New energy automobile intelligent insurance risk assessment platform based on artificial intelligence

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a new energy automobile intelligent insurance risk assessment platform based on artificial intelligence. The platform comprehensively collects multi-dimensional data related to the new energy automobile through the data collection module, the multi-dimensional data comprise the vehicle state, the driving behavior and the environmental factors, the data integrity and consistency are ensured in the data preprocessing stage, a foundation is laid for subsequent feature extraction, the feature extraction module extracts features highly related to risk assessment, and the risk assessment accuracy is improved. According to the method, the scientific property and the accuracy of an evaluation basis are ensured through the change of the driving habits, the vehicle health condition and the driving environment, the risk evaluation module deeply evaluates the insurance risk of the new energy vehicle through a regression analysis technology in combination with the extracted features, so that a comprehensive risk score is generated, and the method not only improves the evaluation accuracy, but also improves the safety of the new energy vehicle. And a more reasonable pricing model is provided for insurance companies, so that the risk management strategy can be optimized and the market competitiveness of enterprises can be improved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based smart insurance risk assessment platform for new energy vehicles. Background Art

[0002] With the rapid popularization of new energy vehicles and the continuous advancement of technology, the traditional automobile insurance model is facing unprecedented challenges. Due to their unique power systems, driving characteristics and usage environments, new energy vehicles are more complex in insurance risk assessment than traditional fuel vehicles. Insurance companies need to assess the risks of new energy vehicles in a more scientific and accurate way in order to reasonably price, reduce the claim rate, and improve user experience.

[0003] In the traditional automobile insurance model, due to the lack of evaluation standards and data support for the unique characteristics of new energy vehicles, insurance companies often find it difficult to accurately assess the insurance risks of new energy vehicles. This leads to irrational insurance pricing, which may cause high-risk users to be underestimated and low-risk users to be overestimated, thereby affecting the profitability and market competitiveness of insurance companies. Summary of the invention

[0004] 1. Technical issues to be resolved In view of the deficiencies in the prior art, the present invention provides an intelligent insurance risk assessment platform for new energy vehicles based on artificial intelligence. The data acquisition module comprehensively collects multidimensional data related to new energy vehicles, including vehicle status, driving behavior and environmental factors. The data preprocessing stage ensures the integrity and consistency of the data, laying the foundation for subsequent feature extraction. The feature extraction module extracts features that are highly relevant to risk assessment, such as driving habits, vehicle health status and changes in driving environment, to ensure the scientificity and accuracy of the assessment basis. The risk assessment module uses regression analysis technology combined with the extracted features to conduct an in-depth assessment of the insurance risk of new energy vehicles, thereby generating a comprehensive risk score. This method not only improves the accuracy of the assessment, but also provides insurance companies with a more reasonable pricing model, which helps to optimize risk management strategies and enhance corporate market competitiveness.

[0005] (II) Technical solution To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an artificial intelligence-based new energy vehicle intelligent insurance risk assessment platform, comprising a data acquisition module, a data preprocessing module, a feature extraction module, a risk assessment module and an assessment report visualization module; The data acquisition module is used to collect new energy vehicle related data, including vehicle data, driving behavior data, environmental data and accident technical data, and transmit the above collected data to the data preprocessing module; The data preprocessing module performs data deduplication, data integrity check, data labeling and data normalization operations on the new energy vehicle related data, and the processed data is transmitted to the feature extraction module; The feature extraction module performs feature extraction based on the preprocessed new energy vehicle related data, including extracting driving habit features, vehicle health features, and driving environment features; The risk assessment module performs new energy vehicle insurance risk assessment based on the features input by the feature extraction module through regression analysis, calculates the comprehensive risk score of automobile insurance, and generates a risk assessment report; The assessment report visualization module is used to visualize the risk assessment report in the form of charts.

[0006] Preferably, the formula for deduplication of data is as follows: ; In the formula, represents the original data set, represents the processed non-repetitive data set, Indicates the first records, , Indicates an index subscript.

[0007] Preferably, the formula for the data integrity check is as follows: ; In the formula, Indicates the number of complete records, Representation dataset The total number of records, Indicates the first records, Indicates an index subscript.

[0008] Preferably, the formula for data labeling is as follows: ; In the formula, represents the labeled dataset, Indicates the first records, express .

[0009] Preferably, the formula for data normalization is as follows: ; In the formula, represents the normalized data, Indicates the first records, represents the minimum value in the data set. Represents the maximum value in the data set.

[0010] Preferably, the formula for extracting driving habit features is as follows: ; In the formula, represents the driving habit characteristic value, Indicates the statistical time period. Indicates at time Recorded driving habits characteristics.

[0011] Preferably, the formula for extracting vehicle health characteristics is as follows: ; In the formula, represents the vehicle health characteristic value, Indicates engine health indicators, Indicates the battery health indicator, Indicates the health indicator of the suspension system. , , Represents the weight of each feature.

[0012] Preferably, the formula for extracting driving environment features is as follows: ; In the formula, represents the driving environment characteristic value, Indicates weather conditions, Indicates road conditions, Indicates driving time, Represents the environmental feature extraction formula.

[0013] Preferably, the calculation formula for the automobile insurance comprehensive risk score is as follows: ; In the formula, represents the comprehensive risk score of automobile insurance, , , represents the weight coefficient of the corresponding feature, Represents the bias term.

[0014] Preferably, the calculation formula of the weight coefficient is as follows: ; In the formula, Indicates The information entropy of the features, represents the number of features, represents the number of samples, represents the logarithmic function, Represents the normalized feature data.

[0015] Compared with the prior art, the present invention provides an intelligent insurance risk assessment platform for new energy vehicles based on artificial intelligence, which has the following beneficial effects: The present invention comprehensively collects multi-dimensional data related to new energy vehicles, including vehicle status, driving behavior and environmental factors, through the data acquisition module. The data preprocessing stage ensures the integrity and consistency of the data, laying the foundation for subsequent feature extraction. The feature extraction module extracts features that are highly relevant to risk assessment, such as driving habits, vehicle health status and changes in driving environment, ensuring the scientificity and accuracy of the assessment basis. The risk assessment module uses regression analysis technology combined with the extracted features to conduct an in-depth assessment of the insurance risk of new energy vehicles, thereby generating a comprehensive risk score. This method not only improves the accuracy of the assessment, but also provides insurance companies with a more reasonable pricing model, which helps to optimize risk management strategies and enhance corporate market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Due to the lack of evaluation standards and data support for the unique characteristics of new energy vehicles, insurance companies often find it difficult to accurately evaluate the insurance risks of new energy vehicles, which leads to irrational insurance pricing, which may cause high-risk users to be underestimated and low-risk users to be overestimated, thus affecting the profitability and market competitiveness of insurance companies. Therefore, an intelligent insurance risk assessment platform for new energy vehicles based on artificial intelligence is proposed. Please refer to Figure 1 ,The platform includes data acquisition module, data preprocessing module, feature extraction module, risk assessment module, and assessment report visualization module; The data collection module is the core component of the new energy vehicle intelligent insurance risk assessment platform. It aims to efficiently and accurately collect various data related to new energy vehicles through a variety of technical means. First, the module uses the Internet of Things (IoT) technology to monitor and collect vehicle data in real time through sensors and edge computing devices, including but not limited to basic vehicle information (such as model, brand, production year, vehicle identification code, etc.), battery status (such as battery power, charging status, health index), real-time driving data (such as speed, acceleration, mileage and driving time, etc.) and vehicle location data; In addition, the vehicle terminal system will record driving behavior data and analyze the driver's operating habits, including acceleration, braking frequency, steering angle, etc., to better evaluate the impact of driving habits on accident risks. In order to achieve comprehensive monitoring of environmental factors, the data acquisition module also integrates multiple environmental sensors to collect real-time data on surrounding weather conditions (such as temperature, humidity, rainfall), road conditions (such as traffic congestion, construction information, road conditions), etc., thereby providing a comprehensive driving environment analysis; In order to improve the accuracy and reliability of data, the data acquisition module uses cloud computing and big data technology to perform preliminary processing and storage of these real-time collected data in the background. Through high-speed data transmission networks (such as 5G networks), the collected vehicle and environmental data are quickly transmitted to the data preprocessing module for further analysis and processing. The data transmission in this process uses encryption protocols to ensure the security and privacy protection of data during transmission. The main functions of the data preprocessing module include data deduplication, data integrity check, data labeling, and data normalization operations to ensure the accuracy and effectiveness of subsequent analysis; First, data deduplication is necessary, which is achieved through the following formula: ; In this formula, represents the original data set, Represents the processed non-duplicate data set. By eliminating duplicate records, data deduplication not only reduces data redundancy, but also effectively saves computing resources and storage space, improves the efficiency of data processing, and thus improves the accuracy of the risk assessment model; Next, the data integrity check ensures that each record of the data has the required basic information and is counted using the following formula: ; here, represents the number of complete records, and is the total number of records in the data set. This process ensures that the data used for subsequent data analysis is comprehensive and available, which helps improve the model's ability to identify potential risks. After data deduplication and integrity check, the module will perform data labeling to add contextual information or classification labels to the data to make the data more interpretable. The specific formula is as follows: ; This process can provide a clearer perspective in subsequent analysis, allowing risk assessment models to classify and learn for specific scenarios or characteristics; Finally, the data normalization step is implemented by the following formula to convert data of different dimensions into a unified range: ; in, It is the normalized data. Normalization makes the features have a unified scale and eliminates the dimension effect, thus avoiding the situation where some features dominate other features due to their large value range during model training. This process promotes the convergence speed and accuracy of the model; After the above preprocessing, high-quality data sets will be transmitted to the feature extraction module. Through effective data preprocessing, the platform can not only significantly improve the quality and efficiency of data analysis, but also enhance the reliability and scientificity of the entire risk assessment model. This series of measures ensures that subsequent feature extraction and risk assessment are more accurate, thereby providing insurance companies with more targeted risk management solutions and minimizing potential losses. At the same time, accurate data will help improve users' driving safety and lay a good foundation for the intelligent development of insurance services for new energy vehicles. The feature extraction module plays a key role in the new energy vehicle intelligent insurance risk assessment platform. Its main function is to extract driving habit features, vehicle health features, and driving environment features from the preprocessed data. These features constitute the basic data for subsequent risk assessment module analysis. Specifically, driving habit features include the driver's acceleration, braking, lane change and other behavior patterns. The extraction of these features can use statistical analysis and machine learning algorithms to quantify the safety of driving styles. For example, the comprehensive score of driving habits can be calculated using the following formula: ; in, represents the driving habit characteristic value, Indicates the statistical time period. It's in time The recorded driving habits (such as acceleration and sudden braking frequency) not only help identify high-risk driving behaviors, but also lay the foundation for insurance companies to provide customized insurance products and services; The vehicle health characteristics evaluate the technical status of new energy vehicles, mainly including battery health, engine efficiency, and maintenance status of other system components. The vehicle health characteristics score can be calculated using the following formula: ; In this formula, , and They are the health indicators of the engine, battery and suspension system, and , , is the corresponding weight value. In this way, the impact of each system on the performance of the vehicle is fully considered to help evaluate the overall safety of the vehicle; The driving environment characteristics integrate external factors such as weather and road conditions. Its characteristics can be calculated through complex data models, such as: ; here Indicates weather conditions, Indicates road conditions. The driving time is a dynamic assessment that takes into account the impact of environmental changes on driving safety and can more accurately reflect the risk level. The risk assessment module conducts new energy vehicle insurance risk assessment based on the features input by the feature extraction module through regression analysis. The calculation formula for the comprehensive risk score is as follows: ; in, represents the comprehensive risk score, is the driving habits score, is the vehicle health score, is the driving environment score, As a bias term, regression analysis can be used to not only quantify the contribution of each feature to the risk, but also continuously optimize the scoring system through model training; Finally, the assessment report visualization module visualizes the risk assessment report in the form of charts, such as generating risk heat maps, bar charts and pie charts. This form of visualization is intuitive and clear, making it easy for insurance companies, users and relevant decision makers to quickly understand the risk assessment results. Through clear visual presentation, insurance companies can formulate strategies efficiently, and users can better grasp their own risk status, thereby improving driving safety. This series of measures not only promotes the decision-making efficiency of insurance companies, but also provides users with more scientific protection for safe driving, truly realizing the friendly combination of technology and services.

[0019] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An artificial intelligence-based new energy vehicle intelligent insurance risk assessment platform, characterized by: It includes data acquisition module, data preprocessing module, feature extraction module, risk assessment module and assessment report visualization module; The data acquisition module is used to collect new energy vehicle related data, including vehicle data, driving behavior data, environmental data and accident technical data, and transmit the above collected data to the data preprocessing module; The data preprocessing module performs data deduplication, data integrity check, data labeling and data normalization operations on the new energy vehicle related data, and the processed data is transmitted to the feature extraction module; The feature extraction module performs feature extraction based on the preprocessed new energy vehicle related data, including extracting driving habit features, vehicle health features, and driving environment features; The risk assessment module performs new energy vehicle insurance risk assessment through regression analysis based on the features input by the feature extraction module, calculates the comprehensive risk score of the vehicle insurance, and generates a risk assessment report; The assessment report visualization module is used to visualize the risk assessment report in the form of charts.

2. The new energy vehicle intelligent insurance risk assessment platform based on artificial intelligence according to claim 1 is characterized by: The formula for data deduplication is as follows: ； In the formula, represents the original data set, represents the processed non-repetitive data set, Indicates the first records, , Indicates an index subscript.

3. The artificial intelligence-based new energy vehicle intelligent insurance risk assessment platform according to claim 2 is characterized by: The formula for the data integrity check is as follows: ； In the formula, Indicates the number of complete records, Representation dataset The total number of records, Indicates the first records, Indicates an index subscript.

4. The new energy vehicle intelligent insurance risk assessment platform based on artificial intelligence according to claim 3 is characterized by: The formula for the data labeling is as follows: ； In the formula, represents the labeled dataset, Indicates the first records, express .

5. The artificial intelligence-based new energy vehicle intelligent insurance risk assessment platform according to claim 4 is characterized by: The formula for data normalization is as follows: ； In the formula, represents the normalized data, Indicates the first records, represents the minimum value in the data set. Represents the maximum value in the data set.

6. The new energy vehicle intelligent insurance risk assessment platform based on artificial intelligence according to claim 5 is characterized by: The formula for extracting driving habit features is as follows: ； In the formula, represents the driving habit characteristic value, Indicates the statistical time period. Indicates at time Recorded driving habits characteristics.

7. The artificial intelligence-based new energy vehicle intelligent insurance risk assessment platform according to claim 6 is characterized by: The formula for extracting vehicle health features is as follows: ； In the formula, represents the vehicle health characteristic value, Indicates engine health indicators, Indicates the battery health indicator, Indicates the health indicator of the suspension system. , , Represents the weight of each feature.

8. The artificial intelligence-based new energy vehicle intelligent insurance risk assessment platform according to claim 7 is characterized by: The formula for extracting driving environment features is as follows: ； In the formula, represents the driving environment characteristic value, Indicates weather conditions, Indicates road conditions, Indicates driving time, Represents the environmental feature extraction formula.

9. The artificial intelligence-based new energy vehicle intelligent insurance risk assessment platform according to claim 8 is characterized by: The calculation formula of the automobile insurance comprehensive risk score is as follows: ； In the formula, represents the comprehensive risk score of automobile insurance, , , represents the weight coefficient of the corresponding feature, Represents the bias term.

10. The artificial intelligence-based new energy vehicle intelligent insurance risk assessment platform according to claim 9, characterized in that: The calculation formula of the weight coefficient is as follows: ； In the formula, Indicates The information entropy of the features, represents the number of features, represents the number of samples, represents the logarithmic function, Represents the normalized feature data.

Images