Automobile financial risk intelligent identification method, system and device

Abstract

The invention discloses an automobile financial risk intelligent identification method, system and equipment, and the method comprises the steps: obtaining the target trajectory data of a target vehicle based on a positioning device disposed on the target vehicle; obtaining a target behavior track according to the target track data; obtaining the consumption possibility of at least one target behavior in the target behavior track based on GIS information according to the target behavior track; obtaining consumption data of a target vehicle owner according to the consumption possibility of at least one behavior node in the target behavior track; and obtaining risk data of the target vehicle according to the consumption data of the owner of the target vehicle. The problems that an existing post-loan risk assessment method depends on more user privacy data such as data of other loans, income data and asset data, the user needs to authorize query of the data to achieve the data, and meanwhile leakage of the data can greatly affect privacy security of the user are solved.

Description

Technical Field

[0001] The present application relates to the field of financial management technology, and in particular to a method, system and device for intelligently identifying automobile financial risks. Background Art

[0002] The field of automotive finance technology focuses on promoting the purchase, sale and leasing of automobiles through financial tools, services and technologies, including vehicle loans, lease agreements, insurance services and credit management. In automotive finance, by providing financing support for individual and corporate car purchase needs, including credit assessment, asset management, credit risk assessment and customer relationship management, the purchase and management of vehicles are promoted, and by managing the repurchase and loan default risks associated with automobile transactions, the repayment of loans and the safety of funds are ensured, the efficiency of capital use is optimized, and financial stability and market competitiveness are improved.

[0003] Among them, the post-loan risk assessment method aims to realize the post-monitoring and management risks of auto loans, and to achieve effective prevention and control of loan risks by identifying signals that may lead to defaults at an early stage. By analyzing various factors such as the borrower's repayment behavior, changes in economic conditions, and market environment, it warns of default risks and provides corresponding disposal strategies, including readjusting repayment plans, implementing collection measures, and taking legal actions, to help financial institutions reduce losses, maintain asset value, and protect the interests of consumers and investors.

[0004] Existing post-loan risk assessment methods rely on a lot of user privacy data, such as data on other loans, income data, asset data, etc., which require users to authorize queries on these data. At the same time, the leakage of these data will also have a significant impact on user privacy security. Summary of the invention

[0005] The present invention provides a method, system and device for intelligently identifying automobile financial risks, which at least solves the problem that the existing post-loan risk assessment method relies on a lot of user privacy data, such as data on other loans, income data, asset data, etc., and requires users to authorize the query of these data. At the same time, the leakage of these data will also have a significant impact on user privacy security.

[0006] An intelligent identification method for automobile financial risks includes the following steps:

[0007] Based on a positioning device installed on the target vehicle, target trajectory data of the target vehicle is obtained, wherein the target trajectory data is configured to include data corresponding to the location and time of the target vehicle;

[0008] According to the target trajectory data, a target behavior trajectory is obtained, wherein the target behavior trajectory is configured to include data corresponding to the owner's behavior and time of the target vehicle;

[0009] According to the target behavior trajectory, based on GIS information, obtaining consumption possibility of at least one target behavior in the target behavior trajectory, the target behavior belonging to the vehicle owner's behavior;

[0010] Obtaining consumption data of a target vehicle owner according to the consumption possibility of at least one behavior node in the target behavior trajectory;

[0011] The risk data of the target vehicle is obtained based on the consumption data of the owner of the target vehicle.

[0012] Optionally, obtaining a target behavior trajectory according to the target trajectory data includes:

[0013] According to the target trajectory data, obtaining positioning time series data of the target vehicle positioning;

[0014] According to the positioning time series data, based on a preset target behavior judgment logic, obtain the behavior time corresponding to the target behavior in the positioning time series data and the positioning corresponding to the behavior time;

[0015] The target behavior trajectory is obtained according to the behavior time corresponding to the target behavior in the positioning time series data and the positioning corresponding to the behavior time.

[0016] Optionally, obtaining the consumption possibility of at least one target behavior in the target behavior trajectory based on GIS information according to the target behavior trajectory includes:

[0017] According to the target behavior trajectory, obtaining a location corresponding to at least one target behavior in the target behavior trajectory;

[0018] According to the positioning corresponding to at least one target behavior, based on GIS information, a target area corresponding to at least one target behavior in the target behavior trajectory and a target merchant corresponding to the at least one target behavior in the target area are obtained;

[0019] According to the target merchant corresponding to the at least one target behavior, the consumption possibility of at least one target behavior in the target behavior trajectory is obtained.

[0020] Optionally, obtaining the consumption possibility of at least one target behavior in the target behavior track according to the target merchant corresponding to the at least one target behavior includes:

[0021] According to the target merchant corresponding to the at least one target behavior and according to the user portrait of the target vehicle owner, obtaining the probability of the target vehicle owner consuming at each target merchant;

[0022] According to the probability of the target vehicle owner consuming at each target merchant, the consumption possibility of at least one target behavior in the target behavior trajectory is obtained.

[0023] Optionally, obtaining consumption data of the target vehicle owner according to the consumption possibility of at least one behavior node in the target behavior trajectory includes:

[0024] The consumption data of the target vehicle owner is obtained according to the probability of the target vehicle owner consuming at each target merchant and the expected consumption at each target merchant.

[0025] Optionally, obtaining the risk data of the target vehicle according to the consumption data of the owner of the target vehicle includes:

[0026] According to the consumption data and user portrait of the target vehicle owner, based on a preset asset evaluation model, the asset data and income data of the target vehicle owner are obtained;

[0027] According to the asset data and income data of the owner of the target vehicle and based on the car loan data of the target vehicle, the risk data of the target vehicle is obtained.

[0028] Optionally, obtaining the risk data of the target vehicle according to the consumption data of the owner of the target vehicle includes:

[0029] According to the consumption data of the target vehicle owner, obtaining consumption changes of at least one target behavior of the target vehicle owner;

[0030] The risk data of the target vehicle is obtained according to the consumption change of at least one target behavior of the owner of the target vehicle.

[0031] On the other hand, an intelligent identification system for automobile financial risks includes a risk warning platform and a positioning platform;

[0032] The positioning platform is configured as follows:

[0033] Communicate with a positioning device installed on the target vehicle, obtain target trajectory data of the target vehicle, and send the target trajectory data of the target vehicle to the risk warning platform, wherein the target trajectory data is configured to include data corresponding to the location and time of the target vehicle;

[0034] The risk early warning platform is configured as follows:

[0035] Receiving target trajectory data sent by the positioning platform;

[0036] According to the target trajectory data, a target behavior trajectory is obtained, wherein the target behavior trajectory is configured to include data corresponding to the owner's behavior and time of the target vehicle;

[0037] According to the target behavior trajectory, based on GIS information, obtaining consumption possibility of at least one target behavior in the target behavior trajectory, the target behavior belonging to the vehicle owner's behavior;

[0038] Obtaining consumption data of a target vehicle owner according to the consumption possibility of at least one behavior node in the target behavior trajectory;

[0039] The risk data of the target vehicle is obtained based on the consumption data of the owner of the target vehicle.

[0040] Optionally, based on GIS information, obtaining the consumption possibility of at least one target behavior in the target behavior trajectory includes:

[0041] According to the target behavior trajectory, obtaining a location corresponding to at least one target behavior in the target behavior trajectory;

[0042] According to the positioning corresponding to at least one target behavior, based on GIS information, a target area corresponding to at least one target behavior in the target behavior trajectory and a target merchant corresponding to the at least one target behavior in the target area are obtained;

[0043] According to the target merchant corresponding to the at least one target behavior, the consumption possibility of at least one target behavior in the target behavior trajectory is obtained.

[0044] On the other hand, a computer device is provided. The computer device includes a memory and a processor. The memory stores a computer program. The processor executes the computer program to implement the above method.

[0045] On the other hand, a computer storage medium stores a computer program, and a processor executes the computer program to implement the above method.

[0046] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0047] The present invention provides an intelligent identification method, system and device for automobile financial risk, comprising: obtaining target trajectory data of the target vehicle based on a positioning device installed on the target vehicle, wherein the target trajectory data is configured to include data corresponding to the positioning and time of the target vehicle; obtaining a target behavior trajectory based on the target trajectory data, wherein the target behavior trajectory is configured to include data corresponding to the owner's behavior and time of the target vehicle; obtaining the consumption possibility of at least one target behavior in the target behavior trajectory based on GIS information according to the target behavior trajectory; obtaining the consumption data of the owner of the target vehicle based on the consumption possibility of at least one behavior node in the target behavior trajectory; and obtaining the risk data of the target vehicle based on the consumption data of the owner of the target vehicle. At least the existing post-loan risk assessment method relies on a lot of user privacy data, such as data of other loans, income data, asset data, etc., which requires the user to authorize the query of these data to be realized, and at the same time, the leakage of these data will also have a greater impact on user privacy security. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the specific implementation of the present application or the technical solution in the prior art, the following is a brief introduction to the drawings required for the specific implementation or the prior art description. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale.

[0049] Figure 1 A flowchart of an intelligent identification method for automobile financial risks in this application;

[0050] Figure 2 This is a schematic diagram of the structure of a computer device in this application.

[0051] Markings in the figure: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory.

[0052] 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

[0053] In order to enable those skilled in the art to better understand the scheme of the present disclosure, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present disclosure.

[0054] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0055] Example 1

[0056] like Figure 1 As shown, a method for intelligently identifying automobile financial risks includes the following steps:

[0057] S1. Based on a positioning device installed on a target vehicle, target trajectory data of the target vehicle is obtained.

[0058] Specifically, the target trajectory data is configured to include data corresponding to the target vehicle location and time.

[0059] Optionally, based on a positioning device installed on the target vehicle, a method for obtaining target trajectory data of the target vehicle mainly includes:

[0060] The positioning device transmits the collected vehicle location information to a cloud server or other data center in real time through wireless communication technologies such as cellular networks;

[0061] The cloud server or designated application receives and stores the vehicle location information transmitted by the positioning device, and performs preliminary processing on the received data, such as deduplication and cleaning, to improve the accuracy of subsequent data analysis;

[0062] The cloud server or designated application uses data analysis techniques, such as data mining and machine learning, to analyze and process the received vehicle location information, such as by calculating parameters such as speed, acceleration, and average speed to determine the vehicle's driving trajectory and driving status;

[0063] The cloud server or designated application program smoothes the analyzed vehicle trajectory, eliminates noise and outliers, and improves the accuracy and readability of the trajectory. It can also further process and optimize the trajectory data according to actual needs, such as map matching and coordinate conversion.

[0064] The report displays the vehicle's trajectory data, driving speed, driving time and other related information, and provides query and export functions to facilitate users to view and analyze the vehicle's driving trajectory data at any time.

[0065] When collecting, processing and using vehicle location information, users shall be clearly informed of the relevant information and their consent and authorization shall be obtained.

[0066] In summary, by selecting a suitable positioning device, ensuring the security of data transmission and reception, conducting accurate data analysis and processing, realizing trajectory visualization and display, and strengthening security and privacy protection, the target trajectory data of the target vehicle can be effectively obtained based on the positioning device installed on the target vehicle.

[0067] Specifically, the target trajectory data may be structured data, including a timestamp and positioning coordinate data corresponding to the timestamp.

[0068] S2. Obtain the target behavior trajectory according to the target trajectory data.

[0069] Specifically, the target behavior trajectory is configured to include data corresponding to the owner's behavior of the target vehicle and time.

[0070] Optionally, according to the target trajectory data, the method for obtaining the target behavior trajectory mainly includes:

[0071] According to the target trajectory data, identify the vehicle status, such as driving, traffic jam, parking, etc.;

[0072] According to the identified vehicle status and the time corresponding to the vehicle status, the owner's behavior at different times is classified based on a clustering algorithm or other feature recognition or data analysis method, so as to identify the behavior patterns of the owner's behavior at different times. Specifically, the owner's behavior may include: eating breakfast, eating lunch, eating dinner, weekday entertainment, holiday entertainment, etc.;

[0073] Through the above method, the target behavior trajectory corresponding to the target trajectory data is obtained.

[0074] Specifically, the target behavior trajectory may be a column for indicating the owner's behavior added to the target trajectory data, that is, including a timestamp and the positioning coordinate data corresponding to the timestamp and the owner's behavior.

[0075] S3. According to the target behavior trajectory and based on GIS information, the consumption possibility of at least one target behavior in the target behavior trajectory is obtained.

[0076] Specifically, the target behavior belongs to the behavior of the car owner.

[0077] Optionally, consumption may be configured as the product of at least one merchant where the target behavior can consume near the location corresponding to the target behavior and the probability of consumption at the at least one merchant and the average consumption amount of the merchant.

[0078] Optionally, according to the target behavior trajectory and based on GIS information, a possible implementation method for obtaining consumption of at least one target behavior in the target behavior trajectory mainly includes:

[0079] According to the target behavior trajectory, obtaining an occurrence position of at least one target behavior in the target behavior trajectory;

[0080] According to the occurrence location of at least one target behavior, based on the GIS information, obtaining a merchant corresponding to the target behavior near the occurrence location of at least one target behavior;

[0081] According to a merchant corresponding to the target behavior near the occurrence location of at least one target behavior, the probability of the target vehicle owner consuming at the merchant and the average consumption amount at the merchant are obtained;

[0082] According to the probability of the target vehicle owner consuming at the merchant and the average consumption amount of the merchant, the consumption possibility of at least one target behavior in the target behavior trajectory is obtained.

[0083] S4. Obtain consumption data of the target vehicle owner according to the consumption possibility of at least one behavior node in the target behavior trajectory.

[0084] Optionally, the consumption data is configured to include a target behavior and at least one merchant where the target behavior can be consumed near a location corresponding to the target behavior and an expected value of consumption at at least one merchant, wherein the expected value of consumption at each merchant is equal to the probability of consumption at the merchant multiplied by the average consumption amount at the merchant.

[0085] S5. Obtain risk data of the target vehicle based on the consumption data of the owner of the target vehicle.

[0086] Optionally, the method for obtaining the risk data of the target vehicle based on the consumption data of the owner of the target vehicle mainly includes:

[0087] According to the consumption data of the target vehicle owner, the change of the target vehicle owner's consumption on at least one target behavior is obtained. When the target vehicle owner's consumption on at least one target behavior decreases, the risk of the target vehicle increases.

[0088] According to the above method, the risk data of the target vehicle is obtained.

[0089] Compared with the existing post-loan risk assessment methods that rely on more user privacy data, such as data of other loans, income data, asset data, etc., this solution only needs to obtain the target trajectory data of the target vehicle through the positioning device installed on the target vehicle, and then evaluate the financial status of the corresponding user based on the target trajectory data of the target vehicle. When buying a car with a loan, a GPS positioning device will also be installed on the vehicle in most cases. When purchasing a car and applying for a loan, the user generally authorizes the financial institution to query the relevant positioning data. Therefore, this solution can be implemented without the user authorizing more privacy data. At least it solves the problem that the existing post-loan risk assessment methods rely on more user privacy data, such as data of other loans, income data, asset data, etc., and the user needs to authorize the query of these data to be realized. At the same time, the leakage of these data will also have a greater impact on user privacy security.

[0090] Example 2

[0091] This embodiment is based on the first embodiment, and provides an intelligent identification method for automobile financial risks, including the following steps:

[0092] S1. Based on a positioning device installed on a target vehicle, target trajectory data of the target vehicle is obtained.

[0093] Specifically, the target trajectory data is configured to include data corresponding to the target vehicle location and time.

[0094] Optionally, based on a positioning device installed on the target vehicle, a method for obtaining target trajectory data of the target vehicle mainly includes:

[0095] The positioning device transmits the collected vehicle location information to a cloud server or other data center in real time through wireless communication technologies such as cellular networks;

[0096] The cloud server or designated application receives and stores the vehicle location information transmitted by the positioning device, and performs preliminary processing on the received data, such as deduplication and cleaning, to improve the accuracy of subsequent data analysis;

[0097] The cloud server or designated application uses data analysis techniques, such as data mining and machine learning, to analyze and process the received vehicle location information, such as by calculating parameters such as speed, acceleration, and average speed to determine the vehicle's driving trajectory and driving status;

[0098] The cloud server or designated application program smoothes the analyzed vehicle trajectory, eliminates noise and outliers, and improves the accuracy and readability of the trajectory. It can also further process and optimize the trajectory data according to actual needs, such as map matching and coordinate conversion.

[0099] The report displays the vehicle's trajectory data, driving speed, driving time and other related information, and provides query and export functions to facilitate users to view and analyze the vehicle's driving trajectory data at any time.

[0100] When collecting, processing and using vehicle location information, users shall be clearly informed of the relevant information and their consent and authorization shall be obtained.

[0101] In summary, by selecting a suitable positioning device, ensuring the security of data transmission and reception, conducting accurate data analysis and processing, realizing trajectory visualization and display, and strengthening security and privacy protection, the target trajectory data of the target vehicle can be effectively obtained based on the positioning device installed on the target vehicle.

[0102] Specifically, the target trajectory data may be structured data, including a timestamp and positioning coordinate data corresponding to the timestamp.

[0103] S2. Obtain the target behavior trajectory according to the target trajectory data.

[0104] Specifically, the target behavior trajectory is configured to include data corresponding to the owner's behavior of the target vehicle and time.

[0105] Optionally, according to the target trajectory data, the method for obtaining the target behavior trajectory mainly includes:

[0106] According to the target trajectory data, identify the vehicle status, such as driving, traffic jam, parking, etc.;

[0107] According to the identified vehicle status and the time corresponding to the vehicle status, the owner's behavior at different times is classified based on a clustering algorithm or other feature recognition or data analysis method, so as to identify the behavior patterns of the owner's behavior at different times. Specifically, the owner's behavior may include: eating breakfast, eating lunch, eating dinner, weekday entertainment, holiday entertainment, etc.;

[0108] Through the above method, the target behavior trajectory corresponding to the target trajectory data is obtained.

[0109] Specifically, the target behavior trajectory may be a column for indicating the owner's behavior added to the target trajectory data, that is, including a timestamp and the positioning coordinate data corresponding to the timestamp and the owner's behavior.

[0110] Optionally, the target behavior trajectory is obtained according to the target trajectory data, including:

[0111] According to the target trajectory data, the positioning time series data of the target vehicle positioning is obtained;

[0112] According to the positioning time series data, based on the preset target behavior judgment logic, the behavior time corresponding to the target behavior in the positioning time series data and the positioning corresponding to the behavior time are obtained;

[0113] The target behavior trajectory is obtained according to the behavior time corresponding to the target behavior in the positioning time series data and the positioning corresponding to the behavior time.

[0114] Optional, a target behavior judgment logic:

[0115] According to the positioning time series data, identify the vehicle state, such as driving, traffic jam, parking, etc., and obtain positioning time series data corresponding to at least one parking state according to the recognition result;

[0116] According to the positioning time series data corresponding to at least one parking state, the time corresponding to each parking state is obtained in sequence;

[0117] According to the preset target behavior time period judgment logic and the time and positioning corresponding to each parking state, the target behavior corresponding to each parking state is determined. Specifically, an example of a target behavior time period judgment logic: parking from 11:30 to 1:30 corresponds to lunch, and parking from 17:00 to 19:30 corresponds to dinner; optionally, the target behavior time period judgment logic may also include duration adjustment, such as parking for more than 15 minutes from 17:00 to 19:30 corresponds to dinner; optionally, the time parameters in the target behavior time period judgment logic may be adjusted according to the user habits of different users; optionally, positioning data may also be introduced into the target behavior time period judgment logic, such as parking in a mall for 30 minutes to 2 hours from 17:00 to 23:30 corresponds to dinner, and parking in a mall for more than 2 hours corresponds to dinner and entertainment, etc.

[0118] S3. According to the target behavior trajectory and based on GIS information, the consumption possibility of at least one target behavior in the target behavior trajectory is obtained.

[0119] Specifically, the target behavior belongs to the behavior of the car owner.

[0120] Optionally, consumption may be configured as the product of at least one merchant where the target behavior can consume near the location corresponding to the target behavior and the probability of consumption at the at least one merchant and the average consumption amount of the merchant.

[0121] Optionally, according to the target behavior trajectory and based on GIS information, a possible implementation method for obtaining consumption of at least one target behavior in the target behavior trajectory mainly includes:

[0122] According to the target behavior trajectory, obtaining an occurrence position of at least one target behavior in the target behavior trajectory;

[0123] According to the occurrence location of at least one target behavior, based on GIS information, obtain merchants corresponding to the target behavior near the occurrence location of at least one target behavior, where the merchants near the occurrence location of the target behavior are only those whose distance from the occurrence location of the target behavior is less than a preset threshold;

[0124] According to a merchant corresponding to the target behavior near the occurrence location of at least one target behavior, the probability of the target vehicle owner consuming at the merchant and the average consumption amount at the merchant are obtained;

[0125] According to the probability of the target vehicle owner consuming at the merchant and the average consumption amount of the merchant, the consumption possibility of at least one target behavior in the target behavior trajectory is obtained.

[0126] Optionally, according to the target behavior trajectory, based on GIS information, obtaining the consumption possibility of at least one target behavior in the target behavior trajectory includes:

[0127] According to the target behavior trajectory, obtaining a location corresponding to at least one target behavior in the target behavior trajectory;

[0128] According to the positioning corresponding to the at least one target behavior, based on the GIS information, a target area corresponding to the at least one target behavior in the target behavior trajectory and a target merchant corresponding to the at least one target behavior in the target area are obtained;

[0129] According to a target merchant corresponding to at least one target behavior, a consumption possibility of at least one target behavior in a target behavior track is obtained.

[0130] Optionally, obtaining the consumption possibility of at least one target behavior in the target behavior track according to the target merchant corresponding to the at least one target behavior includes:

[0131] According to the target merchant corresponding to at least one target behavior and according to the user portrait of the target vehicle owner, the probability of the target vehicle owner consuming at each target merchant is obtained;

[0132] According to the probability of the target vehicle owner consuming at each target merchant, the consumption possibility of at least one target behavior in the target behavior trajectory is obtained.

[0133] Specifically, the user portrait of the target vehicle owner can be obtained with the user's authorization. The portrait mainly involves the user's consumption habits and does not involve specific financial data.

[0134] S4. Obtain consumption data of the target vehicle owner according to the consumption possibility of at least one behavior node in the target behavior trajectory.

[0135] Optionally, the consumption data is configured to include a target behavior and at least one merchant where the target behavior can be consumed near a location corresponding to the target behavior and an expected value of consumption at at least one merchant, wherein the expected value of consumption at each merchant is equal to the probability of consumption at the merchant multiplied by the average consumption amount at the merchant.

[0136] Optionally, based on the consumption possibility of at least one behavior node in the target behavior trajectory, the consumption data of the target vehicle owner is obtained, including:

[0137] The consumption data of the target vehicle owner is obtained according to the probability of the target vehicle owner consuming at each target merchant and the expected consumption of each target merchant.

[0138] S5. Obtain risk data of the target vehicle based on the consumption data of the owner of the target vehicle.

[0139] Optionally, the method for obtaining the risk data of the target vehicle based on the consumption data of the owner of the target vehicle mainly includes:

[0140] According to the consumption data of the target vehicle owner, the change of the target vehicle owner's consumption on at least one target behavior is obtained. When the target vehicle owner's consumption on at least one target behavior decreases, the risk of the target vehicle increases.

[0141] According to the above method, the risk data of the target vehicle is obtained.

[0142] Optionally, based on the consumption data of the owner of the target vehicle, the risk data of the target vehicle is obtained, including:

[0143] According to the consumption data and user portrait of the target vehicle owner, based on the preset asset evaluation model, the asset data and income data of the target vehicle owner are obtained;

[0144] According to the asset data and income data of the owner of the target vehicle and based on the car loan data of the target vehicle, the risk data of the target vehicle is obtained.

[0145] Optionally, the asset valuation model is configured as a model that takes consumption data and user portraits as input and asset data and income data as output. The model can be trained using relevant data collected by a professional data research organization.

[0146] Specifically, an asset valuation model for Python is configured as follows:

[0147]

[0148] data.fillna(data.mean(), inplace=True)#Fill missing values ​​with mean

[0149] # Encode categorical data into numerical values

[0150] categorical_features = ['gender', 'occupation', 'location'] # Assume these are categorical data

[0151] numerical_features = ['age', 'spending_score', 'credit_score'] # numerical features

[0152] #3. Feature Engineering

[0153] #You can further extract features or generate interactive features, etc.

[0154] #For example: consumption type ratio, household income range, etc.

[0155] #4. Feature processing and standardization

[0156] #Standardize numerical features and encode categorical features

[0157] preprocessor=ColumnTransformer(

[0158] transformers=[

[0159] ('num',StandardScaler(),numerical_features),

[0160] ('cat',OneHotEncoder(),categorical_features) ])

[0162] #5. Divide the training set and test set

[0163] X=data.drop(['asset_value','income_value','user_id'],axis=1)#Features

[0164] y=data[['asset_value','income_value']]#target variable

[0165] X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=42)

[0166] #6. Model training

[0167] #Select a regression model and use pipeline to integrate data processing and model training model = Pipeline (steps = [

[0168] ('preprocessor',preprocessor),

[0169] ('regressor',xgb.XGBRegressor(objective='reg:squarederror',n_estimators=100,random_state=42)) ])

[0171] #Train model

[0172] model.fit(X_train,y_train)

[0173] #7. Model Evaluation

[0174] #Predict on the test set

[0175] y_pred=model.predict(X_test)

[0176] #Evaluate model performance (mean square error and R 2 )

[0177] mse=mean_squared_error(y_test,y_pred)

[0178] r2=r2_score(y_test,y_pred)

[0179] print(f'Mean Squared Error:{mse}')

[0180] print(f'R 2 :{r2}')

[0181] #8. Tune the model (optional)

[0182] #Use grid search for hyperparameter tuning

[0183] param_grid = {

[0184] 'regressor__n_estimators':[100,200],

[0185] 'regressor__max_depth':[3,5,7],

[0186] 'regressor__learning_rate':[0.01,0.1,0.2]

[0187] }

[0188] grid_search=GridSearchCV(model,param_grid,cv=5,scoring='neg_mean_squared_error')

[0189] grid_search.fit(X_train,y_train)

[0190] # Output the optimal parameters

[0191] print(f'Best parameters:{grid_search.best_params_}')

[0192] #9. Use the trained model to make predictions

[0193] #Now you can use the model to predict assets and income

[0194] new_data = pd.DataFrame({

[0195] 'age':

[30] ,

[0196] 'gender':['M'],

[0197] 'spending_score':

[80] ,

[0198]

[0199] In the above example, we loaded two data sets, user_data.csv (containing the user's consumption data and user profile information) and asset_data.csv (containing the user's asset data and income data). Merge them through pd.merge();

[0200] Use fillna() to fill missing values, use one-hot encoding for categorical data (such as gender, occupation, location, etc.), and standardize numerical data (through StandardScaler);

[0201] Use ColumnTransformer to standardize numerical features and one-hot encode categorical features;

[0202] Use XGBoost regression model (XGBRegressor) to predict assets and income;

[0203] Use mean square error (MSE) and R2 to evaluate the performance of the model. The smaller the MSE and the closer the R2 is to 1, the better the model effect.

[0204] Use GridSearchCV to perform grid search and tuning to find the best hyperparameter combination;

[0205] After the model is trained and tuned, use the trained model to make predictions on new data.

[0206] Optionally, the XGBoost regression model can also be replaced with other regression models, such as RandomForestRegressor or LinearRegression, or model integration can be performed (such as weighted averaging of the prediction results of XGBoost and other models).

[0207] Optionally, based on the consumption data of the owner of the target vehicle, the risk data of the target vehicle is obtained, including:

[0208] According to the consumption data of the target vehicle owner, obtaining consumption changes of at least one target behavior of the target vehicle owner;

[0209] Risk data of the target vehicle is obtained according to consumption changes of at least one target behavior of an owner of the target vehicle.

[0210] Example 3

[0211] An intelligent identification system for automobile financial risks, including a risk warning platform and a positioning platform;

[0212] The positioning platform is configured as:

[0213] Communicate with a positioning device installed on the target vehicle, obtain target trajectory data of the target vehicle, and send the target trajectory data of the target vehicle to the risk warning platform, where the target trajectory data is configured to include data corresponding to the location and time of the target vehicle;

[0214] The risk warning platform is configured as follows:

[0215] Receive target trajectory data sent by the positioning platform;

[0216] According to the target trajectory data, a target behavior trajectory is obtained, where the target behavior trajectory is configured to include data corresponding to the owner's behavior and time of the target vehicle;

[0217] According to the target behavior trajectory, based on GIS information, obtaining the consumption possibility of at least one target behavior in the target behavior trajectory, wherein the target behavior belongs to the vehicle owner's behavior;

[0218] Obtaining consumption data of the target vehicle owner according to the consumption possibility of at least one behavior node in the target behavior trajectory;

[0219] The risk data of the target vehicle is obtained based on the consumption data of the owner of the target vehicle.

[0220] Optionally, the target behavior trajectory is obtained according to the target trajectory data, including:

[0221] According to the target trajectory data, the positioning time series data of the target vehicle positioning is obtained;

[0222] According to the positioning time series data, based on the preset target behavior judgment logic, the behavior time corresponding to the target behavior in the positioning time series data and the positioning corresponding to the behavior time are obtained;

[0223] The target behavior trajectory is obtained according to the behavior time corresponding to the target behavior in the positioning time series data and the positioning corresponding to the behavior time.

[0224] Optionally, according to the target behavior trajectory, based on GIS information, obtaining the consumption possibility of at least one target behavior in the target behavior trajectory includes:

[0225] According to the target behavior trajectory, obtaining a location corresponding to at least one target behavior in the target behavior trajectory;

[0226] According to the positioning corresponding to the at least one target behavior, based on the GIS information, a target area corresponding to the at least one target behavior in the target behavior trajectory and a target merchant corresponding to the at least one target behavior in the target area are obtained;

[0227] According to a target merchant corresponding to at least one target behavior, a consumption possibility of at least one target behavior in a target behavior track is obtained.

[0228] Optionally, obtaining the consumption possibility of at least one target behavior in the target behavior track according to the target merchant corresponding to the at least one target behavior includes:

[0229] According to the target merchant corresponding to at least one target behavior and according to the user portrait of the target vehicle owner, the probability of the target vehicle owner consuming at each target merchant is obtained;

[0230] According to the probability of the target vehicle owner consuming at each target merchant, the consumption possibility of at least one target behavior in the target behavior trajectory is obtained.

[0231] Optionally, based on the consumption possibility of at least one behavior node in the target behavior trajectory, the consumption data of the target vehicle owner is obtained, including:

[0232] The consumption data of the target vehicle owner is obtained according to the probability of the target vehicle owner consuming at each target merchant and the expected consumption of each target merchant.

[0233] Optionally, based on the consumption data of the owner of the target vehicle, the risk data of the target vehicle is obtained, including:

[0234] According to the consumption data and user portrait of the target vehicle owner, based on the preset asset evaluation model, the asset data and income data of the target vehicle owner are obtained;

[0235] According to the asset data and income data of the owner of the target vehicle and based on the car loan data of the target vehicle, the risk data of the target vehicle is obtained.

[0236] Optionally, based on the consumption data of the owner of the target vehicle, the risk data of the target vehicle is obtained, including:

[0237] According to the consumption data of the target vehicle owner, obtaining consumption changes of at least one target behavior of the target vehicle owner;

[0238] Risk data of the target vehicle is obtained according to consumption changes of at least one target behavior of an owner of the target vehicle.

[0239] Example 4

[0240] This embodiment provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the above methods.

[0241] Specifically, Figure 2 As shown, Figure 2 This is a structural diagram of a computer device in the present application, and the computer device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 105 may optionally be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) memory, or it may be a stable non-volatile memory (NVM), such as at least one disk storage; the processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0242] Those skilled in the art will appreciate that Figure 2 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0243] like Figure 2 As shown, the memory 105 as a storage medium may include an operating system, a network communication module, a user interface module, and an application program for implementing an intelligent identification method for automobile financial risks.

[0244] exist Figure 2 In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in the present application can be set in the electronic device, and the electronic device calls the application program stored in the memory 105 for implementing an intelligent identification method for automobile financial risks through the processor 101 to implement the above method.

[0245] Example 5

[0246] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and a processor executes the computer program to implement any of the above methods.

[0247] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0248] In the above embodiments of the present disclosure, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0249] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0250] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0251] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0252] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a non-volatile storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present disclosure. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0253] The above are only preferred embodiments of the present disclosure. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications should also be regarded as the protection scope of the present disclosure.

Claims

1. An intelligent identification method for automobile financial risks, characterized in that: The following steps are involved: Based on a positioning device installed on the target vehicle, target trajectory data of the target vehicle is obtained, wherein the target trajectory data is configured to include data corresponding to the location and time of the target vehicle; According to the target trajectory data, a target behavior trajectory is obtained, wherein the target behavior trajectory is configured to include data corresponding to the owner's behavior and time of the target vehicle; According to the target behavior trajectory, based on GIS information, obtaining consumption possibility of at least one target behavior in the target behavior trajectory, the target behavior belonging to the vehicle owner's behavior; Obtaining consumption data of a target vehicle owner according to the consumption possibility of at least one behavior node in the target behavior trajectory; The risk data of the target vehicle is obtained based on the consumption data of the owner of the target vehicle.

2. The method for intelligently identifying automobile financial risks according to claim 1, characterized in that: The step of obtaining a target behavior trajectory according to the target trajectory data includes: According to the target trajectory data, obtaining positioning time series data of the target vehicle positioning; According to the positioning time series data, based on a preset target behavior judgment logic, obtain the behavior time corresponding to the target behavior in the positioning time series data and the positioning corresponding to the behavior time; The target behavior trajectory is obtained according to the behavior time corresponding to the target behavior in the positioning time series data and the positioning corresponding to the behavior time.

3. The method for intelligently identifying automobile financial risks according to claim 1, characterized in that: The obtaining, according to the target behavior trajectory and based on GIS information, the consumption possibility of at least one target behavior in the target behavior trajectory includes: According to the target behavior trajectory, obtaining a location corresponding to at least one target behavior in the target behavior trajectory; According to the positioning corresponding to at least one target behavior, based on GIS information, a target area corresponding to at least one target behavior in the target behavior trajectory and a target merchant corresponding to the at least one target behavior in the target area are obtained; According to the target merchant corresponding to the at least one target behavior, the consumption possibility of at least one target behavior in the target behavior trajectory is obtained.

4. The method for intelligently identifying automobile financial risks according to claim 3 is characterized in that: The obtaining, according to the target merchant corresponding to the at least one target behavior, the consumption possibility of at least one target behavior in the target behavior track includes: According to the target merchant corresponding to the at least one target behavior and according to the user portrait of the target vehicle owner, obtaining the probability of the target vehicle owner consuming at each target merchant; According to the probability of the target vehicle owner consuming at each target merchant, the consumption possibility of at least one target behavior in the target behavior trajectory is obtained.

5. The method for intelligently identifying automobile financial risks according to claim 4, characterized in that: The obtaining the consumption data of the target vehicle owner according to the consumption possibility of at least one behavior node in the target behavior trajectory includes: The consumption data of the target vehicle owner is obtained according to the probability of the target vehicle owner consuming at each target merchant and the expected consumption at each target merchant.

6. The method for intelligently identifying automobile financial risks according to claim 1, characterized in that: The step of obtaining the risk data of the target vehicle based on the consumption data of the owner of the target vehicle includes: According to the consumption data and user portrait of the target vehicle owner, based on a preset asset evaluation model, the asset data and income data of the target vehicle owner are obtained; According to the asset data and income data of the owner of the target vehicle and based on the car loan data of the target vehicle, the risk data of the target vehicle is obtained.

7. The method for intelligently identifying automobile financial risks according to claim 1, characterized in that: The step of obtaining the risk data of the target vehicle based on the consumption data of the owner of the target vehicle includes: According to the consumption data of the target vehicle owner, obtaining consumption changes of at least one target behavior of the target vehicle owner; The risk data of the target vehicle is obtained according to the consumption change of at least one target behavior of the owner of the target vehicle.

8. An intelligent identification system for automobile financial risks, characterized in that: Including risk warning platform and positioning platform; The positioning platform is configured as follows: Communicate with a positioning device installed on the target vehicle, obtain target trajectory data of the target vehicle, and send the target trajectory data of the target vehicle to the risk warning platform, wherein the target trajectory data is configured to include data corresponding to the location and time of the target vehicle; The risk early warning platform is configured as follows: Receiving target trajectory data sent by the positioning platform; According to the target trajectory data, a target behavior trajectory is obtained, wherein the target behavior trajectory is configured to include data corresponding to the owner's behavior and time of the target vehicle; According to the target behavior trajectory, based on GIS information, obtaining consumption possibility of at least one target behavior in the target behavior trajectory, the target behavior belonging to the vehicle owner's behavior; Obtaining consumption data of a target vehicle owner according to the consumption possibility of at least one behavior node in the target behavior trajectory; The risk data of the target vehicle is obtained based on the consumption data of the owner of the target vehicle.

9. The intelligent identification system for automobile financial risks according to claim 8 is characterized in that: The obtaining, according to the target behavior trajectory and based on GIS information, the consumption possibility of at least one target behavior in the target behavior trajectory includes: According to the target behavior trajectory, obtaining a location corresponding to at least one target behavior in the target behavior trajectory; According to the positioning corresponding to at least one target behavior, based on GIS information, a target area corresponding to at least one target behavior in the target behavior trajectory and a target merchant corresponding to the at least one target behavior in the target area are obtained; According to the target merchant corresponding to the at least one target behavior, the consumption possibility of at least one target behavior in the target behavior trajectory is obtained.

10. A device, characterized in that: The device comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the computer program to implement the method according to any one of claims 1 to 7.

Images