Risk model construction method and device based on similar vehicle types, equipment and medium

Abstract

The invention provides a risk model construction method and device based on similar vehicle models, equipment and a storage medium, and relates to the field of data processing. According to the method, the initial prediction model related to the slave factor is established in advance through the slave factor risk data of the similar vehicle types, so that the problem that the risk prediction model cannot be established due to the lack of risk data of the new vehicle type is avoided, the risk prediction of the new vehicle type is realized in advance, and the timeliness of the risk prediction of the new vehicle type is improved. Through the risk data residual error of the vehicle risk data and the prediction risk data, the slave vehicle factor and the corresponding risk weight, the model parameter optimization is performed on the initial prediction model, and the risk prediction model is generated, so that the establishment time of the risk prediction model of the target vehicle model is shortened, and the risk prediction accuracy of the risk prediction model is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a method, device, equipment and medium for constructing a risk model based on similar vehicle models. Background Art

[0002] In recent years, the popularity of new energy vehicles has brought many challenges to the auto insurance industry. Compared with the original traditional cars, the popularity of new energy vehicles has brought many new models. At the same time, the driving and control methods of new energy vehicles are also very different from those of traditional cars. For example, the driving speed and starting speed are often higher than expected, and the forced power recovery and single-pedal mode may cause drivers to be uncomfortable.

[0003] The above factors have put forward higher requirements for auto insurance pricing, but from the current perspective, there are still deficiencies in the assessment of risks of new energy vehicles. The most important factor is insufficient data accumulation, which leads to low accuracy in risk prediction of new models.

[0004] Therefore, how to solve the low accuracy of risk prediction for new car models has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The present application provides a method, device, equipment and storage medium for constructing a risk model based on similar vehicle models, aiming to improve the accuracy of risk prediction for new vehicle models.

[0006] In a first aspect, the present application provides a method for constructing a risk model based on similar vehicle models, the method comprising the following steps:

[0007] Establish an initial prediction model based on human factor risk data of similar models;

[0008] Based on the initial prediction model, predict the predicted risk data of the target vehicle model;

[0009] Based on at least one preset period, collecting vehicle risk data of the target vehicle model in each of the preset periods, and calculating a risk data residual between the vehicle risk data and the predicted risk data;

[0010] Based on the preset vehicle factor, the risk data residual and the risk adjustment weight corresponding to the vehicle risk data, the initial prediction model is iteratively optimized to generate a risk prediction model for the target vehicle model.

[0011] In a second aspect, the present application further provides a device for constructing a risk model based on similar vehicle models, the device for constructing a risk model based on similar vehicle models comprising:

[0012] Model building module, used to build an initial prediction model based on human factor risk data of similar vehicle models;

[0013] A risk prediction module, used to predict the predicted risk data of the target vehicle type based on the initial prediction model;

[0014] A residual calculation module, used for collecting vehicle risk data of the target vehicle type in each preset period based on at least one preset period, and calculating the risk data residual of the vehicle risk data and the predicted risk data;

[0015] The model parameter optimization module is used to iteratively optimize the initial prediction model based on a preset vehicle factor, the risk data residual, and the risk adjustment weight corresponding to the vehicle risk data to generate a risk prediction model for the target vehicle model.

[0016] In a third aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method for constructing a risk model based on similar vehicle models as described above are implemented.

[0017] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the steps of the method for constructing a risk model based on similar vehicle models as described above are implemented.

[0018] The present application provides a method, device, equipment and storage medium for constructing a risk model based on similar vehicle models. The method of the present application includes establishing an initial prediction model based on the risk data of the human factor of similar vehicle models; predicting the predicted risk data of the target vehicle model based on the initial prediction model; collecting the vehicle risk data of the target vehicle model in each preset period based on at least one preset period, and calculating the risk data residual of the vehicle risk data and the predicted risk data; iteratively optimizing the initial prediction model based on the preset vehicle factor, the risk data residual and the risk adjustment weight corresponding to the vehicle risk data, and generating the risk prediction model of the target vehicle model. In the above manner, the present application first establishes an initial prediction model related to the human factor through the risk data of the human factor of similar vehicle models, avoiding the problem that the risk prediction model cannot be established due to the lack of risk data for the new vehicle model, thereby realizing the risk prediction of the new vehicle model in advance and improving the timeliness of the risk prediction of the new vehicle model. Through the risk data residual of the vehicle risk data and the predicted risk data, the vehicle factor and its corresponding risk weight, the model parameters of the initial prediction model are optimized to generate a risk prediction model, shortening the establishment time of the risk prediction model of the target vehicle model, and improving the risk prediction accuracy of the risk prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0020] Figure 1 A schematic diagram of a flow chart of a first embodiment of a method for constructing a risk model based on similar vehicle models provided in this application;

[0021] Figure 2 A schematic diagram of the flow chart of the second embodiment of the method for constructing a risk model based on similar vehicle models provided in this application;

[0022] Figure 3 It is a structural schematic diagram of a first embodiment of a risk model building device based on similar vehicle models provided by the present application;

[0023] Figure 4 It is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application.

[0024] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0027] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0028] Please refer to Figure 1 , Figure 1 A flowchart of a first embodiment of a method for constructing a risk model based on similar vehicle models provided in this application.

[0029] like Figure 1As shown, the method for constructing a risk model based on similar vehicle models includes steps S101 to S103.

[0030] S101. Establish an initial prediction model based on human factor risk data of similar vehicle models;

[0031] In one embodiment, the biggest problem faced in modeling newly launched car models is the lack of historical accident data. The embodiment of the present application uses historical risk data of historical models similar to the new target model to screen out risk data from human factors, and establish an initial prediction model related to human factors to perform early risk prediction, so as to fill the gap in risk prediction data that is lacking in the early stages of new models.

[0032] In one embodiment, the embodiment of the present application divides the risk of vehicle accidents into two parts, one is the risk related to people, and the other is the risk related to the vehicle. First, for the risk related to people, the risk data of human factors of similar models are used to train and construct an initial prediction model related to human factors.

[0033] Specifically, human factor risk data is collected from historical vehicle risk data of similar models, including driver age, gender, driving experience, driving habits and other information. An initial prediction model is established based on the training of human factor risk data to predict the safety risk of drivers of new models (target models).

[0034] Furthermore, based on the historical vehicle risk data of similar vehicle models, the human factor risk data is screened out, wherein the human factor risk data includes age, gender, driving experience, driving habits and health status; based on data preprocessing, the human factor risk data is processed to obtain model training data; based on the regression analysis algorithm and the model training data, the initial prediction model is established.

[0035] In one embodiment, historical vehicle risk data of similar vehicle models are used to model human data. First, the historical vehicle risk data of similar vehicle models are screened, and then these historical vehicle risk data are processed based on human-related factors, that is, human factor risk data, including age, gender, driving experience, driving habits, health status, etc.

[0036] In one embodiment, the collected human factor risk data is sorted, cleaned and processed through a data preprocessing process to ensure the accuracy and completeness of the data. Then, a human-related factor regression prediction model is established as an initial prediction model using a regression analysis algorithm to predict the driving risk of the target vehicle model.

[0037] For example, assuming that a linear regression model is used to predict the accident risk R, referring to age A and driving experience E from the human factor risk data, we have:

[0038] R=β0+β1·A+β2·E+ε

[0039] Among them, β0, β1, β2 are model parameters, and ε is the error term.

[0040] In one embodiment, data preprocessing is a crucial step in the process of data analysis and machine learning. It involves cleaning, converting and normalizing the raw data to facilitate subsequent modeling and analysis. The common processes of data preprocessing are: removing unique attributes, handling missing values, attribute encoding, data standardization and regularization, feature selection, and principal component analysis. Data preprocessing can ensure the accuracy and completeness of the data, thereby improving the accuracy of model prediction.

[0041] In one embodiment, the regression analysis algorithm is to establish the regression relationship function expression (referred to as regression equation) between the dependent variable and the independent variable based on a large amount of observation data using mathematical statistics. Regression analysis is a predictive modeling technique that studies the relationship between the dependent variable (target) and the independent variable (predictor), and the uncertainty relationship (correlation relationship) between the dependent variable and the independent variable.

[0042] S102, predicting risk data of a target vehicle model based on the initial prediction model;

[0043] S103, based on at least one preset period, collecting vehicle risk data of the target vehicle model in each of the preset periods, and calculating the risk data residual between the vehicle risk data and the predicted risk data;

[0044] In one embodiment, the predicted risk data is a risk prediction value predicted using an initial prediction model.

[0045] In one embodiment, after the initial prediction model is adjusted by the vehicle factor risk data to obtain the risk prediction model for the target vehicle model, more vehicle risk data can be continuously collected, and the risk prediction model parameters can be adjusted (residual calculation, factor modeling, cleaning and processing) using the latest collected vehicle risk data to continuously optimize and iterate the risk identification effect of the risk prediction model. In this way, as the data is continuously updated, the risk prediction model can always maintain a high prediction accuracy and effectiveness. In this way, a more accurate and effective risk prediction model can be established.

[0046] In one embodiment, the preset period can be collected according to actual needs, for example, it can be set to six months, that is, the vehicle risk data is collected every six months.

[0047] In one embodiment, the vehicle risk data collected each time may be separate, that is, data collected within each preset period.

[0048] In another embodiment, the vehicle risk data collected each time may be combined with the vehicle risk data collected historically to form fused data, that is, all vehicle risk data within the range from the start time of the first vehicle risk data collection to the end time of the current vehicle risk data collection, and the risk prediction model may be iteratively optimized using the fused vehicle risk data.

[0049] In one embodiment, the vehicle risk data includes, but is not limited to, vehicle age, number of accidents, number of maintenances, repair costs, insurance claim amounts, and maintenance items.

[0050] Furthermore, based on the time correspondence, the vehicle risk data at the time corresponding to each predicted risk data is determined; and the risk data residual of the predicted risk data and the vehicle risk data corresponding to the same time is calculated.

[0051] In one embodiment, the vehicle risk data refers to the risk data actually observed and collected during the use of the target vehicle model, such as the actual number of accidents, insurance claim amounts, etc. The predicted risk data is the risk prediction value predicted using the initial prediction model.

[0052] In one embodiment, the correspondence between the predicted risk data and the vehicle risk data can be determined based on the time correspondence. For example, based on the time corresponding to the predicted risk data, the vehicle risk data at the corresponding time can be collected to form a data pair of the predicted risk data and the vehicle risk data, and then the risk data residuals of the predicted risk data and the vehicle risk data corresponding to the same time can be calculated.

[0053] For each observation, the difference between the predicted value and the actual value is calculated. i It can be calculated by the following formula:

[0054]

[0055] Among them, e i is the risk data residual of the ith observation, is the vehicle risk data of the i-th observation, is the predicted risk data for the ith observation.

[0056] In one embodiment, statistical indicators of the risk data residuals, such as mean, standard deviation, skewness, and kurtosis, may be calculated to evaluate the distribution characteristics of the risk data residuals. Ideally, the residuals are randomly distributed without obvious patterns or trends.

[0057] In one embodiment, if the mean of the risk data residuals is close to zero, it means that the initial prediction model has no systematic deviation. If the standard deviation of the risk data residuals is small, it means that the prediction performance of the initial prediction model is relatively accurate. The outliers or outliers in the risk data residuals are points where the model prediction is inaccurate. Therefore, the model parameters can be adjusted according to the results of the residual distribution to optimize the performance of the initial prediction model and improve the accuracy of the model prediction.

[0058] S104: Based on a preset vehicle factor, the risk data residual, and a risk adjustment weight corresponding to the vehicle risk data, the initial prediction model is iteratively optimized to generate a risk prediction model for the target vehicle model.

[0059] In one embodiment, the vehicle factors include vehicle age, vehicle price, and vehicle configuration.

[0060] Understandably, vehicle factors have a significant impact on vehicle risk assessment, as they are directly related to vehicle safety, repair costs, accident probability, and the frequency and severity of insurance claims.

[0061] In one embodiment, as the vehicle is used for a longer period of time, its mechanical performance may decline, increasing the probability of failure, thereby affecting risk assessment. Older vehicles may have a higher risk of failure and accidents due to wear and aging.

[0062] In one embodiment, the condition of the vehicle, including maintenance and repair history, also affects its risk assessment. The vehicle's safety configuration, such as airbags, anti-lock braking system (ABS), electronic stability control, etc., can reduce the severity of an accident.

[0063] In one embodiment, assisted driving functions and intelligent technologies, such as automatic emergency braking and blind spot monitoring, may also affect risk assessment. The frequency and purpose of use of commercial vehicles and non-commercial vehicles are different, affecting their risk exposure. New energy vehicles (such as electric vehicles) may have different risk factors, such as battery safety and the availability of charging facilities.

[0064] It is understandable that the impact of vehicle factors on risk assessment is a dynamic process, and data and models need to be constantly updated to adapt to these changes.

[0065] In this embodiment, in order to address the problem of lack of risk data in the early stage of the launch of new models, the solution adopts an initial prediction model established from human factor risk data as the basis of the risk model, and then uses vehicle factors to dynamically adjust the model parameters of the initial prediction model, gradually adjusting it to a risk prediction model suitable for the target model.

[0066] In one embodiment, the specific implementation is divided into three steps: the first step is to use the risk data residual between the predicted risk data predicted by the initial prediction model and the vehicle risk data as the modeling target of the adjustment model, that is, to use the risk data residual as the basis for adjusting the model parameters, thereby gradually reducing the risk data residual to improve the model prediction accuracy; the second step is to process vehicle factors, such as vehicle age, vehicle price, vehicle configuration, etc.; the third step is to set the risk weights of each vehicle factor to adjust the model parameters of the initial prediction model to generate the final risk prediction model.

[0067] The embodiments of the present application fully utilize the advantages of available data and models while ensuring risk control, thereby improving the accuracy of model risk prediction.

[0068] Furthermore, the length of time for collecting the vehicle risk data is obtained; and the risk weight of the vehicle factor is determined based on the length of time for collecting the vehicle risk data and the standard time length.

[0069] In one embodiment, the data collection time length is divided by one year as the adjustment weight, and the shorter the data collection time range is, the smaller the adjustment range is.

[0070] In one embodiment, the start time and end time of the collection of the vehicle risk data are recorded and determined, and the actual duration of the data collection, that is, the length of the collection time, is calculated.

[0071] In one embodiment, a standard time length is set as a reference, for example, it can be set to one year. The ratio of the vehicle risk data collection time length to the standard time length is used as a weight adjustment factor. For example, if the vehicle risk data collection time length is 6 months, the weight adjustment factor is 0.5.

[0072] Exemplarily, the risk weight of the vehicle factor is determined based on the weight adjustment factor. The risk weight can be calculated according to the following formula: risk weight = 1 / (weight adjustment factor + 1). If the weight adjustment factor is 0.5, the risk weight is 0.333 (i.e. 1 / (0.5+1)). The calculated risk weight is applied to the vehicle factor to adjust its weight in the risk assessment model.

[0073] For example, assume that the collection period of risk data for a certain vehicle is 18 months (1.5 years). The standard period is set to 1 year, and the weight adjustment factor is 1.5. The risk weight is:

[0074]

[0075] This means that during this model adjustment process, the weight of the vehicle factor will be adjusted to 0.4 to reflect the impact of the length of data collection time on risk assessment.

[0076] Furthermore, based on the residual between the vehicle risk data corresponding to each of the preset periods and the predicted risk data of the current risk prediction model, the vehicle factor and the risk weight corresponding to each of the risk factors in each of the prediction periods, the risk prediction model is iteratively optimized to generate the risk prediction model corresponding to each of the preset periods.

[0077] Exemplarily, the iterative optimization algorithm may be an algorithm such as a gradient descent method.

[0078] In this embodiment, the risk prediction model is iteratively optimized by combining residuals, vehicle factors and risk weights to adjust model parameters, which can minimize the prediction error. For each preset period, an updated risk prediction model is generated to ensure that the risk prediction model can reflect the risk characteristics of the target vehicle model in each preset period. Risk weights and model parameters are reviewed and adjusted regularly to ensure the prediction accuracy and effectiveness of the risk prediction model.

[0079] In this embodiment, compared with traditional auto insurance risk modeling, which often requires waiting for a period of time to collect enough data to establish a risk model, the method of the present application can use data to model and adjust the risk model as early as possible over time when there is a lack of modeling data for new models, and can understand the risk characteristics of new models earlier, thereby providing more accurate and effective risk prediction results for new models when they are just launched on the market.

[0080] This embodiment provides a method for constructing a risk model based on similar vehicle models. The method of this application first establishes an initial prediction model related to the human factor through the risk data of the human factor of similar vehicle models, avoiding the problem that the risk prediction model of the new vehicle model cannot be established due to the lack of risk data, thereby realizing the risk prediction of the new vehicle model in advance and improving the timeliness of the risk prediction of the new vehicle model. The model parameters of the initial prediction model are optimized through the risk data residual of the vehicle risk data and the predicted risk data, the vehicle factor and its corresponding risk weight, and a risk prediction model is generated, which shortens the time to establish the risk prediction model of the target vehicle model and improves the risk prediction accuracy of the risk prediction model.

[0081] Please refer to Figure 2 , Figure 2 This is a flow chart of the second embodiment of the method for constructing a risk model based on similar vehicle models provided in this application.

[0082] In this embodiment, Figure 2 As shown, based on the above Figure 1 In the illustrated embodiment, before step S101, the following steps are further included:

[0083] S201, based on at least one vehicle model similarity parameter and the similarity weights corresponding to the vehicle model similarity parameters, weightedly calculating the vehicle model similarity between the target vehicle model and at least one historical vehicle model;

[0084] In one embodiment, the vehicle model similarity parameters include vehicle price, vehicle type, energy type, and main configurations.

[0085] In one embodiment, for a new model (target model), similarity matching is performed from historical models using similar parameters such as vehicle price, vehicle type, energy type, and main configuration, and historical models with high similarity are found as similar models of the target model.

[0086] For example, vehicle prices can be matched according to price ranges, such as 50,000-80,000 for the first tier, 80,000-120,000 for the second tier, 120,000-150,000 for the third tier, 150,000-200,000 for the fourth tier, and so on, different vehicles can be differentiated according to price ranges.

[0087] Exemplarily, vehicle types may include passenger vehicles (such as sedans, sports cars, multi-purpose vehicles (MPV, Multi-Purpose Vehicle), SUV (Sport Utility Vehicle) and crossover vehicles, etc.), commercial vehicles (trucks, buses, etc.), motorcycles, etc.

[0088] Exemplary energy types may include gasoline, diesel, electricity, natural gas, and hybrid power, among others.

[0089] Exemplarily, the main configurations may include engine performance (such as maximum power and maximum torque, etc.), vehicle size and weight, safety configuration (such as anti-lock braking system, electronic stability program, airbags, etc.), driving assistance system (such as reversing image, radar, etc.), comfort configuration, infotainment system, tires and suspension system, etc.

[0090] In one embodiment, different models have different pricing, configuration, etc. due to different brands, but in the screening of similar models, different similarity weights can be assigned according to the degree of influence of similar parameters of different models on vehicle risk. For example, the price and main configuration of the vehicle have a greater impact on the risk of insurance, and a larger similarity weight can be assigned, while there are many reference types for vehicle types and energy types, which are mainly used to reduce the screening range and have a relatively small impact on risk assessment, so a smaller similarity weight can be assigned.

[0091] In another embodiment, weights may be evenly distributed according to the number of vehicle model similarity parameters. For example, for the four vehicle model similarity parameters of vehicle price, vehicle type, energy type, and main configuration, each vehicle model similarity parameter score may be assigned a quarter of the similarity weight, and then a weighted sum calculation may be performed to obtain the final vehicle model similarity.

[0092] For example, let P = {p1, p2, ..., p n} is a parameter set, w i is the parameter p i The weight, v target，i The target model is in parameter p i The value on v hist，i For historical models, the parameter p i The value on . Parameter similarity s i It can be calculated as follows:

[0093] s i =f(v target，i , v hist，i )

[0094] Where f is a function that may have different forms depending on the parameter type, for example:

[0095] For quantitative parameters:

[0096]

[0097] where ∈ is a small constant to avoid division by zero.

[0098] For quantitative parameters:

[0099]

[0100] Therefore, the calculation formula of vehicle model similarity S is:

[0101]

[0102] In a specific embodiment, assume two vehicle models A (target vehicle model) and B (historical vehicle model), and consider three parameters: horsepower, length, and whether there is an ABS system. The weights are 0.5, 0.3, and 0.2, respectively. The parameter values ​​of vehicle model A are (150 horsepower, 4.5 meters, with ABS), and the parameter values ​​of vehicle model B are (145 horsepower, 4.6 meters, with ABS).

[0103] The similarity of similar parameters of vehicle models is calculated as follows:

[0104] Horsepower Similarity:

[0105]

[0106] Length similarity:

[0107]

[0108] ABS Similarity:

[0109] s3=1

[0110] The weighted sum is used to obtain the similarity between models A and B:

[0111] S=0.5·s1+0.3·s2+0.2·s3=0.898

[0112] This means that the model similarity between the target model A and the historical model B is 0.898.

[0113] S202: Based on the vehicle model similarity, determine at least one of the historical vehicle models as a similar vehicle model to the target vehicle model.

[0114] Furthermore, based on the vehicle model similarities corresponding to each of the historical vehicle models, a similarity ranking is obtained; based on the similarity ranking and preset screening rules, at least one of the historical vehicle models is determined to be a similar vehicle model to the target vehicle model; wherein the preset screening rules include screening according to the number of similar vehicle models and / or screening according to a similarity threshold.

[0115] In one embodiment, the above method can be used to calculate the vehicle model similarity between the target vehicle model and multiple historical vehicle models, and then the vehicle model with the highest similarity is selected as the similar vehicle model of the target vehicle model.

[0116] In another embodiment, a similarity threshold (such as 0.9) may also be set, and all historical vehicle models with vehicle model similarity greater than or equal to the similarity threshold are taken as similar vehicle models of the target vehicle model.

[0117] In another embodiment, the vehicle model similarities may be sorted, and a number of historical vehicle models may be designated in descending order of vehicle model similarity as similar models of the target vehicle model, for example, the top three historical vehicle models in similarity ranking may be designated as similar models of the target vehicle model.

[0118] In another embodiment, a certain number of historical vehicle models may be first screened by using a similarity threshold, and then a specified number of historical vehicle models may be screened out from the screened historical vehicle models as similar vehicle models to the target vehicle model; or similar vehicle models to the target vehicle model may be screened out from the screened historical vehicle models according to a certain ratio, for example, 20% of the historical vehicle models with a vehicle model similarity of 0.8 may be screened out as similar vehicle models.

[0119] See also Figure 3 , Figure 3It is a structural schematic diagram of a first embodiment of a risk model construction device based on similar vehicle models provided in the present application, and the risk model construction device based on similar vehicle models is used to execute the aforementioned risk model construction method based on similar vehicle models.

[0120] like Figure 3 As shown, the risk model construction device 300 based on similar vehicle models includes: a model building module 301, a risk prediction module 302, a residual calculation module 303 and a model parameter optimization module 304.

[0121] A model building module 301 is used to build an initial prediction model based on human factor risk data of similar vehicle models;

[0122] A risk prediction module 302 is used to predict the predicted risk data of the target vehicle type based on the initial prediction model;

[0123] The residual calculation module 303 is used to collect the vehicle risk data of the target vehicle type in each preset period based on at least one preset period, and calculate the risk data residual of the vehicle risk data and the predicted risk data;

[0124] The model parameter optimization module 304 is used to iteratively optimize the initial prediction model based on the preset vehicle factor, the risk data residual and the risk adjustment weight corresponding to the vehicle risk data to generate a risk prediction model for the target vehicle model.

[0125] In one embodiment, the risk model construction device 300 based on similar vehicle models further includes a risk weight determination module, including:

[0126] A collection time acquisition unit, used to acquire the collection time length of the vehicle risk data;

[0127] A risk weight determination unit is used to determine the risk weight of the vehicle factor based on the collection time length and the standard time length of the vehicle risk data.

[0128] In one embodiment, the risk model building device 300 based on similar vehicle models further includes a model iteration optimization module, including:

[0129] A data collection unit, used for collecting at least one set of vehicle risk data of the target vehicle model based on at least one preset period;

[0130] A model iteration optimization unit is used to iteratively optimize the parameters of the risk prediction model based on the residual between the vehicle risk data corresponding to each preset period and the predicted risk data of the current risk prediction model, the vehicle factor, and the risk weight corresponding to each risk factor in each prediction period, so as to generate the risk prediction model corresponding to each preset period.

[0131] In one embodiment, the risk model construction device 300 based on similar vehicle models further includes a similar vehicle model determination module, including:

[0132] a similarity calculation unit, configured to weightedly calculate the vehicle model similarity between the target vehicle model and at least one historical vehicle model based on at least one vehicle model similarity parameter and a similarity weight corresponding to each of the vehicle model similarity parameters;

[0133] A similar vehicle model determination unit is used to determine, based on the vehicle model similarity, at least one of the historical vehicle models as a similar vehicle model to the target vehicle model.

[0134] In one embodiment, the similar vehicle model determining unit includes:

[0135] A similarity ranking subunit, used for obtaining a similarity ranking based on the vehicle model similarities corresponding to each of the historical vehicle models;

[0136] A similar vehicle model screening subunit, configured to determine, based on the similarity ranking and preset screening rules, that at least one of the historical vehicle models is a similar vehicle model to the target vehicle model;

[0137] The preset screening rules include screening based on the number of similar vehicle models and / or screening based on a similarity threshold.

[0138] In one embodiment, the model building module 301 includes:

[0139] A data screening unit, configured to screen out the risk data from human factors based on the historical vehicle risk data of the similar vehicle models, wherein the risk data from human factors includes age, gender, driving experience, driving habits and health status;

[0140] A data preprocessing unit, configured to perform data processing on the human factor risk data based on data preprocessing to obtain model training data;

[0141] The model building unit is used to build the initial prediction model based on the regression analysis algorithm and the model training data.

[0142] In one embodiment, the residual calculation module 303 includes:

[0143] A data corresponding unit, used for determining the vehicle risk data at the corresponding moment of each predicted risk data based on the time corresponding relationship;

[0144] The residual calculation unit is used to calculate the risk data residual of the predicted risk data and the vehicle risk data corresponding to the same moment.

[0145] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned embodiment of the risk model construction method based on similar vehicle models, and will not be repeated here.

[0146] The apparatus provided in the above embodiment may be implemented in the form of a computer program. The computer program may be Figure 4 Runs on the computer device shown.

[0147] See also Figure 4 , Figure 4 1 is a schematic block diagram of a computer device provided in an embodiment of the present application. The computer device may be a server.

[0148] See also Figure 4 The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0149] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any method for building a risk model based on similar vehicle models.

[0150] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0151] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any method for constructing a risk model based on similar vehicle models.

[0152] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0153] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0154] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0155] Establish an initial prediction model based on human factor risk data of similar models;

[0156] Based on the initial prediction model, predict the predicted risk data of the target vehicle model;

[0157] Based on at least one preset period, collecting vehicle risk data of the target vehicle model in each of the preset periods, and calculating a risk data residual between the vehicle risk data and the predicted risk data;

[0158] Based on the preset vehicle factor, the risk data residual and the risk adjustment weight corresponding to the vehicle risk data, the initial prediction model is iteratively optimized to generate a risk prediction model for the target vehicle model.

[0159] In one embodiment, before the processor implements the iterative optimization of the initial prediction model based on the preset vehicle factor, the risk data residual, and the risk adjustment weight corresponding to the vehicle risk data to generate the risk prediction model of the target vehicle model, it is also used to implement:

[0160] Obtaining the collection time length of the vehicle risk data;

[0161] The risk weight of the vehicle factor is determined based on the collection time length and the standard time length of the vehicle risk data.

[0162] In one embodiment, after the processor implements the iterative optimization of the initial prediction model based on the preset vehicle factor, the risk data residual, and the risk adjustment weight corresponding to the vehicle risk data to generate the risk prediction model of the target vehicle model, it is further used to implement:

[0163] Based on at least one preset period, collecting at least one set of vehicle risk data of the target vehicle model;

[0164] Based on the residual of the vehicle risk data corresponding to each preset period and the predicted risk data of the current risk prediction model, the vehicle factor and the risk weight corresponding to each risk factor in each prediction period, the risk prediction model is iteratively optimized to generate the risk prediction model corresponding to each preset period.

[0165] In one embodiment, before implementing the establishment of the initial prediction model based on the human factor risk data of similar vehicle models, the processor is further configured to implement:

[0166] Based on at least one vehicle model similarity parameter and the similarity weights corresponding to the vehicle model similarity parameters, weighted calculation of the vehicle model similarity between the target vehicle model and at least one historical vehicle model;

[0167] Based on the vehicle model similarity, at least one of the historical vehicle models is determined to be a similar vehicle model to the target vehicle model.

[0168] In one embodiment, when the processor implements the step of determining, based on the vehicle model similarity, at least one of the historical vehicle models as a similar vehicle model to the target vehicle model, the processor is configured to implement:

[0169] Based on the vehicle model similarities corresponding to each of the historical vehicle models, obtaining a similarity ranking;

[0170] Based on the similarity ranking and preset screening rules, determining at least one of the historical vehicle models as a similar vehicle model to the target vehicle model;

[0171] The preset screening rules include screening based on the number of similar vehicle models and / or screening based on a similarity threshold.

[0172] In one embodiment, when implementing the establishment of the initial prediction model based on the risk data of human factors of similar vehicle models, the processor is used to implement:

[0173] Based on the historical vehicle risk data of the similar vehicle models, the human factor risk data is screened out, wherein the human factor risk data includes age, gender, driving experience, driving habits and health status;

[0174] Based on data preprocessing, data processing is performed on the human factor risk data to obtain model training data;

[0175] The initial prediction model is established based on the regression analysis algorithm and the model training data.

[0176] In one embodiment, when the processor implements the calculation of the risk data residual of the vehicle risk data and the predicted risk data, it is used to implement:

[0177] Determining the vehicle risk data at the time corresponding to each predicted risk data based on the time correspondence;

[0178] The risk data residual corresponding to the predicted risk data and the vehicle risk data at the same time is calculated.

[0179] A computer-readable storage medium is also provided in an embodiment of the present application, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement any of the risk model construction methods based on similar vehicle models provided in the embodiments of the present application.

[0180] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.

[0181] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for constructing a risk model based on similar vehicle models, characterized in that: The method comprises: Establish an initial prediction model based on human factor risk data of similar models; Based on the initial prediction model, predict the predicted risk data of the target vehicle model; Based on at least one preset period, collecting vehicle risk data of the target vehicle model in each of the preset periods, and calculating a risk data residual between the vehicle risk data and the predicted risk data; Based on the preset vehicle factor, the risk data residual and the risk adjustment weight corresponding to the vehicle risk data, the initial prediction model is iteratively optimized to generate a risk prediction model for the target vehicle model.

2. The method for constructing a risk model based on similar vehicle models according to claim 1, characterized in that: Before the initial prediction model is iteratively optimized based on the preset vehicle factor, the risk data residual and the risk adjustment weight corresponding to the vehicle risk data to generate the risk prediction model of the target vehicle model, the method further includes: Obtaining the collection time length of the vehicle risk data; The risk weight of the vehicle factor is determined based on the collection time length and the standard time length of the vehicle risk data.

3. The method for constructing a risk model based on similar vehicle models according to claim 1, characterized in that: The iterative optimization of the initial prediction model based on the preset vehicle factor, the risk data residual and the risk adjustment weight corresponding to the vehicle risk data to generate the risk prediction model of the target vehicle model includes: Based on the residual of the vehicle risk data corresponding to each preset period and the predicted risk data of the current risk prediction model, the vehicle factor and the risk weight corresponding to each risk factor in each prediction period, the risk prediction model is iteratively optimized to generate the risk prediction model corresponding to each preset period.

4. The method for constructing a risk model based on similar vehicle models according to claim 1, characterized in that: Before establishing the initial prediction model based on the human factor risk data of similar vehicle models, the following steps are also included: Based on at least one vehicle model similarity parameter and the similarity weights corresponding to the vehicle model similarity parameters, weighted calculation of the vehicle model similarity between the target vehicle model and at least one historical vehicle model; Based on the vehicle model similarity, at least one of the historical vehicle models is determined to be a similar vehicle model to the target vehicle model.

5. The method for constructing a risk model based on similar vehicle models according to claim 4, characterized in that: The determining, based on the vehicle model similarity, at least one of the historical vehicle models as a similar vehicle model to the target vehicle model includes: Based on the vehicle model similarities corresponding to each of the historical vehicle models, obtaining a similarity ranking; Based on the similarity ranking and preset screening rules, determining at least one of the historical vehicle models as a similar vehicle model to the target vehicle model; The preset screening rules include screening based on the number of similar vehicle models and / or screening based on a similarity threshold.

6. The method for constructing a risk model based on similar vehicle models according to claim 1, characterized in that: The initial prediction model is established based on the human factor risk data of similar vehicle models, including: Based on the historical vehicle risk data of the similar vehicle models, the human factor risk data is screened out, wherein the human factor risk data includes age, gender, driving experience, driving habits and health status; Based on data preprocessing, data processing is performed on the human factor risk data to obtain model training data; The initial prediction model is established based on the regression analysis algorithm and the model training data.

7. The method for constructing a risk model based on similar vehicle models according to claim 1, characterized in that: The calculating the risk data residual of the vehicle risk data and the predicted risk data includes: Determining the vehicle risk data at the time corresponding to each predicted risk data based on the time correspondence; The risk data residual corresponding to the predicted risk data and the vehicle risk data at the same time is calculated.

8. A risk model construction device based on similar vehicle models, characterized in that: The risk model building device based on similar vehicle models includes: Model building module, used to build an initial prediction model based on human factor risk data of similar vehicle models; A risk prediction module, used to predict the predicted risk data of the target vehicle type based on the initial prediction model; A residual calculation module, used for collecting vehicle risk data of the target vehicle model in each preset period based on at least one preset period, and calculating the risk data residual of the vehicle risk data and the predicted risk data; The model parameter optimization module is used to iteratively optimize the initial prediction model based on a preset vehicle factor, the risk data residual, and the risk adjustment weight corresponding to the vehicle risk data to generate a risk prediction model for the target vehicle model.

9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method for constructing a risk model based on similar vehicle models as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the method for constructing a risk model based on similar vehicle models as claimed in any one of claims 1 to 7 are implemented.

Images