can scientifically evaluate the scratch risks brought to the vehicle by different climate conditions, making up for the shortcomings of insufficient consideration of climate factors in traditional pricing. At the same time, the vehicle data of the target vehicle is obtained, and the vehicle risk score is performed using a preset vehicle risk scoring model to comprehensively consider the risks brought by the vehicle's own characteristics. Finally, the public security environment score, climate risk index and vehicle risk index are integrated, and insurance pricing is performed through a preset premium pricing model, achieving accurate auto insurance pricing for customers with different risk conditions, making pricing more scientific and reasonable.

[0096] In one embodiment, the environment scoring module 402 includes:

[0097] A coordinate extraction submodule is used to extract the geographic coordinates of the permanent location of the target vehicle using geographic information system technology;

[0098] Create a submodule for creating a spatial distribution map of public security at a permanent location based on geographic coordinates and public security data;

[0099] The first feature extraction submodule is used to extract features from public security data to obtain illegal behavior indicators, traffic safety indicators, and environmental brightness;

[0100] The weight determination submodule is used to determine the public security weights of illegal behavior indicators, traffic safety indicators, and environmental brightness based on the spatial distribution map;

[0101] The first weighted summation submodule is used to perform weighted summation based on the violation index, traffic safety index, environmental brightness and public security weight using a preset environmental scoring model to obtain a public security environment score for the permanent location.

[0102] The embodiment of the present application can extract the geographic coordinates of the permanent location of the target vehicle by using geographic information system technology, and create a public security spatial distribution map in combination with public security data, thereby realizing an intuitive visual analysis of the public security environment at the permanent location of the vehicle. Furthermore, feature extraction is performed on the public security data to obtain illegal behavior indicators, traffic safety indicators and environmental brightness, which can comprehensively and meticulously characterize the public security risk situation at the location. The public security weights of each indicator are determined based on the public security spatial distribution map, ensuring the rationality and scientific nature of the weight distribution, and fully considering the spatial distribution differences of different public security factors and their influence on the public security environment score. Finally, a preset environmental scoring model is used for weighted summation to obtain the public security environment score of the permanent location. The score comprehensively reflects the public security risk level of the permanent location of the target vehicle, and provides an important reference basis for auto insurance pricing. This public security environment scoring method based on geographic information system and public security data overcomes the limitations and subjectivity of traditional pricing methods and improves the accuracy and rationality of auto insurance pricing.

[0103] In one embodiment, the coordinate extraction submodule is further used to obtain the target vehicle's historical location information from the target vehicle's onboard positioning system; based on the location information, the target vehicle's permanent location and the geographic coordinates of the permanent location are determined using geographic information system technology.

[0104] The embodiment of the present application can obtain the historical location information of the target vehicle from the on-board positioning system of the target vehicle, and use geographic information system technology based on this information to determine the permanent location and geographic coordinates of the target vehicle, thereby achieving an accurate portrayal of the vehicle's usage environment and risk status.

[0105] In one embodiment, the creation submodule is further used to draw a map based on the public security data and geographic coordinates using a preset map drawing software to obtain a public security spatial distribution map of the permanent location.

[0106] In this embodiment, by combining public security data and geographic coordinates, and utilizing pre-set mapping software, a public security spatial distribution map of a permanent location can be created. This map can visually demonstrate the public security situation in the area surrounding the target vehicle. This spatial distribution map provides insurance companies with a more comprehensive understanding of the risk profile of the target vehicle, providing strong support for subsequent precise insurance pricing based on public security environment scores, climate risk indices, and vehicle risk indices. This helps improve the accuracy and rationality of auto insurance pricing and reduces insurance companies' claims risks.

[0107] In one embodiment, the prediction module 403 includes:

[0108] The climate factor extraction submodule is used to extract key climate factors from climate data using a preset principal component analysis;

[0109] The first prediction submodule is used to perform climate risk prediction based on key climate factors using a preset logistic regression model to obtain a climate risk index for the target vehicle.

[0110] The embodiment of the present application can extract key climate factors from climate data by using a preset principal component analysis, and combine it with a logistic regression model to perform climate risk prediction, thereby achieving an accurate quantitative assessment of the climate risk of the target vehicle. Principal component analysis, as an effective means of data dimensionality reduction, can integrate multi-dimensional information in climate data and extract key climate factors such as "high temperature and high humidity factors" and "frequent occurrence of extreme weather factors". These factors not only characterize the main characteristics of climate data, but also reduce the complexity of subsequent analysis. Subsequently, these key climate factors are modeled and analyzed using a logistic regression model, which can accurately predict the risk level of the target vehicle under different climatic conditions and obtain a climate risk index. This technical process overcomes the subjectivity and one-sidedness of climate risk assessment in traditional pricing methods, making auto insurance pricing more scientific and objective. Through the introduction of the climate risk index, the risk status of the target vehicle can be more comprehensively understood, which provides strong support for the formulation of personalized auto insurance pricing strategies and helps to improve the accuracy and rationality of auto insurance pricing.

[0111] In one embodiment, the risk scoring module 404 includes:

[0112] The second feature extraction submodule is used to extract features from vehicle data to obtain the vehicle type code, energy level, average mileage and vehicle value information of the target vehicle;

[0113] The second prediction submodule is used to predict vehicle risk based on the vehicle type code, energy level, average mileage and vehicle value information using a preset vehicle risk scoring model to obtain the vehicle risk index of the target vehicle.

[0114] The embodiment of the present application can extract features from the target vehicle data to obtain vehicle type codes, energy levels, average mileage, and vehicle value information, and perform risk prediction in combination with a preset vehicle risk scoring model, thereby achieving an accurate quantitative assessment of the target vehicle's risk. The vehicle type code reflects the nature of vehicle use and potential risk differences, the energy level reflects the vehicle's power source and corresponding risk characteristics, the average mileage reveals the vehicle's frequency of use and degree of wear and tear, and the vehicle value is directly related to the size of the potential loss. The comprehensive consideration of these features enables the vehicle risk scoring model to more comprehensively capture multi-dimensional information on vehicle risks. Through the application of this model, insurance companies can accurately predict the vehicle risk index of the target vehicle and provide a scientific basis for auto insurance pricing. This technical process overcomes the subjectivity and one-sidedness of vehicle risk assessment in traditional pricing methods, improves the accuracy and rationality of auto insurance pricing, and helps insurance companies achieve personalized pricing.

[0115] In one embodiment, the second prediction submodule is further used to obtain the factor weights corresponding to the vehicle type code, energy level, average mileage and vehicle value information respectively; based on the vehicle type code, energy level, average mileage, vehicle value information and factor weights, a vehicle risk scoring model is used to perform weighted summation to obtain the vehicle risk index of the target vehicle.

[0116] The embodiment of the present application can achieve an accurate quantitative assessment of the target vehicle risk by respectively obtaining the factor weights corresponding to the vehicle type code, energy level, average mileage and vehicle value information, and using the vehicle risk scoring model to perform weighted summation based on these weights. In this process, the introduction of factor weights enables the vehicle risk scoring model to perform differentiated processing according to the degree of influence of different characteristics on vehicle risk, thereby more accurately reflecting the actual risk status of the vehicle. For example, the vehicle type code may have different risk weights due to different uses (such as home and commercial), and the energy level may be assigned different weight values due to the difference between new energy vehicles and traditional fuel vehicles. Average mileage and vehicle value information also play an important role in the calculation of the vehicle risk index through their corresponding weights. This weighted summation method not only takes into account the diversity of vehicle characteristics, but also achieves a refined assessment of vehicle risk through weight adjustment.

[0117] In one embodiment, the pricing module 405 includes:

[0118] An information determination submodule is used to determine the basic premium information of the target vehicle based on the public security environment score, climate risk index, and vehicle risk index;

[0119] The acquisition submodule is used to obtain the feature weights corresponding to the public security environment score, climate risk index, and vehicle risk index respectively;

[0120] The second weighted summation submodule is used to perform weighted summation based on basic premium information, public security environment score, climate risk index, vehicle risk index and feature weight using a preset premium pricing model to obtain the target vehicle's auto insurance pricing information.

[0121] The embodiment of the present application can determine the basic premium information of the target vehicle through the public security environment score, climate risk index and vehicle risk index, and further combine the feature weights corresponding to each factor, and use the preset premium pricing model for weighted summation, thereby achieving accurate and personalized auto insurance pricing. The public security environment score reflects the safety status of the vehicle's permanent location, the climate risk index reflects the impact of climate factors on the probability of vehicle accidents, and the vehicle risk index comprehensively considers the risk characteristics of the vehicle itself. Information from these three dimensions together constitutes the basis for auto insurance pricing, ensuring the comprehensiveness and accuracy of pricing. The introduction of feature weights allows the degree of influence of each factor in pricing to be quantified, further improving the level of refinement in pricing. Through the weighted summation method, premium pricing can be flexibly adjusted according to the risk status of different vehicles, which not only meets the personalized needs of customers, but also effectively reduces the compensation pressure of property and casualty insurance companies, laying a solid foundation for the sustainable development of auto insurance business.

[0122] To solve the above technical problems, the present application also provides a computer device. Figure 4 , Figure 4 This is a basic structural block diagram of the computer device in this embodiment.

[0123] The computer device 6 includes a memory 61, a processor 62, and a network interface 63 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 6 with a memory 61, a processor 62, and a network interface 63, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to a microprocessor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0124] Computer devices can be desktop computers, laptops, PDAs, cloud servers, etc. Computer devices can interact with users through keyboards, mice, remote controls, touchpads, or voice control devices.

[0125] Memory 61 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic storage, magnetic disk, optical disk, etc. In some embodiments, memory 61 may be an internal storage unit of computer device 6, such as the hard disk or memory of computer device 6. In other embodiments, memory 61 may also be an external storage device of computer device 6, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on computer device 6. Of course, memory 61 may also include both internal storage units and external storage devices of computer device 6. In this embodiment, memory 61 is generally used to store the operating system and various application software installed on computer device 6, such as computer-readable instructions for the method for determining auto insurance pricing information. In addition, memory 61 may also be used to temporarily store various types of data that have been output or are about to be output.

[0126] In some embodiments, processor 62 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. Processor 62 is generally used to control the overall operation of computer device 6. In this embodiment, processor 62 is used to execute computer-readable instructions stored in memory 61 or process data, such as computer-readable instructions for executing a method for determining auto insurance pricing information.

[0127] The network interface 63 may include a wireless network interface or a wired network interface. The network interface 63 is generally used to establish a communication connection between the computer device 6 and other electronic devices.

[0128] When the embodiment of the present application detects the insurance pricing request of the target vehicle, it first obtains the public security data of its permanent location and performs a public security score based on a preset environmental scoring model. This can accurately quantify the impact of different public security environments on the risk of vehicle scratches, changing the ambiguity of traditional public security factors that rely solely on experience. Then, the climate data of the permanent location is obtained, and the climate risk prediction is performed using a preset logistic regression model. This can scientifically evaluate the scratch risks brought to the vehicle by different climate conditions, making up for the shortcomings of insufficient consideration of climate factors in traditional pricing. At the same time, the vehicle data of the target vehicle is obtained, and the vehicle risk score is performed using a preset vehicle risk scoring model to comprehensively consider the risks brought by the vehicle's own characteristics. Finally, the public security environment score, climate risk index and vehicle risk index are integrated, and insurance pricing is performed through a preset premium pricing model, achieving accurate auto insurance pricing for customers with different risk conditions, making pricing more scientific and reasonable.

[0129] The present application also provides another embodiment, namely, providing a computer-readable storage medium, which stores computer-readable instructions. The computer-readable instructions can be executed by at least one processor to enable the at least one processor to perform the steps of the method for determining the vehicle insurance pricing information as described above.

[0130] When the embodiment of the present application detects the insurance pricing request of the target vehicle, it first obtains the public security data of its permanent location and performs a public security score based on a preset environmental scoring model. This can accurately quantify the impact of different public security environments on the risk of vehicle scratches, changing the ambiguity of traditional public security factors that rely solely on experience. Then, the climate data of the permanent location is obtained, and the climate risk prediction is performed using a preset logistic regression model. This can scientifically evaluate the scratch risks brought to the vehicle by different climate conditions, making up for the shortcomings of insufficient consideration of climate factors in traditional pricing. At the same time, the vehicle data of the target vehicle is obtained, and the vehicle risk score is performed using a preset vehicle risk scoring model to comprehensively consider the risks brought by the vehicle's own characteristics. Finally, the public security environment score, climate risk index and vehicle risk index are integrated, and insurance pricing is performed through a preset premium pricing model, achieving accurate auto insurance pricing for customers with different risk conditions, making pricing more scientific and reasonable.

[0131] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods of each embodiment of the present application.

[0132] Obviously, the embodiments described above are only some of the embodiments of the present application, rather than all of the embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application has been described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific embodiments, or to make equivalent replacements for some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is also within the scope of patent protection of this application. The non-company enterprise software tools or components that appear in the embodiments of this application are merely examples and do not represent actual use.

Claims

1. A method for determining automobile insurance pricing information, characterized in that: The steps include: When an insurance pricing request of a target vehicle is detected, obtaining public security data of a permanent location of the target vehicle; Based on the public security data, a preset environment scoring model is used to perform a public security score to obtain a public security environment score for the permanent location; Acquiring climate data of the permanent location, and performing climate risk prediction based on the climate data using a preset logistic regression model to obtain a climate risk index for the target vehicle; Acquiring vehicle data of the target vehicle, and performing a vehicle risk score using a preset vehicle risk scoring model based on the vehicle data to obtain a vehicle risk index of the target vehicle; Based on the public security environment score, the climate risk index, and the vehicle risk index, a preset premium pricing model is used to perform insurance pricing to obtain vehicle insurance pricing information for the target vehicle.

2. The method according to claim 1, characterized in that The step of performing a public security score based on the public security data using a preset environment scoring model to obtain a public security environment score for the permanent location specifically includes: Using geographic information system technology, extracting the geographic coordinates of the permanent location of the target vehicle; Creating a public security spatial distribution map of the permanent location based on the geographic coordinates and the public security data; Extracting features from the public security data to obtain illegal behavior indicators, traffic safety indicators, and environmental brightness; Based on the spatial distribution map, respectively determining the public security weights of the illegal behavior index, the traffic safety index, and the environmental brightness; Based on the illegal behavior index, the traffic safety index, the environmental brightness and the public security weight, a preset environmental scoring model is used to perform weighted summation to obtain a public security environment score for the permanent location.

3. The method according to claim 2, characterized in that The step of extracting the geographic coordinates of the permanent location of the target vehicle using geographic information system technology specifically includes: Obtaining historical location information of the target vehicle from the vehicle-mounted positioning system of the target vehicle; Based on the location information, using geographic information system technology, determine the permanent location of the target vehicle and the geographic coordinates of the permanent location; The step of creating a public security spatial distribution map of the permanent location based on the geographic coordinates and the public security data specifically includes: Based on the public security data and the geographic coordinates, a map is drawn using a preset map drawing software to obtain a public security spatial distribution map of the permanent location.

4. The method according to claim 1, wherein The step of performing climate risk prediction based on the climate data using a preset logistic regression model to obtain the climate risk index of the target vehicle specifically includes: Using a preset principal component analysis, key climate factors are extracted from the climate data; Based on the key climate factors, a preset logistic regression model is used to perform climate risk prediction to obtain a climate risk index for the target vehicle.

5. The method according to claim 1, wherein The step of performing vehicle risk scoring based on the vehicle data using a preset vehicle risk scoring model to obtain a vehicle risk index of the target vehicle specifically includes: Extracting features from the vehicle data to obtain the vehicle type code, energy level, average mileage, and vehicle value information of the target vehicle; Based on the vehicle type code, the energy level, the average mileage and the vehicle value information, a preset vehicle risk scoring model is used to perform vehicle risk prediction to obtain a vehicle risk index of the target vehicle.

6. The method according to claim 5, characterized in that The step of performing vehicle risk prediction using a preset vehicle risk scoring model based on the vehicle type code, the energy level, the average mileage, and the vehicle value information to obtain a vehicle risk index of the target vehicle specifically includes: Respectively obtaining factor weights corresponding to the vehicle type code, the energy level, the average mileage, and the vehicle value information; Based on the vehicle type code, the energy level, the average mileage, the vehicle value information and the factor weights, the vehicle risk scoring model is used to perform weighted summation to obtain the vehicle risk index of the target vehicle.

7. The method according to claim 1, characterized in that The step of performing insurance pricing based on the public security environment score, the climate risk index, and the vehicle risk index using a preset premium pricing model to obtain the vehicle insurance pricing information of the target vehicle specifically includes: Determining basic insurance premium information for the target vehicle based on the public security environment score, the climate risk index, and the vehicle risk index; Obtaining feature weights corresponding to the public security environment score, the climate risk index, and the vehicle risk index respectively; Based on the basic premium information, the public security environment score, the climate risk index, the vehicle risk index and the feature weight, a preset premium pricing model is used to perform weighted summation to obtain the vehicle insurance pricing information of the target vehicle.

8. A device for determining automobile insurance pricing information, characterized in that: include: an acquisition module, configured to acquire the public security data of the permanent location of the target vehicle when an insurance pricing request of the target vehicle is detected; An environment scoring module, configured to perform a public security score based on the public security data using a preset environment scoring model to obtain a public security environment score for the permanent location; a prediction module, configured to obtain climate data of the permanent location, and perform climate risk prediction based on the climate data using a preset logistic regression model to obtain a climate risk index of the target vehicle; A risk scoring module is used to obtain vehicle data of the target vehicle, and perform a vehicle risk score based on the vehicle data using a preset vehicle risk scoring model to obtain a vehicle risk index of the target vehicle; The pricing module is used to perform insurance pricing based on the public security environment score, the climate risk index and the vehicle risk index using a preset premium pricing model to obtain vehicle insurance pricing information for the target vehicle.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and when the processor executes the computer-readable instructions, the method for determining the auto insurance pricing information according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the steps of the method for determining vehicle insurance pricing information according to any one of claims 1 to 7.

Images